- Kernel - mailweb.openeuler.org

[PATCH 07/15] Complete the developing of hikptool ub_dfx function
by veega2022 06 Oct '23

06 Oct '23

The hikptool ub_dfx command is submitted for the first time. This command can be used to dump register information of the LRB, PFA, and PM modules. Signed-off-by: Jianqiang Li <lijianqiang16(a)huawei.com> --- libhikptdev/include/hikptdev_plug.h | 1 + net/hikp_net_lib.h | 9 + net/ub/ub_dfx/hikp_ub_dfx.c | 319 ++++++++++++++++++++++++++++ net/ub/ub_dfx/hikp_ub_dfx.h | 100 +++++++++ tool_lib/tool_lib.h | 2 +- 5 files changed, 430 insertions(+), 1 deletion(-) create mode 100644 net/ub/ub_dfx/hikp_ub_dfx.c create mode 100644 net/ub/ub_dfx/hikp_ub_dfx.h diff --git a/libhikptdev/include/hikptdev_plug.h b/libhikptdev/include/hikptdev_plug.h index 42bea6b..56cea78 100644 --- a/libhikptdev/include/hikptdev_plug.h +++ b/libhikptdev/include/hikptdev_plug.h @@ -43,6 +43,7 @@ enum cmd_module_type { MAC_MOD = 8, DPDK_MOD = 9, CXL_MOD = 10, + UB_MOD = 11, }; void hikp_unlock(void); diff --git a/net/hikp_net_lib.h b/net/hikp_net_lib.h index cc99d0c..af0a51d 100644 --- a/net/hikp_net_lib.h +++ b/net/hikp_net_lib.h @@ -98,6 +98,15 @@ enum roce_cmd_type { GET_ROCEE_TSP_CMD, }; +enum ub_cmd_type { + GET_UNIC_PPP_CMD = 0x1, + GET_UB_DFX_INFO_CMD, + GET_UB_LINK_INFO_CMD, + GET_UB_BP_INFO_CMD, + GET_UB_CRD_INFO_CMD, + GET_UB_BASIC_INFO_CMD, +}; + #define HIKP_MAX_PF_NUM 8 #define HIKP_NIC_MAX_FUNC_NUM 256 diff --git a/net/ub/ub_dfx/hikp_ub_dfx.c b/net/ub/ub_dfx/hikp_ub_dfx.c new file mode 100644 index 0000000..c50f555 --- /dev/null +++ b/net/ub/ub_dfx/hikp_ub_dfx.c @@ -0,0 +1,319 @@ +/* + * Copyright (c) 2023 Hisilicon Technologies Co., Ltd. + * Hikptool is licensed under Mulan PSL v2. + * You can use this software according to the terms and conditions of the Mulan PSL v2. + * You may obtain a copy of Mulan PSL v2 at: + * http://license.coscl.org.cn/MulanPSL2 + * THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, + * EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, + * MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE. + * + * See the Mulan PSL v2 for more details. + */ + +#include "tool_cmd.h" +#include "hikp_net_lib.h" +#include "hikp_ub_dfx.h" + +struct ub_dfx_param g_ub_dfx_param = { 0 }; + +static const struct dfx_module_cmd g_ub_dfx_module_parse[] = { + {"LRB", LRB_DFX_REG_DUMP}, + {"PFA", PFA_DFX_REG_DUMP}, + {"PM", PM_DFX_REG_DUMP} +}; + +static const struct dfx_type_parse g_dfx_type_parse[] = { + {INCORRECT_REG_TYPE, WIDTH_32_BIT, "INCORRECT TYPE"}, + {TYPE_32_STATS, WIDTH_32_BIT, "32 bit statistics"}, + {TYPE_32_RUNNING_STATUS, WIDTH_32_BIT, "32 bit running status"}, + {TYPE_64_STATS, WIDTH_64_BIT, "64 bit statistics"}, +}; + +static void dfx_help_info(const struct major_cmd_ctrl *self) +{ + printf("\n Usage: %s %s\n", self->cmd_ptr->name, "-i <interface>\n"); + printf("\n %s\n", self->cmd_ptr->help_info); + printf(" Options:\n\n"); + printf(" %s, %-25s %s\n", "-h", "--help", "display this help and exit"); + printf(" %s, %-25s %s\n", "-i", "--interface=<interface>", + "device target or bdf id, e.g. ubn0 or 0000:35:00.0"); + printf(" %s\n", " [-m/--module LRB/PFA/PM] : this is necessary param\n"); +} + +static int hikp_ub_dfx_help(struct major_cmd_ctrl *self, const char *argv) +{ + dfx_help_info(self); + return 0; +} + +static int hikp_ub_dfx_target(struct major_cmd_ctrl *self, const char *argv) +{ + self->err_no = tool_check_and_get_valid_bdf_id(argv, &(g_ub_dfx_param.target)); + if (self->err_no != 0) { + snprintf(self->err_str, sizeof(self->err_str), "Unknown device %s.", argv); + return self->err_no; + } + + return 0; +} + +static int hikp_ub_dfx_module_select(struct major_cmd_ctrl *self, const char *argv) +{ + size_t arr_size = HIKP_ARRAY_SIZE(g_ub_dfx_module_parse); + bool is_found; + size_t i; + + for (i = 0; i < arr_size; i++) { + is_found = strncmp(argv, (const char *)g_ub_dfx_module_parse[i].module_name, + sizeof(g_ub_dfx_module_parse[i].module_name)) == 0; + if (is_found) { + g_ub_dfx_param.sub_cmd_code = g_ub_dfx_module_parse[i].sub_cmd_code; + g_ub_dfx_param.module_idx = i; + g_ub_dfx_param.flag |= MODULE_SET_FLAG; + return 0; + } + } + dfx_help_info(self); + snprintf(self->err_str, sizeof(self->err_str), "-m/--module param error!!!"); + self->err_no = -EINVAL; + + return -EINVAL; +} + +static int hikp_ub_dfx_get_blk_data(struct hikp_cmd_ret **cmd_ret, + uint32_t blk_id, uint32_t sub_cmd_code) +{ + struct hikp_cmd_header req_header = { 0 }; + struct ub_dfx_req_para req_data = { 0 }; + + req_data.bdf = g_ub_dfx_param.target.bdf; + req_data.block_id = blk_id; + hikp_cmd_init(&req_header, UB_MOD, GET_UB_DFX_INFO_CMD, sub_cmd_code); + *cmd_ret = hikp_cmd_alloc(&req_header, &req_data, sizeof(req_data)); + + return hikp_rsp_normal_check(*cmd_ret); +} + +static int hikp_ub_get_first_blk_dfx(struct ub_dfx_rsp_head *rsp_head, uint32_t **reg_data, + uint32_t *max_dfx_size, uint32_t *version) +{ + struct ub_dfx_rsp *dfx_rsp = NULL; + struct hikp_cmd_ret *cmd_ret; + int ret; + + ret = hikp_ub_dfx_get_blk_data(&cmd_ret, 0, g_ub_dfx_param.sub_cmd_code); + if (ret < 0) + goto err_out; + + dfx_rsp = (struct ub_dfx_rsp *)(cmd_ret->rsp_data); + *version = cmd_ret->version; + *rsp_head = dfx_rsp->rsp_head; + if (rsp_head->total_blk_num == 0) { + /* if total block number is zero, set total type number to zero anyway */ + rsp_head->total_type_num = 0; + goto err_out; + } + *max_dfx_size = (uint32_t)(rsp_head->total_blk_num * MAX_DFX_DATA_NUM * sizeof(uint32_t)); + *reg_data = (uint32_t *)calloc(1, *max_dfx_size); + if (*reg_data == NULL) { + HIKP_ERROR_PRINT("malloc log memory 0x%x failed.\n", *max_dfx_size); + ret = -ENOMEM; + goto err_out; + } + + if (rsp_head->cur_blk_size > *max_dfx_size) { + free(*reg_data); + *reg_data = NULL; + HIKP_ERROR_PRINT("blk0 reg_data copy size error, data size: 0x%x, max size: 0x%x\n", + rsp_head->cur_blk_size, *max_dfx_size); + ret = -EINVAL; + goto err_out; + } + memcpy(*reg_data, dfx_rsp->reg_data, rsp_head->cur_blk_size); + + *max_dfx_size -= (uint32_t)rsp_head->cur_blk_size; +err_out: + free(cmd_ret); + cmd_ret = NULL; + + return ret; +} + +static int hikp_ub_get_blk_dfx(struct ub_dfx_rsp_head *rsp_head, uint32_t blk_id, + uint32_t *reg_data, uint32_t *max_dfx_size) +{ + struct ub_dfx_rsp *dfx_rsp = NULL; + struct hikp_cmd_ret *cmd_ret; + int ret; + + ret = hikp_ub_dfx_get_blk_data(&cmd_ret, blk_id, g_ub_dfx_param.sub_cmd_code); + if (ret < 0) + goto err_out; + + dfx_rsp = (struct ub_dfx_rsp *)(cmd_ret->rsp_data); + *rsp_head = dfx_rsp->rsp_head; + if (rsp_head->cur_blk_size > *max_dfx_size) { + HIKP_ERROR_PRINT("blk%u reg_data copy size error, " + "data size: 0x%x, max size: 0x%x\n", + blk_id, rsp_head->cur_blk_size, *max_dfx_size); + ret = -EINVAL; + goto err_out; + } + memcpy(reg_data, dfx_rsp->reg_data, rsp_head->cur_blk_size); + *max_dfx_size -= (uint32_t)rsp_head->cur_blk_size; + +err_out: + free(cmd_ret); + cmd_ret = NULL; + + return ret; +} + +static bool is_type_found(uint16_t type_id, uint32_t *index) +{ + size_t arr_size = HIKP_ARRAY_SIZE(g_dfx_type_parse); + size_t i; + + for (i = 0; i < arr_size; i++) { + if (g_dfx_type_parse[i].type_id == type_id) { + *index = i; + return true; + } + } + + return false; +} + +static void hikp_ub_dfx_print_type_head(uint8_t type_id, uint8_t *last_type_id) +{ + uint32_t index = 0; + + if (type_id != *last_type_id) { + printf("-----------------------------------------------------\n"); + if (is_type_found(type_id, &index)) + printf("type name: %s\n\n", g_dfx_type_parse[index].type_name); + else + HIKP_WARN_PRINT("type name: unknown type, type id is %u\n\n", type_id); + + *last_type_id = type_id; + } +} + +static void hikp_ub_dfx_print_b32(uint32_t num, uint32_t *reg_data) +{ + uint32_t word_num = num * WORD_NUM_PER_REG; + uint16_t offset; + uint32_t value; + uint32_t index; + uint32_t i; + + for (i = 0, index = 1; i < word_num; i = i + WORD_NUM_PER_REG, index++) { + offset = (uint16_t)HI_GET_BITFIELD(reg_data[i], 0, DFX_REG_ADDR_MASK); + value = reg_data[i + 1]; + printf("%03u: 0x%04x\t0x%08x\n", index, offset, value); + } +} + +static void hikp_ub_dfx_print_b64(uint32_t num, uint32_t *reg_data) +{ + uint32_t word_num = num * WORD_NUM_PER_REG; + uint16_t offset; + uint64_t value; + uint32_t index; + uint32_t i; + + for (i = 0, index = 1; i < word_num; i = i + WORD_NUM_PER_REG, index++) { + offset = (uint16_t)HI_GET_BITFIELD(reg_data[i], 0, DFX_REG_ADDR_MASK); + value = (uint64_t)reg_data[i + 1] | + (HI_GET_BITFIELD((uint64_t)reg_data[i], DFX_REG_VALUE_OFF, + DFX_REG_VALUE_MASK) << BIT_NUM_OF_WORD); + printf("%03u: 0x%04x\t0x%016lx\n", index, offset, value); + } +} + +static void hikp_ub_dfx_print(const struct ub_dfx_rsp_head *rsp_head, uint32_t *reg_data) +{ + struct ub_dfx_type_head *type_head; + uint8_t last_type_id = 0; + uint32_t *ptr = reg_data; + uint8_t i; + + printf("****************** module %s reg dump start ********************\n", + g_ub_dfx_module_parse[g_ub_dfx_param.module_idx].module_name); + for (i = 0; i < rsp_head->total_type_num; i++) { + type_head = (struct ub_dfx_type_head *)ptr; + if (type_head->type_id == INCORRECT_REG_TYPE) { + HIKP_ERROR_PRINT("No.%u type is incorrect reg type\n", i + 1u); + break; + } + hikp_ub_dfx_print_type_head(type_head->type_id, &last_type_id); + ptr++; + if (type_head->bit_width == WIDTH_32_BIT) { + hikp_ub_dfx_print_b32((uint32_t)type_head->reg_num, ptr); + } else if (type_head->bit_width == WIDTH_64_BIT) { + hikp_ub_dfx_print_b64((uint32_t)type_head->reg_num, ptr); + } else { + HIKP_ERROR_PRINT("type%u's bit width error.\n", type_head->type_id); + break; + } + ptr += (uint32_t)type_head->reg_num * WORD_NUM_PER_REG; + } + printf("################### ====== dump end ====== ######################\n"); +} + +static void hikp_ub_dfx_execute(struct major_cmd_ctrl *self) +{ + struct ub_dfx_rsp_head rsp_head = { 0 }; + struct ub_dfx_rsp_head tmp_head = { 0 }; + uint32_t *reg_data = NULL; + uint32_t max_dfx_size = 0; + uint32_t real_reg_size; + uint32_t version; + uint32_t i; + + if (!(g_ub_dfx_param.flag & MODULE_SET_FLAG)) { + self->err_no = -EINVAL; + snprintf(self->err_str, sizeof(self->err_str), "Please specify a module."); + dfx_help_info(self); + return; + } + + self->err_no = hikp_ub_get_first_blk_dfx(&rsp_head, &reg_data, &max_dfx_size, &version); + if (self->err_no != 0) { + snprintf(self->err_str, sizeof(self->err_str), "get the first block dfx fail."); + return; + } + real_reg_size = (uint32_t)rsp_head.cur_blk_size; + for (i = 1; i < rsp_head.total_blk_num; i++) { + self->err_no = hikp_ub_get_blk_dfx(&tmp_head, i, + reg_data + (real_reg_size / sizeof(uint32_t)), + &max_dfx_size); + if (self->err_no != 0) { + snprintf(self->err_str, sizeof(self->err_str), + "getting block%u reg fail.", i); + free(reg_data); + return; + } + real_reg_size += (uint32_t)tmp_head.cur_blk_size; + memset(&tmp_head, 0, sizeof(struct ub_dfx_rsp_head)); + } + + printf("DFX cmd version: 0x%x\n\n", version); + hikp_ub_dfx_print((const struct ub_dfx_rsp_head *)&rsp_head, reg_data); + free(reg_data); +} + +static void cmd_ub_dfx_init(void) +{ + struct major_cmd_ctrl *major_cmd = get_major_cmd(); + + major_cmd->option_count = 0; + major_cmd->execute = hikp_ub_dfx_execute; + + cmd_option_register("-h", "--help", false, hikp_ub_dfx_help); + cmd_option_register("-i", "--interface", true, hikp_ub_dfx_target); + cmd_option_register("-m", "--module", true, hikp_ub_dfx_module_select); +} + +HIKP_CMD_DECLARE("ub_dfx", "dump ub dfx info of hardware", cmd_ub_dfx_init); diff --git a/net/ub/ub_dfx/hikp_ub_dfx.h b/net/ub/ub_dfx/hikp_ub_dfx.h new file mode 100644 index 0000000..4ba37a1 --- /dev/null +++ b/net/ub/ub_dfx/hikp_ub_dfx.h @@ -0,0 +1,100 @@ +/* + * Copyright (c) 2023 Hisilicon Technologies Co., Ltd. + * Hikptool is licensed under Mulan PSL v2. + * You can use this software according to the terms and conditions of the Mulan PSL v2. + * You may obtain a copy of Mulan PSL v2 at: + * http://license.coscl.org.cn/MulanPSL2 + * THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, + * EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, + * MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE. + * + * See the Mulan PSL v2 for more details. + */ + +#ifndef HIKP_UB_DFX_H +#define HIKP_UB_DFX_H + +#include "hikp_net_lib.h" + +#define MAX_DFX_DATA_NUM 59 +#define MODULE_SET_FLAG 0x1 + +enum ub_dfx_cmd_type { + LRB_DFX_REG_DUMP = 0, + PFA_DFX_REG_DUMP = 1, + PM_DFX_REG_DUMP = 2, + INVALID_MODULE = 0xFFFFFFFF, +}; + +enum ub_dfx_reg_type { + INCORRECT_REG_TYPE = 0, + TYPE_32_STATS = 1, + TYPE_32_RUNNING_STATUS = 2, + TYPE_64_STATS = 3, + TYPE_INVALID = 255, +}; + +#define MAX_TYPE_NAME_LEN 40 + +enum ub_dfx_reg_width { + WIDTH_32_BIT = 32, + WIDTH_64_BIT = 64, +}; + +struct dfx_type_parse { + uint8_t type_id; + uint8_t bit_width; + uint8_t type_name[MAX_TYPE_NAME_LEN]; +}; + +struct ub_dfx_param { + struct tool_target target; + uint32_t sub_cmd_code; + uint8_t module_idx; + uint8_t flag; +}; + +#define MAX_MODULE_NAME_LEN 20 +struct dfx_module_cmd { + uint8_t module_name[MAX_MODULE_NAME_LEN]; + uint32_t sub_cmd_code; +}; + +struct ub_dfx_req_para { + struct bdf_t bdf; + uint8_t block_id; +}; + +struct ub_dfx_type_head { + uint8_t type_id; + uint8_t bit_width; + uint8_t reg_num; + uint8_t flag; +}; + +struct ub_dfx_rsp_head { + uint8_t total_blk_num; + uint8_t total_type_num; + uint8_t cur_blk_size; + uint8_t rsvd; +}; + +/********************************************************* + * All registers are returned as key-value pairs, and divided + * into three groups of data. + * 1. 32bit regs: R0 bit0~bit15: offset, R1 bit0~bit31: value + * 2. 64bit regs: R0 bit0~bit15: offset, R0 bit16~bit31 high16 value, R1 bit0~bit31: low32 value + *********************************************************/ +#define DFX_REG_VALUE_OFF 16 +#define DFX_REG_VALUE_MASK 0xFFFF +#define DFX_REG_ADDR_MASK 0xFFFF + +#define WORD_NUM_PER_REG 2 +#define BIT_NUM_OF_WORD 32 + +struct ub_dfx_rsp { + struct ub_dfx_rsp_head rsp_head; + uint32_t reg_data[MAX_DFX_DATA_NUM]; +}; + +#endif /* HIKP_UB_DFX_H */ diff --git a/tool_lib/tool_lib.h b/tool_lib/tool_lib.h index b211175..bf37465 100644 --- a/tool_lib/tool_lib.h +++ b/tool_lib/tool_lib.h @@ -18,7 +18,7 @@ #define TOOL_NAME "hikptool" -#define TOOL_VER "1.0.14" +#define TOOL_VER "1.0.15" #define HI_GET_BITFIELD(value, start, mask) (((value) >> (start)) & (mask)) #define HI_SET_FIELD(origin, shift, val) ((origin) |= (val) << (shift)) -- 2.36.1.windows.1

2 21

[PATCH OLK-5.10 v2 00/44] xfs: recent patches to fix xfs issues
by Long Li 28 Sep '23

28 Sep '23

Baokun Li (1): xfs: propagate the return value of xfs_log_force() to avoid soft lockup Colin Ian King (2): xfs: remove redundant initializations of pointers drop_leaf and save_leaf xfs: remove redundant pointer lip Darrick J. Wong (9): xfs: use setattr_copy to set vfs inode attributes xfs: remove kmem_zone typedef xfs: rename _zone variables to _cache xfs: compact deferred intent item structures xfs: create slab caches for frequently-used deferred items xfs: rename xfs_bmap_add_free to xfs_free_extent_later xfs: reduce the size of struct xfs_extent_free_item xfs: remove unused parameter from refcount code xfs: pass xfs_extent_free_item directly through the log intent code Dave Chinner (19): xfs: don't assert fail on perag references on teardown xfs: set prealloc flag in xfs_alloc_file_space() xfs: validity check agbnos on the AGFL xfs: validate block number being freed before adding to xefi xfs: don't reverse order of items in bulk AIL insertion xfs: use deferred frees for btree block freeing xfs: pass alloc flags through to xfs_extent_busy_flush() xfs: allow extent free intents to be retried xfs: don't block in busy flushing when freeing extents xfs: journal geometry is not properly bounds checked xfs: AGF length has never been bounds checked xfs: fix bounds check in xfs_defer_agfl_block() xfs: block reservation too large for minleft allocation xfs: punching delalloc extents on write failure is racy xfs: use byte ranges for write cleanup ranges xfs,iomap: move delalloc punching to iomap iomap: buffered write failure should not truncate the page cache xfs: xfs_bmap_punch_delalloc_range() should take a byte range xfs: fix off-by-one-block in xfs_discard_folio() Gaosheng Cui (1): xfs: remove xfs_setattr_time() declaration Guo Xuenan (1): xfs: set minleft correctly for randomly sparse inode allocations Jiapeng Chong (1): xfs: Remove redundant assignment to busy Long Li (6): xfs: fix dir3 block read verify fail during log recover Revert "xfs: propagate the return value of xfs_log_force() to avoid soft lockup" xfs: xfs_trans_cancel() path must check for log shutdown xfs: don't verify agf length when log recovery xfs: shutdown to ensure submits buffers on LSN boundaries xfs: update the last_sync_lsn with ctx start lsn yangerkun (4): xfs: keep growfs sb log item active until ail flush success xfs: fix xfs shutdown since we reserve more blocks in agfl fixup xfs: longest free extent no need consider postalloc xfs: shutdown xfs once inode double free fs/xfs/kmem.h | 4 - fs/xfs/libxfs/xfs_alloc.c | 390 +++++++++++++++++++++-------- fs/xfs/libxfs/xfs_alloc.h | 51 +++- fs/xfs/libxfs/xfs_alloc_btree.c | 2 +- fs/xfs/libxfs/xfs_attr_leaf.c | 2 - fs/xfs/libxfs/xfs_bmap.c | 90 +++---- fs/xfs/libxfs/xfs_bmap.h | 37 +-- fs/xfs/libxfs/xfs_bmap_btree.c | 27 +- fs/xfs/libxfs/xfs_btree.c | 4 +- fs/xfs/libxfs/xfs_btree.h | 2 +- fs/xfs/libxfs/xfs_da_btree.c | 6 +- fs/xfs/libxfs/xfs_da_btree.h | 3 +- fs/xfs/libxfs/xfs_defer.c | 70 +++++- fs/xfs/libxfs/xfs_defer.h | 3 + fs/xfs/libxfs/xfs_ialloc.c | 32 ++- fs/xfs/libxfs/xfs_ialloc_btree.c | 8 +- fs/xfs/libxfs/xfs_inode_fork.c | 4 +- fs/xfs/libxfs/xfs_inode_fork.h | 2 +- fs/xfs/libxfs/xfs_refcount.c | 56 +++-- fs/xfs/libxfs/xfs_refcount.h | 7 +- fs/xfs/libxfs/xfs_refcount_btree.c | 11 +- fs/xfs/libxfs/xfs_rmap.c | 21 +- fs/xfs/libxfs/xfs_rmap.h | 7 +- fs/xfs/libxfs/xfs_rmap_btree.c | 2 +- fs/xfs/libxfs/xfs_sb.c | 56 ++++- fs/xfs/libxfs/xfs_types.c | 23 ++ fs/xfs/libxfs/xfs_types.h | 2 + fs/xfs/xfs_aops.c | 32 +-- fs/xfs/xfs_bmap_item.c | 16 +- fs/xfs/xfs_bmap_item.h | 6 +- fs/xfs/xfs_bmap_util.c | 19 +- fs/xfs/xfs_bmap_util.h | 2 +- fs/xfs/xfs_buf.c | 16 +- fs/xfs/xfs_buf_item.c | 10 +- fs/xfs/xfs_buf_item.h | 11 +- fs/xfs/xfs_buf_item_recover.c | 9 +- fs/xfs/xfs_dquot.c | 26 +- fs/xfs/xfs_extent_busy.c | 36 ++- fs/xfs/xfs_extent_busy.h | 6 +- fs/xfs/xfs_extfree_item.c | 137 +++++++--- fs/xfs/xfs_extfree_item.h | 6 +- fs/xfs/xfs_file.c | 8 - fs/xfs/xfs_icache.c | 8 +- fs/xfs/xfs_icreate_item.c | 6 +- fs/xfs/xfs_icreate_item.h | 2 +- fs/xfs/xfs_inode.c | 2 +- fs/xfs/xfs_inode.h | 2 +- fs/xfs/xfs_inode_item.c | 6 +- fs/xfs/xfs_inode_item.h | 2 +- fs/xfs/xfs_iomap.c | 292 ++++++++++++++++++--- fs/xfs/xfs_iops.c | 56 +---- fs/xfs/xfs_iops.h | 1 - fs/xfs/xfs_log.c | 72 +++--- fs/xfs/xfs_log_priv.h | 2 +- fs/xfs/xfs_log_recover.c | 6 +- fs/xfs/xfs_mount.c | 12 +- fs/xfs/xfs_mru_cache.c | 2 +- fs/xfs/xfs_pnfs.c | 3 +- fs/xfs/xfs_qm.h | 2 +- fs/xfs/xfs_refcount_item.c | 16 +- fs/xfs/xfs_refcount_item.h | 6 +- fs/xfs/xfs_reflink.c | 7 +- fs/xfs/xfs_rmap_item.c | 16 +- fs/xfs/xfs_rmap_item.h | 6 +- fs/xfs/xfs_super.c | 233 ++++++++--------- fs/xfs/xfs_trans.c | 24 +- fs/xfs/xfs_trans.h | 2 +- fs/xfs/xfs_trans_ail.c | 5 +- fs/xfs/xfs_trans_dquot.c | 4 +- mm/filemap.c | 1 + 70 files changed, 1358 insertions(+), 700 deletions(-) -- 2.31.1

2 45

[PATCH openEuler-23.09 00/13] LoongArch: fix some pci problems
by Hongchen Zhang 28 Sep '23

28 Sep '23

Hongchen Zhang (13): LoongArch: fix ls2k500 bmc not work when installing iso LS7A2000 : Add quirk for OHCI device rev 0x02 PCI: Check if entry->offset already exist for mem resource PCI: Check if the pci controller can use both CFG0 and CFG1 mode to access configuration space PCI: PM: Fix pcie mrrs restoring pci: fix kabi error caused by pm_suspend_target_state LoongArch: Fixed some pcie card not scanning properly pci/quirks: ls7a2000: fix pm transition of devices under pcie port LS7A2000: PCIE: Fixup GPU card error pci: fix X server auto probe fail when both ast and etnaviv drm present LoongArch: pci root bridige set acpi companion only when not acpi_disabled. LoongArch: Fix secondary bridge routing errors pci: irq: Add early_param pci_irq_limit to limit pci irq numbers arch/loongarch/pci/acpi.c | 23 ++-- drivers/gpu/drm/loongson/loongson_module.c | 15 +++ drivers/irqchip/irq-loongson-pch-pic.c | 6 +- drivers/pci/controller/pci-loongson.c | 147 ++++++++++++++++++++- drivers/pci/msi/msi.c | 25 ++++ drivers/pci/pci.c | 20 ++- 6 files changed, 217 insertions(+), 19 deletions(-) -- 2.33.0

2 14

[PATCH openEuler-1.0-LTS] can: raw: add missing refcount for memory leak fix
by Ziyang Xuan 28 Sep '23

28 Sep '23

From: Oliver Hartkopp <socketcan(a)hartkopp.net> mainline inclusion from mainline-v6.5 commit c275a176e4b69868576e543409927ae75e3a3288 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I852NG CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------- Commit ee8b94c8510c ("can: raw: fix receiver memory leak") introduced a new reference to the CAN netdevice that has assigned CAN filters. But this new ro->dev reference did not maintain its own refcount which lead to another KASAN use-after-free splat found by Eric Dumazet. This patch ensures a proper refcount for the CAN nedevice. Fixes: ee8b94c8510c ("can: raw: fix receiver memory leak") Reported-by: Eric Dumazet <edumazet(a)google.com> Cc: Ziyang Xuan <william.xuanziyang(a)huawei.com> Signed-off-by: Oliver Hartkopp <socketcan(a)hartkopp.net> Link: https://lore.kernel.org/r/20230821144547.6658-3-socketcan@hartkopp.net Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/can/raw.c Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> --- net/can/raw.c | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-) diff --git a/net/can/raw.c b/net/can/raw.c index 26934174cd42..951d568470c5 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -287,8 +287,10 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (ro->bound) + if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); + dev_put(dev); + } if (ro->count > 1) kfree(ro->filter); @@ -392,10 +394,12 @@ static int raw_release(struct socket *sock) /* remove current filters & unregister */ if (ro->bound) { - if (ro->dev) + if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); - else + dev_put(ro->dev); + } else { raw_disable_allfilters(sock_net(sk), NULL, sk); + } } if (ro->count > 1) @@ -446,10 +450,10 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out; } if (dev->type != ARPHRD_CAN) { - dev_put(dev); err = -ENODEV; - goto out; + goto out_put_dev; } + if (!(dev->flags & IFF_UP)) notify_enetdown = 1; @@ -457,7 +461,9 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); - dev_put(dev); + if (err) + goto out_put_dev; + } else { ifindex = 0; @@ -468,18 +474,28 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->dev) + if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); - else + /* drop reference to old ro->dev */ + dev_put(ro->dev); + } else { raw_disable_allfilters(sock_net(sk), NULL, sk); + } } ro->ifindex = ifindex; ro->bound = 1; + /* bind() ok -> hold a reference for new ro->dev */ ro->dev = dev; + if (ro->dev) + dev_hold(ro->dev); } - out: +out_put_dev: + /* remove potential reference from dev_get_by_index() */ + if (dev) + dev_put(dev); +out: release_sock(sk); rtnl_unlock(); -- 2.25.1

2 1

[PATCH] socip: Return -EINVAL when the parameter check fails
by veega 28 Sep '23

28 Sep '23

From: veega2022 <zhuweijia(a)huawei.com> Return -EINVAL when the parameter check fails Signed-off-by: fangjian <f.fangjian(a)huawei.com> --- socip/hikp_socip_dumpreg.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/socip/hikp_socip_dumpreg.c b/socip/hikp_socip_dumpreg.c index 088f5dd..b74dac8 100644 --- a/socip/hikp_socip_dumpreg.c +++ b/socip/hikp_socip_dumpreg.c @@ -131,6 +131,7 @@ static void hikp_socip_dumpreg_execute(struct major_cmd_ctrl *self) struct hikp_cmd_ret *cmd_ret; if (!check_socip_dumpreg_param()) { + self->err_no = -EINVAL; cmd_socip_dump_help(self, NULL); return; } @@ -141,6 +142,7 @@ static void hikp_socip_dumpreg_execute(struct major_cmd_ctrl *self) hikp_cmd_init(&req_header, SOCIP_MOD, HIKP_SOCIP_CMD_DUMPREG, param[MODULE_ID_INDEX].val); cmd_ret = hikp_cmd_alloc(&req_header, &req_data, sizeof(req_data)); if (!cmd_ret) { + self->err_no=-EINVAL; HIKP_ERROR_PRINT("hikp_cmd_alloc\n"); return; } -- 2.33.0

1 36

[PATCH openEuler-23.09 00/13] LoongArch: fix some pci problems
by Hongchen Zhang 28 Sep '23

28 Sep '23

Hongchen Zhang (13): LoongArch: fix ls2k500 bmc not work when installing iso LS7A2000 : Add quirk for OHCI device rev 0x02 PCI: Check if entry->offset already exist for mem resource PCI: Check if the pci controller can use both CFG0 and CFG1 mode to access configuration space PCI: PM: Fix pcie mrrs restoring pci: fix kabi error caused by pm_suspend_target_state LoongArch: Fixed some pcie card not scanning properly pci/quirks: ls7a2000: fix pm transition of devices under pcie port LS7A2000: PCIE: Fixup GPU card error pci: fix X server auto probe fail when both ast and etnaviv drm present LoongArch: pci root bridige set acpi companion only when not acpi_disabled. LoongArch: Fix secondary bridge routing errors pci: irq: Add early_param pci_irq_limit to limit pci irq numbers arch/loongarch/pci/acpi.c | 23 ++-- drivers/gpu/drm/loongson/loongson_module.c | 15 +++ drivers/irqchip/irq-loongson-pch-pic.c | 6 +- drivers/pci/controller/pci-loongson.c | 147 ++++++++++++++++++++- drivers/pci/msi/msi.c | 25 ++++ drivers/pci/pci.c | 20 ++- 6 files changed, 217 insertions(+), 19 deletions(-) -- 2.33.0

1 13

[PATCH openEuler-23.09 00/14] LoongArch: fix some pci problems
by Hongchen Zhang 28 Sep '23

28 Sep '23

Hongchen Zhang (14): LoongArch: fix ls2k500 bmc not work when installing iso LS7A2000 : Add quirk for OHCI device rev 0x02 PCI: Check if entry->offset already exist for mem resource PCI: Check if the pci controller can use both CFG0 and CFG1 mode to access configuration space PCI: PM: Fix pcie mrrs restoring pci: fix kabi error caused by pm_suspend_target_state LoongArch: Fixed some pcie card not scanning properly pci/quirks: ls7a2000: fix pm transition of devices under pcie port LS7A2000: PCIE: Fixup GPU card error pci: fix X server auto probe fail when both ast and etnaviv drm present LoongArch: pci root bridige set acpi companion only when not acpi_disabled. LoongArch: Fix secondary bridge routing errors pci: irq: Add early_param pci_irq_limit to limit pci irq numbers irqchip/loongson-pch-pic: 7a1000 int_clear reg must use 64bit write. arch/loongarch/pci/acpi.c | 23 ++-- drivers/gpu/drm/loongson/loongson_module.c | 15 +++ drivers/irqchip/irq-loongson-pch-pic.c | 22 +-- drivers/pci/controller/pci-loongson.c | 147 ++++++++++++++++++++- drivers/pci/msi/msi.c | 25 ++++ drivers/pci/pci.c | 20 ++- 6 files changed, 228 insertions(+), 24 deletions(-) -- 2.33.0

1 5

[PATCH openEuler-23.09 00/11] LoongArch: some optimization and
by Hongchen Zhang 28 Sep '23

28 Sep '23

Hongchen Zhang (11): LoongArch: Adapted SECTION_SIZE_BITS with page size LoongArch: Remove redudant csr save/restore LoongArch: use 40 bits address space for user LoongArch: refresh usage of sync LoongArch: fix SECCOMP test error LoongArch: Change definition of cpu_relax() for Loongson-3 usb: xhci: add XHCI_NO_SOFT_RETRY quirk for EJ188 net: stmmac: fix potential double free of dma descriptor resources LoongArch: Remove generic irq migration irqchip/loongson-pch-pic: 7a1000 int_clear reg must use 64bit write. LoongArch: defconfig: Enable a large number of configurations arch/loongarch/Kconfig | 8 +- arch/loongarch/configs/loongson3_defconfig | 1586 +++++++++++++++-- arch/loongarch/include/asm/atomic.h | 8 + arch/loongarch/include/asm/cmpxchg.h | 2 + arch/loongarch/include/asm/futex.h | 2 + arch/loongarch/include/asm/irq.h | 1 + arch/loongarch/include/asm/pgtable.h | 7 +- arch/loongarch/include/asm/sparsemem.h | 2 +- arch/loongarch/include/asm/stackframe.h | 9 - arch/loongarch/include/asm/thread_info.h | 1 + arch/loongarch/include/asm/vdso/processor.h | 11 +- arch/loongarch/kernel/entry.S | 8 - arch/loongarch/kernel/irq.c | 36 + arch/loongarch/kernel/smp.c | 3 +- arch/loongarch/kernel/switch.S | 6 - arch/loongarch/mm/pgtable.c | 2 - drivers/irqchip/irq-loongson-pch-pic.c | 16 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 11 + drivers/usb/host/xhci-pci.c | 6 + kernel/irq/Kconfig | 4 +- 20 files changed, 1546 insertions(+), 183 deletions(-) -- 2.33.0

2 12

[PATCH openEuler-23.09 00/14] LoongArch: fix some pci problems
by Hongchen Zhang 28 Sep '23

28 Sep '23

Hongchen Zhang (14): LoongArch: fix ls2k500 bmc not work when installing iso LS7A2000 : Add quirk for OHCI device rev 0x02 PCI: Check if entry->offset already exist for mem resource PCI: Check if the pci controller can use both CFG0 and CFG1 mode to access configuration space PCI: PM: Fix pcie mrrs restoring pci: fix kabi error caused by pm_suspend_target_state LoongArch: Fixed some pcie card not scanning properly pci/quirks: ls7a2000: fix pm transition of devices under pcie port LS7A2000: PCIE: Fixup GPU card error pci: fix X server auto probe fail when both ast and etnaviv drm present LoongArch: pci root bridige set acpi companion only when not acpi_disabled. LoongArch: Fix secondary bridge routing errors pci: irq: Add early_param pci_irq_limit to limit pci irq numbers irqchip/loongson-pch-pic: 7a1000 int_clear reg must use 64bit write. arch/loongarch/pci/acpi.c | 23 ++-- drivers/gpu/drm/loongson/loongson_module.c | 15 +++ drivers/irqchip/irq-loongson-pch-pic.c | 22 +-- drivers/pci/controller/pci-loongson.c | 147 ++++++++++++++++++++- drivers/pci/msi/msi.c | 25 ++++ drivers/pci/pci.c | 20 ++- 6 files changed, 228 insertions(+), 24 deletions(-) -- 2.33.0

2 15

[PATCH openEuler-23.09 00/24] LoongArch: some fix and optimization for LoongArch machine
by Hongchen Zhang 28 Sep '23

28 Sep '23

Hongchen Zhang (24): LoongArch: fix ls2k500 bmc not work when installing iso LoongArch: Adapted SECTION_SIZE_BITS with page size LoongArch: Remove redudant csr save/restore LoongArch: use 40 bits address space for user LoongArch: refresh usage of sync LoongArch: fix SECCOMP test error LoongArch: Change definition of cpu_relax() for Loongson-3 LS7A2000 : Add quirk for OHCI device rev 0x02 PCI: Check if entry->offset already exist for mem resource PCI: Check if the pci controller can use both CFG0 and CFG1 mode to access configuration space PCI: PM: Fix pcie mrrs restoring pci: fix kabi error caused by pm_suspend_target_state LoongArch: Fixed some pcie card not scanning properly pci/quirks: ls7a2000: fix pm transition of devices under pcie port LS7A2000: PCIE: Fixup GPU card error pci: fix X server auto probe fail when both ast and etnaviv drm present LoongArch: pci root bridige set acpi companion only when not acpi_disabled. usb: xhci: add XHCI_NO_SOFT_RETRY quirk for EJ188 net: stmmac: fix potential double free of dma descriptor resources LoongArch: Fix secondary bridge routing errors LoongArch: Remove generic irq migration pci: irq: Add early_param pci_irq_limit to limit pci irq numbers irqchip/loongson-pch-pic: 7a1000 int_clear reg must use 64bit write. LoongArch: defconfig: Enable a large number of configurations arch/loongarch/Kconfig | 8 +- arch/loongarch/configs/loongson3_defconfig | 1586 +++++++++++++++-- arch/loongarch/include/asm/atomic.h | 8 + arch/loongarch/include/asm/cmpxchg.h | 2 + arch/loongarch/include/asm/futex.h | 2 + arch/loongarch/include/asm/irq.h | 1 + arch/loongarch/include/asm/pgtable.h | 7 +- arch/loongarch/include/asm/sparsemem.h | 2 +- arch/loongarch/include/asm/stackframe.h | 9 - arch/loongarch/include/asm/thread_info.h | 1 + arch/loongarch/include/asm/vdso/processor.h | 11 +- arch/loongarch/kernel/entry.S | 8 - arch/loongarch/kernel/irq.c | 36 + arch/loongarch/kernel/smp.c | 3 +- arch/loongarch/kernel/switch.S | 6 - arch/loongarch/mm/pgtable.c | 2 - arch/loongarch/pci/acpi.c | 23 +- drivers/gpu/drm/loongson/loongson_module.c | 15 + drivers/irqchip/irq-loongson-pch-pic.c | 22 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 11 + drivers/pci/controller/pci-loongson.c | 147 +- drivers/pci/msi/msi.c | 25 + drivers/pci/pci.c | 20 +- drivers/usb/host/xhci-pci.c | 6 + kernel/irq/Kconfig | 4 +- 25 files changed, 1763 insertions(+), 202 deletions(-) -- 2.33.0

1 15

[src-openeuler/rdma-core v3 0/5] Support reporting wc as software mode
by Chengchang Tang 26 Sep '23

26 Sep '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> Chengchang Tang (5): libhns: Support reporting wc as software mode libhns: return error when post send in reset state libhns: separate the initialization steps of lock libhns: assign doorbell to zero when allocate it libhns: Fix missing reset notification. providers/hns/hns_roce_u.c | 4 + providers/hns/hns_roce_u.h | 14 ++ providers/hns/hns_roce_u_db.c | 2 + providers/hns/hns_roce_u_hw_v2.c | 272 +++++++++++++++++++++++++++---- providers/hns/hns_roce_u_hw_v2.h | 2 + providers/hns/hns_roce_u_verbs.c | 147 ++++++++++++++--- 6 files changed, 387 insertions(+), 54 deletions(-) -- 2.30.0

1 5

[OLK-5.10 1/2] RDMA/hns: Fix potential UAF after reset
by Chengchang Tang 26 Sep '23

26 Sep '23

driver inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/rdma-core/issues/I83L7U ---------------------------------------------------------- Currently, the mapping relationship of reset page between kernel mode and user mode is maintained by driver. If the driver is hot-plugged (e.g. reset), the memory of the reset page is released by kernel driver, but the reset page in user mode still points to this released address which would lead to a UAF. This patch use the helper rdma_user_mmap_io() to maintain the vma mapping, rather than driver itself, which remmaps the userspace reset page to an safe zero page if driver was hot-plugged. Fixes: e8b1fec497a0 ("RDMA/hns: Kernel notify usr space to stop ring db") Signed-off-by: Chengchang Tang <tangchengchang(a)huawei.com> --- drivers/infiniband/hw/hns/hns_roce_main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index 4a16200ab950..2f0a5b2bbc50 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -675,10 +675,9 @@ static int hns_roce_mmap(struct ib_ucontext *uctx, struct vm_area_struct *vma) goto out; } - ret = remap_pfn_range(vma, vma->vm_start, - page_to_pfn(hr_dev->reset_page), - PAGE_SIZE, vma->vm_page_prot); - goto out; + prot = vma->vm_page_prot; + pfn = page_to_pfn(hr_dev->reset_page); + break; default: ret = -EINVAL; goto out; -- 2.30.0

1 1

[PATCH OLK-5.10] drm/inspur: fix compile warning
by Hongchen Zhang 26 Sep '23

26 Sep '23

LoongArch inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I84IWW ------------------------------------------ Fix the following warning of inspur BMC drm driver: drivers/gpu/drm/inspur/inspur_drm_drv.c: In function ‘inspur_pci_probe’: drivers/gpu/drm/inspur/inspur_drm_drv.c:379:29: warning: unused variable ‘priv’ [-Wunused-variable] 379 | struct inspur_drm_private *priv; | ^~~~ Fixes: b9d65551a3ad ("drm: add inspur drm driver support") Signed-off-by: Hongchen Zhang <zhanghongchen(a)loongson.cn> --- drivers/gpu/drm/inspur/inspur_drm_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/inspur/inspur_drm_drv.c b/drivers/gpu/drm/inspur/inspur_drm_drv.c index d7026e1df167..f615d6d89109 100644 --- a/drivers/gpu/drm/inspur/inspur_drm_drv.c +++ b/drivers/gpu/drm/inspur/inspur_drm_drv.c @@ -376,7 +376,7 @@ static int inspur_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { int ret = 0; - struct inspur_drm_private *priv; + struct inspur_drm_private __maybe_unused *priv; struct drm_device *dev; inspur_remove_framebuffers(pdev); -- 2.33.0

2 1

[PATCH openEuler-1.0-LTS] sched/rt: Fix RT utilization tracking during policy change
by Xia Fukun 26 Sep '23

26 Sep '23

From: Vincent Donnefort <vincent.donnefort(a)arm.com> stable inclusion from stable-5.10.50 commit c576472a051a9975e2433de6c80ed27acea2d6f9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I84IKS CVE: NA -------------------------------- [ Upstream commit fecfcbc288e9f4923f40fd23ca78a6acdc7fdf6c ] RT keeps track of the utilization on a per-rq basis with the structure avg_rt. This utilization is updated during task_tick_rt(), put_prev_task_rt() and set_next_task_rt(). However, when the current running task changes its policy, set_next_task_rt() which would usually take care of updating the utilization when the rq starts running RT tasks, will not see a such change, leaving the avg_rt structure outdated. When that very same task will be dequeued later, put_prev_task_rt() will then update the utilization, based on a wrong last_update_time, leading to a huge spike in the RT utilization signal. The signal would eventually recover from this issue after few ms. Even if no RT tasks are run, avg_rt is also updated in __update_blocked_others(). But as the CPU capacity depends partly on the avg_rt, this issue has nonetheless a significant impact on the scheduler. Fix this issue by ensuring a load update when a running task changes its policy to RT. Fixes: 371bf427 ("sched/rt: Add rt_rq utilization tracking") Signed-off-by: Vincent Donnefort <vincent.donnefort(a)arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Vincent Guittot <vincent.guittot(a)linaro.org> Link: https://lore.kernel.org/r/1624271872-211872-2-git-send-email-vincent.donnef… Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Xia Fukun <xiafukun(a)huawei.com> --- kernel/sched/rt.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 5dff9a6fe2cf..28fc1e341e17 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2242,13 +2242,20 @@ void __init init_sched_rt_class(void) static void switched_to_rt(struct rq *rq, struct task_struct *p) { /* - * If we are already running, then there's nothing - * that needs to be done. But if we are not running - * we may need to preempt the current running task. - * If that current running task is also an RT task + * If we are running, update the avg_rt tracking, as the running time + * will now on be accounted into the latter. + */ + if (task_current(rq, p)) { + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); + return; + } + + /* + * If we are not running we may need to preempt the current + * running task. If that current running task is also an RT task * then see if we can move to another run queue. */ - if (task_on_rq_queued(p) && rq->curr != p) { + if (task_on_rq_queued(p)) { #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) rt_queue_push_tasks(rq); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] cifs: Release folio lock on fscache read hit.
by ZhaoLong Wang 26 Sep '23

26 Sep '23

From: Russell Harmon via samba-technical <samba-technical(a)lists.samba.org> stable inclusion from stable-v4.19.293 commit 5a87735675147f848445f05fd1f06168188f91af category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I84IKB CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 69513dd669e243928f7450893190915a88f84a2b upstream. Under the current code, when cifs_readpage_worker is called, the call contract is that the callee should unlock the page. This is documented in the read_folio section of Documentation/filesystems/vfs.rst as: > The filesystem should unlock the folio once the read has completed, > whether it was successful or not. Without this change, when fscache is in use and cache hit occurs during a read, the page lock is leaked, producing the following stack on subsequent reads (via mmap) to the page: $ cat /proc/3890/task/12864/stack [<0>] folio_wait_bit_common+0x124/0x350 [<0>] filemap_read_folio+0xad/0xf0 [<0>] filemap_fault+0x8b1/0xab0 [<0>] __do_fault+0x39/0x150 [<0>] do_fault+0x25c/0x3e0 [<0>] __handle_mm_fault+0x6ca/0xc70 [<0>] handle_mm_fault+0xe9/0x350 [<0>] do_user_addr_fault+0x225/0x6c0 [<0>] exc_page_fault+0x84/0x1b0 [<0>] asm_exc_page_fault+0x27/0x30 This requires a reboot to resolve; it is a deadlock. Note however that the call to cifs_readpage_from_fscache does mark the page clean, but does not free the folio lock. This happens in __cifs_readpage_from_fscache on success. Releasing the lock at that point however is not appropriate as cifs_readahead also calls cifs_readpage_from_fscache and *does* unconditionally release the lock after its return. This change therefore effectively makes cifs_readpage_worker work like cifs_readahead. Signed-off-by: Russell Harmon <russ(a)har.mn> Acked-by: Paulo Alcantara (SUSE) <pc(a)manguebit.com> Reviewed-by: David Howells <dhowells(a)redhat.com> Cc: stable(a)vger.kernel.org Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> --- fs/cifs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index bc3d0d76c2c4..875cb44ba573 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4005,9 +4005,9 @@ static int cifs_readpage_worker(struct file *file, struct page *page, io_error: kunmap(page); - unlock_page(page); read_complete: + unlock_page(page); return rc; } -- 2.34.3

2 1

[PATCH OLK-5.10] xfrm6: fix inet6_dev refcount underflow problem
by Zhengchao Shao 26 Sep '23

26 Sep '23

From: Lu Wei <luwei32(a)huawei.com> maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I84HSL Reference: https://lore.kernel.org/netdev/CADvbK_euiOKytyFd6KYgNoM5SbDcyz92Li=K7P48H35… -------------------------------- There are race conditions that may lead to inet6_dev refcount underflow in xfrm6_dst_destroy() and rt6_uncached_list_flush_dev(). One of the refcount underflow bugs is shown below: (cpu 1) | (cpu 2) xfrm6_dst_destroy() | ... | in6_dev_put() | | rt6_uncached_list_flush_dev() ... | ... | in6_dev_put() rt6_uncached_list_del() | ... ... | xfrm6_dst_destroy() calls rt6_uncached_list_del() after in6_dev_put(), so rt6_uncached_list_flush_dev() has a chance to call in6_dev_put() again for the same inet6_dev. Fix it by moving in6_dev_put() after rt6_uncached_list_del() in xfrm6_dst_destroy(). Fixes: 510c321b5571 ("xfrm: reuse uncached_list to track xdsts") Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> Reviewed-by: Xin Long <lucien.xin(a)gmail.com> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv6/xfrm6_policy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 247296e3294b..4c3aa97f23fa 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -120,11 +120,11 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt6.rt6i_idev)) - in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); if (xdst->u.rt6.rt6i_uncached_list) rt6_uncached_list_del(&xdst->u.rt6); + if (likely(xdst->u.rt6.rt6i_idev)) + in6_dev_put(xdst->u.rt6.rt6i_idev); xfrm_dst_destroy(xdst); } -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] xfrm6: fix inet6_dev refcount underflow problem
by Zhengchao Shao 26 Sep '23

26 Sep '23

From: Lu Wei <luwei32(a)huawei.com> maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I84HSL Reference: https://lore.kernel.org/netdev/CADvbK_euiOKytyFd6KYgNoM5SbDcyz92Li=K7P48H35… -------------------------------- There are race conditions that may lead to inet6_dev refcount underflow in xfrm6_dst_destroy() and rt6_uncached_list_flush_dev(). One of the refcount underflow bugs is shown below: (cpu 1) | (cpu 2) xfrm6_dst_destroy() | ... | in6_dev_put() | | rt6_uncached_list_flush_dev() ... | ... | in6_dev_put() rt6_uncached_list_del() | ... ... | xfrm6_dst_destroy() calls rt6_uncached_list_del() after in6_dev_put(), so rt6_uncached_list_flush_dev() has a chance to call in6_dev_put() again for the same inet6_dev. Fix it by moving in6_dev_put() after rt6_uncached_list_del() in xfrm6_dst_destroy(). Fixes: 510c321b5571 ("xfrm: reuse uncached_list to track xdsts") Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> Reviewed-by: Xin Long <lucien.xin(a)gmail.com> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv6/xfrm6_policy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 30232591cf2b..cfe650cddeb6 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -243,11 +243,11 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt6.rt6i_idev)) - in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); if (xdst->u.rt6.rt6i_uncached_list) rt6_uncached_list_del(&xdst->u.rt6); + if (likely(xdst->u.rt6.rt6i_idev)) + in6_dev_put(xdst->u.rt6.rt6i_idev); xfrm_dst_destroy(xdst); } -- 2.34.1

2 1

[PATCH OLK-5.10 00/44] xfs: recent patches to fix xfs issues
by Long Li 26 Sep '23

26 Sep '23

Baokun Li (1): xfs: propagate the return value of xfs_log_force() to avoid soft lockup Colin Ian King (2): xfs: remove redundant initializations of pointers drop_leaf and save_leaf xfs: remove redundant pointer lip Darrick J. Wong (9): xfs: use setattr_copy to set vfs inode attributes xfs: remove kmem_zone typedef xfs: rename _zone variables to _cache xfs: compact deferred intent item structures xfs: create slab caches for frequently-used deferred items xfs: rename xfs_bmap_add_free to xfs_free_extent_later xfs: reduce the size of struct xfs_extent_free_item xfs: remove unused parameter from refcount code xfs: pass xfs_extent_free_item directly through the log intent code Dave Chinner (19): xfs: don't assert fail on perag references on teardown xfs: set prealloc flag in xfs_alloc_file_space() xfs: validity check agbnos on the AGFL xfs: validate block number being freed before adding to xefi xfs: don't reverse order of items in bulk AIL insertion xfs: use deferred frees for btree block freeing xfs: pass alloc flags through to xfs_extent_busy_flush() xfs: allow extent free intents to be retried xfs: don't block in busy flushing when freeing extents xfs: journal geometry is not properly bounds checked xfs: AGF length has never been bounds checked xfs: fix bounds check in xfs_defer_agfl_block() xfs: block reservation too large for minleft allocation xfs: punching delalloc extents on write failure is racy xfs: use byte ranges for write cleanup ranges xfs,iomap: move delalloc punching to iomap iomap: buffered write failure should not truncate the page cache xfs: xfs_bmap_punch_delalloc_range() should take a byte range xfs: fix off-by-one-block in xfs_discard_folio() Gaosheng Cui (1): xfs: remove xfs_setattr_time() declaration Guo Xuenan (1): xfs: set minleft correctly for randomly sparse inode allocations Jiapeng Chong (1): xfs: Remove redundant assignment to busy Long Li (6): xfs: fix dir3 block read verify fail during log recover Revert "[Huawei] xfs: propagate the return value of xfs_log_force() to avoid soft lockup" xfs: xfs_trans_cancel() path must check for log shutdown xfs: don't verify agf length when log recovery xfs: shutdown to ensure submits buffers on LSN boundaries xfs: update the last_sync_lsn with ctx start lsn yangerkun (4): xfs: keep growfs sb log item active until ail flush success xfs: fix xfs shutdown since we reserve more blocks in agfl fixup xfs: longest free extent no need consider postalloc xfs: shutdown xfs once inode double free fs/xfs/kmem.h | 4 - fs/xfs/libxfs/xfs_alloc.c | 390 +++++++++++++++++++++-------- fs/xfs/libxfs/xfs_alloc.h | 51 +++- fs/xfs/libxfs/xfs_alloc_btree.c | 2 +- fs/xfs/libxfs/xfs_attr_leaf.c | 2 - fs/xfs/libxfs/xfs_bmap.c | 90 +++---- fs/xfs/libxfs/xfs_bmap.h | 37 +-- fs/xfs/libxfs/xfs_bmap_btree.c | 27 +- fs/xfs/libxfs/xfs_btree.c | 4 +- fs/xfs/libxfs/xfs_btree.h | 2 +- fs/xfs/libxfs/xfs_da_btree.c | 6 +- fs/xfs/libxfs/xfs_da_btree.h | 3 +- fs/xfs/libxfs/xfs_defer.c | 70 +++++- fs/xfs/libxfs/xfs_defer.h | 3 + fs/xfs/libxfs/xfs_ialloc.c | 32 ++- fs/xfs/libxfs/xfs_ialloc_btree.c | 8 +- fs/xfs/libxfs/xfs_inode_fork.c | 4 +- fs/xfs/libxfs/xfs_inode_fork.h | 2 +- fs/xfs/libxfs/xfs_refcount.c | 56 +++-- fs/xfs/libxfs/xfs_refcount.h | 7 +- fs/xfs/libxfs/xfs_refcount_btree.c | 11 +- fs/xfs/libxfs/xfs_rmap.c | 21 +- fs/xfs/libxfs/xfs_rmap.h | 7 +- fs/xfs/libxfs/xfs_rmap_btree.c | 2 +- fs/xfs/libxfs/xfs_sb.c | 56 ++++- fs/xfs/libxfs/xfs_types.c | 23 ++ fs/xfs/libxfs/xfs_types.h | 2 + fs/xfs/xfs_aops.c | 32 +-- fs/xfs/xfs_bmap_item.c | 16 +- fs/xfs/xfs_bmap_item.h | 6 +- fs/xfs/xfs_bmap_util.c | 19 +- fs/xfs/xfs_bmap_util.h | 2 +- fs/xfs/xfs_buf.c | 16 +- fs/xfs/xfs_buf_item.c | 10 +- fs/xfs/xfs_buf_item.h | 11 +- fs/xfs/xfs_buf_item_recover.c | 9 +- fs/xfs/xfs_dquot.c | 26 +- fs/xfs/xfs_extent_busy.c | 36 ++- fs/xfs/xfs_extent_busy.h | 6 +- fs/xfs/xfs_extfree_item.c | 137 +++++++--- fs/xfs/xfs_extfree_item.h | 6 +- fs/xfs/xfs_file.c | 8 - fs/xfs/xfs_icache.c | 8 +- fs/xfs/xfs_icreate_item.c | 6 +- fs/xfs/xfs_icreate_item.h | 2 +- fs/xfs/xfs_inode.c | 2 +- fs/xfs/xfs_inode.h | 2 +- fs/xfs/xfs_inode_item.c | 6 +- fs/xfs/xfs_inode_item.h | 2 +- fs/xfs/xfs_iomap.c | 292 ++++++++++++++++++--- fs/xfs/xfs_iops.c | 56 +---- fs/xfs/xfs_iops.h | 1 - fs/xfs/xfs_log.c | 72 +++--- fs/xfs/xfs_log_priv.h | 2 +- fs/xfs/xfs_log_recover.c | 6 +- fs/xfs/xfs_mount.c | 12 +- fs/xfs/xfs_mru_cache.c | 2 +- fs/xfs/xfs_pnfs.c | 3 +- fs/xfs/xfs_qm.h | 2 +- fs/xfs/xfs_refcount_item.c | 16 +- fs/xfs/xfs_refcount_item.h | 6 +- fs/xfs/xfs_reflink.c | 7 +- fs/xfs/xfs_rmap_item.c | 16 +- fs/xfs/xfs_rmap_item.h | 6 +- fs/xfs/xfs_super.c | 233 ++++++++--------- fs/xfs/xfs_trans.c | 24 +- fs/xfs/xfs_trans.h | 2 +- fs/xfs/xfs_trans_ail.c | 5 +- fs/xfs/xfs_trans_dquot.c | 4 +- 69 files changed, 1357 insertions(+), 700 deletions(-) -- 2.31.1

2 45

[PATCH openEuler-22.03-LTS-SP2] scsi: lpfc: Fix ioremap issues in lpfc_sli4_pci_mem_setup()
by Yong Hu 26 Sep '23

26 Sep '23

From: Shuchang Li <lishuchang(a)hust.edu.cn> stable inclusion from stable-v5.10.180 commit bab8dc38b1a0a12bc064fc064269033bdcf5b88e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZCDZ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit 91a0c0c1413239d0548b5aac4c82f38f6d53a91e ] When if_type equals zero and pci_resource_start(pdev, PCI_64BIT_BAR4) returns false, drbl_regs_memmap_p is not remapped. This passes a NULL pointer to iounmap(), which can trigger a WARN() on certain arches. When if_type equals six and pci_resource_start(pdev, PCI_64BIT_BAR4) returns true, drbl_regs_memmap_p may has been remapped and ctrl_regs_memmap_p is not remapped. This is a resource leak and passes a NULL pointer to iounmap(). To fix these issues, we need to add null checks before iounmap(), and change some goto labels. Fixes: 1351e69fc6db ("scsi: lpfc: Add push-to-adapter support to sli4") Signed-off-by: Shuchang Li <lishuchang(a)hust.edu.cn> Link: https://lore.kernel.org/r/20230404072133.1022-1-lishuchang@hust.edu.cn Reviewed-by: Justin Tee <justin.tee(a)broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yong Hu <yong.hu(a)windriver.com> --- drivers/scsi/lpfc/lpfc_init.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 17200b453cbb..1bb3c96a04bd 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -10477,7 +10477,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) goto out_iounmap_all; } else { error = -ENOMEM; - goto out_iounmap_all; + goto out_iounmap_ctrl; } } @@ -10495,7 +10495,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) dev_err(&pdev->dev, "ioremap failed for SLI4 HBA dpp registers.\n"); error = -ENOMEM; - goto out_iounmap_ctrl; + goto out_iounmap_all; } phba->pci_bar4_memmap_p = phba->sli4_hba.dpp_regs_memmap_p; } @@ -10520,9 +10520,11 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) return 0; out_iounmap_all: - iounmap(phba->sli4_hba.drbl_regs_memmap_p); + if (phba->sli4_hba.drbl_regs_memmap_p) + iounmap(phba->sli4_hba.drbl_regs_memmap_p); out_iounmap_ctrl: - iounmap(phba->sli4_hba.ctrl_regs_memmap_p); + if (phba->sli4_hba.ctrl_regs_memmap_p) + iounmap(phba->sli4_hba.ctrl_regs_memmap_p); out_iounmap_conf: iounmap(phba->sli4_hba.conf_regs_memmap_p); -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS] scsi: lpfc: Fix ioremap issues in lpfc_sli4_pci_mem_setup()
by Yong Hu 26 Sep '23

26 Sep '23

From: Shuchang Li <lishuchang(a)hust.edu.cn> stable inclusion from stable-v5.10.180 commit bab8dc38b1a0a12bc064fc064269033bdcf5b88e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZCDZ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit 91a0c0c1413239d0548b5aac4c82f38f6d53a91e ] When if_type equals zero and pci_resource_start(pdev, PCI_64BIT_BAR4) returns false, drbl_regs_memmap_p is not remapped. This passes a NULL pointer to iounmap(), which can trigger a WARN() on certain arches. When if_type equals six and pci_resource_start(pdev, PCI_64BIT_BAR4) returns true, drbl_regs_memmap_p may has been remapped and ctrl_regs_memmap_p is not remapped. This is a resource leak and passes a NULL pointer to iounmap(). To fix these issues, we need to add null checks before iounmap(), and change some goto labels. Fixes: 1351e69fc6db ("scsi: lpfc: Add push-to-adapter support to sli4") Signed-off-by: Shuchang Li <lishuchang(a)hust.edu.cn> Link: https://lore.kernel.org/r/20230404072133.1022-1-lishuchang@hust.edu.cn Reviewed-by: Justin Tee <justin.tee(a)broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yong Hu <yong.hu(a)windriver.com> --- drivers/scsi/lpfc/lpfc_init.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 134e4ee5dc48..2f7a17e96e25 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -10474,7 +10474,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) goto out_iounmap_all; } else { error = -ENOMEM; - goto out_iounmap_all; + goto out_iounmap_ctrl; } } @@ -10492,7 +10492,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) dev_err(&pdev->dev, "ioremap failed for SLI4 HBA dpp registers.\n"); error = -ENOMEM; - goto out_iounmap_ctrl; + goto out_iounmap_all; } phba->pci_bar4_memmap_p = phba->sli4_hba.dpp_regs_memmap_p; } @@ -10517,9 +10517,11 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) return 0; out_iounmap_all: - iounmap(phba->sli4_hba.drbl_regs_memmap_p); + if (phba->sli4_hba.drbl_regs_memmap_p) + iounmap(phba->sli4_hba.drbl_regs_memmap_p); out_iounmap_ctrl: - iounmap(phba->sli4_hba.ctrl_regs_memmap_p); + if (phba->sli4_hba.ctrl_regs_memmap_p) + iounmap(phba->sli4_hba.ctrl_regs_memmap_p); out_iounmap_conf: iounmap(phba->sli4_hba.conf_regs_memmap_p); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c
by Lu Wei 26 Sep '23

26 Sep '23

From: Kyle Zeng <zengyhkyle(a)gmail.com> mainline inclusion from mainline-v6.6-rc1 commit 050d91c03b28ca479df13dfb02bcd2c60dd6a878 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I83QCZ CVE: CVE-2023-42753 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The missing IP_SET_HASH_WITH_NET0 macro in ip_set_hash_netportnet can lead to the use of wrong `CIDR_POS(c)` for calculating array offsets, which can lead to integer underflow. As a result, it leads to slab out-of-bound access. This patch adds back the IP_SET_HASH_WITH_NET0 macro to ip_set_hash_netportnet to address the issue. Fixes: 886503f34d63 ("netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net") Suggested-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> Acked-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/netfilter/ipset/ip_set_hash_netportnet.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 613e18e720a4..9290a4d7b862 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -39,6 +39,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net"); #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 +#define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c
by Lu Wei 26 Sep '23

26 Sep '23

From: Kyle Zeng <zengyhkyle(a)gmail.com> mainline inclusion from mainline-v6.6-rc1 commit 050d91c03b28ca479df13dfb02bcd2c60dd6a878 category: bugfix bugzilla: 189250 CVE: CVE-2023-42753 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The missing IP_SET_HASH_WITH_NET0 macro in ip_set_hash_netportnet can lead to the use of wrong `CIDR_POS(c)` for calculating array offsets, which can lead to integer underflow. As a result, it leads to slab out-of-bound access. This patch adds back the IP_SET_HASH_WITH_NET0 macro to ip_set_hash_netportnet to address the issue. Fixes: 886503f34d63 ("netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net") Suggested-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> Acked-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/netfilter/ipset/ip_set_hash_netportnet.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 613e18e720a4..9290a4d7b862 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -39,6 +39,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net"); #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 +#define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS,v2] netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c
by Lu Wei 26 Sep '23

26 Sep '23

From: Kyle Zeng <zengyhkyle(a)gmail.com> mainline inclusion from mainline-v6.6-rc1 commit 050d91c03b28ca479df13dfb02bcd2c60dd6a878 category: bugfix bugzilla: 189250 CVE: CVE-2023-42753 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The missing IP_SET_HASH_WITH_NET0 macro in ip_set_hash_netportnet can lead to the use of wrong `CIDR_POS(c)` for calculating array offsets, which can lead to integer underflow. As a result, it leads to slab out-of-bound access. This patch adds back the IP_SET_HASH_WITH_NET0 macro to ip_set_hash_netportnet to address the issue. Fixes: 886503f34d63 ("netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net") Suggested-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> Acked-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/netfilter/ipset/ip_set_hash_netportnet.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 613e18e720a4..9290a4d7b862 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -39,6 +39,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net"); #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 +#define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ -- 2.34.1

1 0

[PATCH openEuler-1.0-LTS] [just for review!!!!]Add feature: eNFS - nfs multipath to improve performance and reliability
by mingqian218472 25 Sep '23

25 Sep '23

From: 闫海涛 <yanhaitao2(a)huawei.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7SVH7 --------------------------------- Currently, the NFS client can use only one server IP address at a single mount point. As a result, the hardware capability of multiple storage nodes and NICs cannot be fully utilized. In multiple financial sites, the performance cannot meet service requirements. In addition, when a single link is faulty, services are suspended. The reliability problem needs to be solved. OpenEuler-based commercial OS vendors hope that the eNFS feature will be integrated into 20.03 SP4 to resolve performance and reliability problems. When user mount one NFS share, can input localaddrs/remoteaddrs these two optional Parameters to use eNFS multipath. If these optional parameters are not used, NFS will behave as before. For example, mount -t nfs -o [localaddrs=127.17.0.1-127.17.0.4],[remoteaddrs=127.17.1.1-127.17.1.4] xx.xx.xx.xx:/test /mnt/test Changes in eNFS are as follows: 1. patch 0001: At the NFS layer, the eNFS registration function is called back when the mount command parses parameters. The eNFS parses and saves the IP address list entered by users. 2. patch 0002: At the sunrpc layer, the eNFS registration function is called back When the NFS uses sunrpc to create rpc_clnt, the eNFS combines the IP address list entered for mount to generate multiple xprts. When the I/O times out, the callback function of the eNFS is called back so that the eNFS switches to an available link for retry. 3. patch 0003: The eNFS module registers the interface for parsing the mount command. During the mount process, the NFS invokes the eNFS interface to enable the eNFS to parse the mounting parameters of UltraPath. The eNFS module saves the mounting parameters to the context of nfs_client. 4. patch 0004: When the NFS invokes the SunRPC to create rpc_clnt, the eNFS interface is called back. The eNFS creates multiple xprts based on the output IP address list. When NFS V3 I/Os are delivered, eNFS distributes I/Os to available links based on the link status, improving performance through load balancing. 5. patch 0005: When sending I/Os from the SunRPC module to the NFS server times out, the SunRPC module calls back the eNFS module to reselect a link. The eNFS module distributes I/Os to other available links, preventing service interruption caused by a single link failure. 6. patch 0006: The eNFS compilation option and makefile are added. By default, the eNFS compilation is not performed. Signed-off-by: mingqian218472 <zhangmingqian.zhang(a)huawei.com> --- ...-nfs-multipath-to-improve-performanc.patch | 6148 +++++++++++++++++ ...enfs_registe_and_handle_mount_option.patch | 757 ++ ...nd_create_multipath_then_dispatch_IO.patch | 805 +++ ...add_enfs_module_for_nfs_mount_option.patch | 1209 ++++ ...dd_enfs_module_for_sunrpc_multipatch.patch | 1581 +++++ ...le_for_sunrpc_failover_and_configure.patch | 1607 +++++ 0006-add_enfs_compile_option.patch | 70 + 7 files changed, 12177 insertions(+) create mode 100644 0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch create mode 100644 0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch create mode 100644 0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch create mode 100644 0003-add_enfs_module_for_nfs_mount_option.patch create mode 100644 0004-add_enfs_module_for_sunrpc_multipatch.patch create mode 100644 0005-add_enfs_module_for_sunrpc_failover_and_configure.patch create mode 100644 0006-add_enfs_compile_option.patch diff --git a/0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch b/0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch new file mode 100644 index 0000000..2974c5f --- /dev/null +++ b/0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch @@ -0,0 +1,6148 @@ +From 53f616b0a649494e33d30b250d06c4049ccb88be Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?=E9=97=AB=E6=B5=B7=E6=B6=9B?= <yanhaitao2(a)huawei.com> +Date: Mon, 25 Sep 2023 19:19:15 +0800 +Subject: [PATCH openEuler-20.03-LTS-SP3] Add feature: eNFS - nfs multipath to + improve performance and reliability + +driver inclusion +category: feature +bugzilla: https://gitee.com/openeuler/release-management/issues/I7U0W0 + +--------------------------------- + +Currently, the NFS client can use only one server IP address at a single mount point. As a result, the hardware capability of multiple storage nodes and NICs cannot be fully utilized. In multiple financial sites, the performance cannot meet service requirements. In addition, when a single link is faulty, services are suspended. The reliability problem needs to be solved. +OpenEuler-based commercial OS vendors hope that the eNFS feature will be integrated into 20.03 SP4 to resolve performance and reliability problems. + +When user mount one NFS share, can input localaddrs/remoteaddrs these two optional Parameters to use eNFS multipath. If these optional parameters are not used, NFS will behave as before. For example, +mount -t nfs -o [localaddrs=127.17.0.1-127.17.0.4],[remoteaddrs=127.17.1.1-127.17.1.4] xx.xx.xx.xx:/test /mnt/test + +Changes in eNFS are as follows: +1. patch 0001: +At the NFS layer, the eNFS registration function is called back when the mount command parses parameters. The eNFS parses and saves the IP address list entered by users. +2. patch 0002: +At the sunrpc layer, the eNFS registration function is called back When the NFS uses sunrpc to create rpc_clnt, the eNFS combines the IP address list entered for mount to generate multiple xprts. When the I/O times out, the callback function of the eNFS is called back so that the eNFS switches to an available link for retry. +3. patch 0003: +The eNFS module registers the interface for parsing the mount command. During the mount process, the NFS invokes the eNFS interface to enable the eNFS to parse the mounting parameters of UltraPath. The eNFS module saves the mounting parameters to the context of nfs_client. +4. patch 0004: +When the NFS invokes the SunRPC to create rpc_clnt, the eNFS interface is called back. The eNFS creates multiple xprts based on the output IP address list. When NFS V3 I/Os are delivered, eNFS distributes I/Os to available links based on the link status, improving performance through load balancing. +5. patch 0005: +When sending I/Os from the SunRPC module to the NFS server times out, the SunRPC module calls back the eNFS module to reselect a link. The eNFS module distributes I/Os to other available links, preventing service interruption caused by a single link failure. +6. patch 0006: +The eNFS compilation option and makefile are added. By default, the eNFS compilation is not performed. + +Signed-off-by: mingqian218472 <zhangmingqian.zhang(a)huawei.com> +--- + ...enfs_registe_and_handle_mount_option.patch | 757 ++++++++ + ...nd_create_multipath_then_dispatch_IO.patch | 805 +++++++++ + ...add_enfs_module_for_nfs_mount_option.patch | 1209 +++++++++++++ + ...dd_enfs_module_for_sunrpc_multipatch.patch | 1581 ++++++++++++++++ + ...le_for_sunrpc_failover_and_configure.patch | 1607 +++++++++++++++++ + 0006-add_enfs_compile_option.patch | 70 + + kernel.spec | 13 + + 7 files changed, 6042 insertions(+) + create mode 100644 0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch + create mode 100644 0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch + create mode 100644 0003-add_enfs_module_for_nfs_mount_option.patch + create mode 100644 0004-add_enfs_module_for_sunrpc_multipatch.patch + create mode 100644 0005-add_enfs_module_for_sunrpc_failover_and_configure.patch + create mode 100644 0006-add_enfs_compile_option.patch + +diff --git a/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch +new file mode 100644 +index 0000000..38e57a9 +--- /dev/null ++++ b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch +@@ -0,0 +1,757 @@ ++diff --git a/fs/nfs/client.c b/fs/nfs/client.c ++index 7d02dc52209d..50820a8a684a 100644 ++--- a/fs/nfs/client.c +++++ b/fs/nfs/client.c ++@@ -48,7 +48,7 @@ ++ #include "callback.h" ++ #include "delegation.h" ++ #include "iostat.h" ++-#include "internal.h" +++#include "enfs_adapter.h" ++ #include "fscache.h" ++ #include "pnfs.h" ++ #include "nfs.h" ++@@ -255,6 +255,7 @@ void nfs_free_client(struct nfs_client *clp) ++ put_nfs_version(clp->cl_nfs_mod); ++ kfree(clp->cl_hostname); ++ kfree(clp->cl_acceptor); +++ nfs_free_multi_path_client(clp); ++ kfree(clp); ++ } ++ EXPORT_SYMBOL_GPL(nfs_free_client); ++@@ -330,6 +331,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat ++ sap)) ++ continue; ++ +++ if (!nfs_multipath_client_match(clp, data)) +++ continue; +++ ++ refcount_inc(&clp->cl_count); ++ return clp; ++ } ++@@ -512,6 +516,9 @@ int nfs_create_rpc_client(struct nfs_client *clp, ++ .program = &nfs_program, ++ .version = clp->rpc_ops->version, ++ .authflavor = flavor, +++#if IS_ENABLED(CONFIG_ENFS) +++ .multipath_option = cl_init->enfs_option, +++#endif ++ }; ++ ++ if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) ++@@ -634,6 +641,13 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp, ++ /* the client is already initialised */ ++ if (clp->cl_cons_state == NFS_CS_READY) ++ return clp; +++ error = nfs_create_multi_path_client(clp, cl_init); +++ if (error < 0) { +++ dprintk("%s: create failed.%d!\n", __func__, error); +++ nfs_put_client(clp); +++ clp = ERR_PTR(error); +++ return clp; +++ } ++ ++ /* ++ * Create a client RPC handle for doing FSSTAT with UNIX auth only ++@@ -666,6 +680,9 @@ static int nfs_init_server(struct nfs_server *server, ++ .net = data->net, ++ .timeparms = &timeparms, ++ .init_flags = (1UL << NFS_CS_REUSEPORT), +++#if IS_ENABLED(CONFIG_ENFS) +++ .enfs_option = data->enfs_option, +++#endif ++ }; ++ struct nfs_client *clp; ++ int error; ++diff --git a/fs/nfs/enfs_adapter.c b/fs/nfs/enfs_adapter.c ++new file mode 100644 ++index 000000000000..7f471f2072c4 ++--- /dev/null +++++ b/fs/nfs/enfs_adapter.c ++@@ -0,0 +1,230 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs3.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/sunrpc/sched.h> +++#include <linux/nfs_iostat.h> +++#include "enfs_adapter.h" +++#include "iostat.h" +++ +++struct enfs_adapter_ops __rcu *enfs_adapter; +++ +++int enfs_adapter_register(struct enfs_adapter_ops *ops) +++{ +++ struct enfs_adapter_ops *old; +++ +++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, NULL, ops); +++ if (old == NULL || old == ops) +++ return 0; +++ pr_err("regist %s ops %p failed. old %p\n", __func__, ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(enfs_adapter_register); +++ +++int enfs_adapter_unregister(struct enfs_adapter_ops *ops) +++{ +++ struct enfs_adapter_ops *old; +++ +++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, ops, NULL); +++ if (old == ops || old == NULL) +++ return 0; +++ pr_err("unregist %s ops %p failed. old %p\n", __func__, ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(enfs_adapter_unregister); +++ +++struct enfs_adapter_ops *nfs_multipath_router_get(void) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ rcu_read_lock(); +++ ops = rcu_dereference(enfs_adapter); +++ if (ops == NULL) { +++ rcu_read_unlock(); +++ return NULL; +++ } +++ if (!try_module_get(ops->owner)) +++ ops = NULL; +++ rcu_read_unlock(); +++ return ops; +++} +++ +++void nfs_multipath_router_put(struct enfs_adapter_ops *ops) +++{ +++ if (ops) +++ module_put(ops->owner); +++} +++ +++bool is_valid_option(enum nfsmultipathoptions option) +++{ +++ if (option < REMOTEADDR || option >= INVALID_OPTION) { +++ pr_warn("%s: ENFS invalid option %d\n", __func__, option); +++ return false; +++ } +++ +++ return true; +++} +++ +++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, +++ struct nfs_parsed_mount_data *mnt) +++{ +++ +++ //parseMultiPathOptions(getNfsMultiPathOpt(token), string, mnt); +++ +++ int rc; +++ struct enfs_adapter_ops *ops; +++ +++ ops = nfs_multipath_router_get(); +++ if ((ops == NULL) || (ops->parse_mount_options == NULL) || +++ !is_valid_option(option)) { +++ nfs_multipath_router_put(ops); +++ dfprintk(MOUNT, +++ "NFS: parsing nfs mount option enfs not load[%s]\n" +++ , __func__); +++ return -EOPNOTSUPP; +++ } +++ // nfs_multipath_parse_options +++ dfprintk(MOUNT, "NFS: parsing nfs mount option '%s' type: %d[%s]\n" +++ , str, option, __func__); +++ rc = ops->parse_mount_options(option, str, &mnt->enfs_option, mnt->net); +++ nfs_multipath_router_put(ops); +++ return rc; +++} +++ +++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ if (data->enfs_option == NULL) +++ return; +++ +++ ops = nfs_multipath_router_get(); +++ if ((ops == NULL) || (ops->free_mount_options == NULL)) { +++ nfs_multipath_router_put(ops); +++ return; +++ } +++ ops->free_mount_options((void *)&data->enfs_option); +++ nfs_multipath_router_put(ops); +++} +++ +++int nfs_create_multi_path_client(struct nfs_client *client, +++ const struct nfs_client_initdata *cl_init) +++{ +++ int ret = 0; +++ struct enfs_adapter_ops *ops; +++ +++ if (cl_init->enfs_option == NULL) +++ return 0; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_init != NULL) +++ ret = ops->client_info_init( +++ (void *)&client->cl_multipath_data, cl_init); +++ nfs_multipath_router_put(ops); +++ +++ return ret; +++} +++EXPORT_SYMBOL_GPL(nfs_create_multi_path_client); +++ +++void nfs_free_multi_path_client(struct nfs_client *clp) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ if (clp->cl_multipath_data == NULL) +++ return; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_free != NULL) +++ ops->client_info_free(clp->cl_multipath_data); +++ nfs_multipath_router_put(ops); +++} +++ +++int nfs_multipath_client_match(struct nfs_client *clp, +++ const struct nfs_client_initdata *sap) +++{ +++ int ret = true; +++ struct enfs_adapter_ops *ops; +++ +++ pr_info("%s src %p dst %p\n.", __func__, +++ clp->cl_multipath_data, sap->enfs_option); +++ +++ if (clp->cl_multipath_data == NULL && sap->enfs_option == NULL) +++ return true; +++ +++ if ((clp->cl_multipath_data == NULL && sap->enfs_option) || +++ (clp->cl_multipath_data && sap->enfs_option == NULL)) { +++ pr_err("not match client src %p dst %p\n.", +++ clp->cl_multipath_data, sap->enfs_option); +++ return false; +++ } +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_match != NULL) +++ ret = ops->client_info_match(clp->cl_multipath_data, +++ sap->enfs_option); +++ nfs_multipath_router_put(ops); +++ +++ return ret; +++} +++ +++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst) +++{ +++ int ret = true; +++ struct enfs_adapter_ops *ops; +++ +++ if (src->cl_multipath_data == NULL && dst->cl_multipath_data == NULL) +++ return true; +++ +++ if (src->cl_multipath_data == NULL || dst->cl_multipath_data == NULL) +++ return false; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->nfs4_client_info_match != NULL) +++ ret = ops->nfs4_client_info_match(src->cl_multipath_data, +++ src->cl_multipath_data); +++ nfs_multipath_router_put(ops); +++ +++ return ret; +++} +++EXPORT_SYMBOL_GPL(nfs4_multipath_client_match); +++ +++void nfs_multipath_show_client_info(struct seq_file *mount_option, +++ struct nfs_server *server) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ if (mount_option == NULL || server == NULL || +++ server->client == NULL || +++ server->nfs_client->cl_multipath_data == NULL) +++ return; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_show != NULL) +++ ops->client_info_show(mount_option, server); +++ nfs_multipath_router_put(ops); +++} +++ +++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) +++{ +++ int ret = 0; +++ struct enfs_adapter_ops *ops; +++ +++ if (nfs_client == NULL || nfs_client->cl_rpcclient == NULL) +++ return 0; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->remount_ip_list != NULL) +++ ret = ops->remount_ip_list(nfs_client, enfs_option); +++ nfs_multipath_router_put(ops); +++ return ret; +++} +++EXPORT_SYMBOL_GPL(nfs_remount_iplist); ++diff --git a/fs/nfs/enfs_adapter.h b/fs/nfs/enfs_adapter.h ++new file mode 100644 ++index 000000000000..752544e18056 ++--- /dev/null +++++ b/fs/nfs/enfs_adapter.h ++@@ -0,0 +1,101 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapt header. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _NFS_MULTIPATH_H_ +++#define _NFS_MULTIPATH_H_ +++ +++#include "internal.h" +++ +++#if IS_ENABLED(CONFIG_ENFS) +++enum nfsmultipathoptions { +++ REMOTEADDR, +++ LOCALADDR, +++ REMOTEDNSNAME, +++ REMOUNTREMOTEADDR, +++ REMOUNTLOCALADDR, +++ INVALID_OPTION +++}; +++ +++ +++struct enfs_adapter_ops { +++ const char *name; +++ struct module *owner; +++ int (*parse_mount_options)(enum nfsmultipathoptions option, +++ char *str, void **enfs_option, struct net *net_ns); +++ +++ void (*free_mount_options)(void **data); +++ +++ int (*client_info_init)(void **data, +++ const struct nfs_client_initdata *cl_init); +++ void (*client_info_free)(void *data); +++ int (*client_info_match)(void *src, void *dst); +++ int (*nfs4_client_info_match)(void *src, void *dst); +++ void (*client_info_show)(struct seq_file *mount_option, void *data); +++ int (*remount_ip_list)(struct nfs_client *nfs_client, +++ void *enfs_option); +++}; +++ +++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, +++ struct nfs_parsed_mount_data *mnt); +++void enfs_free_mount_options(struct nfs_parsed_mount_data *data); +++int nfs_create_multi_path_client(struct nfs_client *client, +++ const struct nfs_client_initdata *cl_init); +++void nfs_free_multi_path_client(struct nfs_client *clp); +++int nfs_multipath_client_match(struct nfs_client *clp, +++ const struct nfs_client_initdata *sap); +++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst); +++void nfs_multipath_show_client_info(struct seq_file *mount_option, +++ struct nfs_server *server); +++int enfs_adapter_register(struct enfs_adapter_ops *ops); +++int enfs_adapter_unregister(struct enfs_adapter_ops *ops); +++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); +++int nfs4_create_multi_path(struct nfs_server *server, +++ struct nfs_parsed_mount_data *data, +++ const struct rpc_timeout *timeparms); +++ +++#else +++static inline +++void nfs_free_multi_path_client(struct nfs_client *clp) +++{ +++ +++} +++ +++static inline +++int nfs_multipath_client_match(struct nfs_client *clp, +++ const struct nfs_client_initdata *sap) +++{ +++ return 1; +++} +++ +++static inline +++int nfs_create_multi_path_client(struct nfs_client *client, +++ const struct nfs_client_initdata *cl_init) +++{ +++ return 0; +++} +++ +++static inline +++void nfs_multipath_show_client_info(struct seq_file *mount_option, +++ struct nfs_server *server) +++{ +++ +++} +++ +++static inline +++int nfs4_multipath_client_match(struct nfs_client *src, +++ struct nfs_client *dst) +++{ +++ return 1; +++} +++ +++static inline +++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) +++{ +++ +++} +++ +++#endif // CONFIG_ENFS +++#endif // _NFS_MULTIPATH_H_ ++diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h ++index 0ce5a90640c4..c696693edc7b 100644 ++--- a/fs/nfs/internal.h +++++ b/fs/nfs/internal.h ++@@ -93,6 +93,9 @@ struct nfs_client_initdata { ++ u32 minorversion; ++ struct net *net; ++ const struct rpc_timeout *timeparms; +++#if IS_ENABLED(CONFIG_ENFS) +++ void *enfs_option; /* struct multipath_mount_options * */ +++#endif ++ }; ++ ++ /* ++@@ -135,6 +138,9 @@ struct nfs_parsed_mount_data { ++ ++ struct security_mnt_opts lsm_opts; ++ struct net *net; +++#if IS_ENABLED(CONFIG_ENFS) +++ void *enfs_option; /* struct multipath_mount_options * */ +++#endif ++ }; ++ ++ /* mount_clnt.c */ ++diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c ++index 1350ea673672..4aa6e1f961f7 100644 ++--- a/fs/nfs/nfs4client.c +++++ b/fs/nfs/nfs4client.c ++@@ -10,7 +10,7 @@ ++ #include <linux/sunrpc/xprt.h> ++ #include <linux/sunrpc/bc_xprt.h> ++ #include <linux/sunrpc/rpc_pipe_fs.h> ++-#include "internal.h" +++#include "enfs_adapter.h" ++ #include "callback.h" ++ #include "delegation.h" ++ #include "nfs4session.h" ++@@ -225,6 +225,16 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) ++ __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); ++ __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ err = nfs_create_multi_path_client(clp, cl_init); +++ if (err < 0) { +++ dprintk("%s: create failed.%d\n", __func__, err); +++ nfs_put_client(clp); +++ clp = ERR_PTR(err); +++ return clp; +++ } +++#endif +++ ++ /* ++ * Set up the connection to the server before we add add to the ++ * global list. ++@@ -529,6 +539,9 @@ static int nfs4_match_client(struct nfs_client *pos, struct nfs_client *new, ++ if (!nfs4_match_client_owner_id(pos, new)) ++ return 1; ++ +++ if (!nfs4_multipath_client_match(pos, new)) +++ return 1; +++ ++ return 0; ++ } ++ ++@@ -860,7 +873,7 @@ static int nfs4_set_client(struct nfs_server *server, ++ const size_t addrlen, ++ const char *ip_addr, ++ int proto, const struct rpc_timeout *timeparms, ++- u32 minorversion, struct net *net) +++ u32 minorversion, struct net *net, void *enfs_option) ++ { ++ struct nfs_client_initdata cl_init = { ++ .hostname = hostname, ++@@ -872,6 +885,9 @@ static int nfs4_set_client(struct nfs_server *server, ++ .minorversion = minorversion, ++ .net = net, ++ .timeparms = timeparms, +++#if IS_ENABLED(CONFIG_ENFS) +++ .enfs_option = enfs_option, +++#endif ++ }; ++ struct nfs_client *clp; ++ ++@@ -1042,6 +1058,30 @@ static int nfs4_server_common_setup(struct nfs_server *server, ++ return error; ++ } ++ +++int nfs4_create_multi_path(struct nfs_server *server, +++ struct nfs_parsed_mount_data *data, +++ const struct rpc_timeout *timeparms) +++{ +++ struct nfs_client_initdata cl_init = { +++ .hostname = data->nfs_server.hostname, +++ .addr = (const struct sockaddr *)&data->nfs_server.address, +++ .addrlen = data->nfs_server.addrlen, +++ .ip_addr = data->client_address, +++ .nfs_mod = &nfs_v4, +++ .proto = data->nfs_server.protocol, +++ .minorversion = data->minorversion, +++ .net = data->net, +++ .timeparms = timeparms, +++#if IS_ENABLED(CONFIG_ENFS) +++ .enfs_option = data->enfs_option, +++#endif // CONFIG_ENFS +++ }; +++ +++ return nfs_create_multi_path_client(server->nfs_client, &cl_init); +++ +++} +++EXPORT_SYMBOL_GPL(nfs4_create_multi_path); +++ ++ /* ++ * Create a version 4 volume record ++ */ ++@@ -1050,6 +1090,7 @@ static int nfs4_init_server(struct nfs_server *server, ++ { ++ struct rpc_timeout timeparms; ++ int error; +++ void *enfs_option = NULL; ++ ++ nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, ++ data->timeo, data->retrans); ++@@ -1067,6 +1108,10 @@ static int nfs4_init_server(struct nfs_server *server, ++ else ++ data->selected_flavor = RPC_AUTH_UNIX; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ enfs_option = data->enfs_option; +++#endif +++ ++ /* Get a client record */ ++ error = nfs4_set_client(server, ++ data->nfs_server.hostname, ++@@ -1076,7 +1121,7 @@ static int nfs4_init_server(struct nfs_server *server, ++ data->nfs_server.protocol, ++ &timeparms, ++ data->minorversion, ++- data->net); +++ data->net, enfs_option); ++ if (error < 0) ++ return error; ++ ++@@ -1161,7 +1206,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, ++ XPRT_TRANSPORT_RDMA, ++ parent_server->client->cl_timeout, ++ parent_client->cl_mvops->minor_version, ++- parent_client->cl_net); +++ parent_client->cl_net, NULL); ++ if (!error) ++ goto init_server; ++ #endif /* IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) */ ++@@ -1174,7 +1219,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, ++ XPRT_TRANSPORT_TCP, ++ parent_server->client->cl_timeout, ++ parent_client->cl_mvops->minor_version, ++- parent_client->cl_net); +++ parent_client->cl_net, NULL); ++ if (error < 0) ++ goto error; ++ ++@@ -1269,7 +1314,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, ++ set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); ++ error = nfs4_set_client(server, hostname, sap, salen, buf, ++ clp->cl_proto, clnt->cl_timeout, ++- clp->cl_minorversion, net); +++ clp->cl_minorversion, net, NULL); ++ clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); ++ if (error != 0) { ++ nfs_server_insert_lists(server); ++diff --git a/fs/nfs/super.c b/fs/nfs/super.c ++index a05e1eb2c3fd..83cd294aca15 100644 ++--- a/fs/nfs/super.c +++++ b/fs/nfs/super.c ++@@ -61,7 +61,7 @@ ++ #include "callback.h" ++ #include "delegation.h" ++ #include "iostat.h" ++-#include "internal.h" +++#include "enfs_adapter.h" ++ #include "fscache.h" ++ #include "nfs4session.h" ++ #include "pnfs.h" ++@@ -113,6 +113,12 @@ enum { ++ ++ /* Special mount options */ ++ Opt_userspace, Opt_deprecated, Opt_sloppy, +++#if IS_ENABLED(CONFIG_ENFS) +++ Opt_remote_iplist, +++ Opt_local_iplist, +++ Opt_remote_dnslist, +++ Opt_enfs_info, +++#endif ++ ++ Opt_err ++ }; ++@@ -183,6 +189,13 @@ static const match_table_t nfs_mount_option_tokens = { ++ { Opt_fscache_uniq, "fsc=%s" }, ++ { Opt_local_lock, "local_lock=%s" }, ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ { Opt_remote_iplist, "remoteaddrs=%s" }, +++ { Opt_local_iplist, "localaddrs=%s" }, +++ { Opt_remote_dnslist, "remotednsname=%s" }, +++ { Opt_enfs_info, "enfs_info=%s" }, +++#endif +++ ++ /* The following needs to be listed after all other options */ ++ { Opt_nfsvers, "v%s" }, ++ ++@@ -365,6 +378,21 @@ static struct shrinker acl_shrinker = { ++ .seeks = DEFAULT_SEEKS, ++ }; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++enum nfsmultipathoptions getNfsMultiPathOpt(int token) +++{ +++ switch (token) { +++ case Opt_remote_iplist: +++ return REMOUNTREMOTEADDR; +++ case Opt_local_iplist: +++ return REMOUNTLOCALADDR; +++ case Opt_remote_dnslist: +++ return REMOTEDNSNAME; +++ } +++ return INVALID_OPTION; +++} +++#endif +++ ++ /* ++ * Register the NFS filesystems ++ */ ++@@ -758,6 +786,9 @@ int nfs_show_options(struct seq_file *m, struct dentry *root) ++ seq_printf(m, ",addr=%s", ++ rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient, ++ RPC_DISPLAY_ADDR)); +++ +++ nfs_multipath_show_client_info(m, nfss); +++ ++ rcu_read_unlock(); ++ ++ return 0; ++@@ -853,6 +884,8 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) ++ seq_puts(m, root->d_sb->s_flags & SB_NODIRATIME ? ",nodiratime" : ""); ++ nfs_show_mount_options(m, nfss, 1); ++ +++ nfs_multipath_show_client_info(m, nfss); +++ ++ seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); ++ ++ show_implementation_id(m, nfss); ++@@ -977,6 +1010,7 @@ static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data) ++ kfree(data->nfs_server.export_path); ++ kfree(data->nfs_server.hostname); ++ kfree(data->fscache_uniq); +++ enfs_free_mount_options(data); ++ security_free_mnt_opts(&data->lsm_opts); ++ kfree(data); ++ } ++@@ -1641,7 +1675,34 @@ static int nfs_parse_mount_options(char *raw, ++ return 0; ++ }; ++ break; ++- +++#if IS_ENABLED(CONFIG_ENFS) +++ case Opt_remote_iplist: +++ case Opt_local_iplist: +++ case Opt_remote_dnslist: +++ string = match_strdup(args); +++ if (string == NULL) +++ goto out_nomem; +++ rc = enfs_parse_mount_options(getNfsMultiPathOpt(token), +++ string, mnt); +++ kfree(string); +++ switch (rc) { +++ case 0: +++ break; +++ case -ENOMEM: +++ goto out_nomem; +++ case -ENOSPC: +++ goto out_limit; +++ case -EINVAL: +++ goto out_invalid_address; +++ case -ENOTSUPP: +++ goto out_invalid_address; +++ case -EOPNOTSUPP: +++ goto out_invalid_address; +++ } +++ break; +++ case Opt_enfs_info: +++ break; +++#endif ++ /* ++ * Special options ++ */ ++@@ -1720,6 +1781,11 @@ static int nfs_parse_mount_options(char *raw, ++ free_secdata(secdata); ++ printk(KERN_INFO "NFS: security options invalid: %d\n", rc); ++ return 0; +++#if IS_ENABLED(CONFIG_ENFS) +++out_limit: +++ dprintk("NFS: param is more than supported limit: %d\n", rc); +++ return 0; +++#endif ++ } ++ ++ /* ++@@ -2335,6 +2401,14 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) ++ if (!nfs_parse_mount_options((char *)options, data)) ++ goto out; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ if (data->enfs_option) { +++ error = nfs_remount_iplist(nfss->nfs_client, data->enfs_option); +++ if (error) +++ goto out; +++ } +++#endif +++ ++ /* ++ * noac is a special case. It implies -o sync, but that's not ++ * necessarily reflected in the mtab options. do_remount_sb ++@@ -2347,6 +2421,11 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) ++ /* compare new mount options with old ones */ ++ error = nfs_compare_remount_data(nfss, data); ++ out: +++#if IS_ENABLED(CONFIG_ENFS) +++ /* release remount option member */ +++ if (data->enfs_option) +++ enfs_free_mount_options(data); +++#endif ++ nfs_free_parsed_mount_data(data); ++ return error; ++ } ++diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h ++index 7023ae64e3d7..2c19678afe8d 100644 ++--- a/include/linux/nfs_fs_sb.h +++++ b/include/linux/nfs_fs_sb.h ++@@ -123,6 +123,11 @@ struct nfs_client { ++ ++ struct net *cl_net; ++ struct list_head pending_cb_stateids; +++ +++#if IS_ENABLED(CONFIG_ENFS) +++ /* multi path private structure (struct multipath_client_info *) */ +++ void *cl_multipath_data; +++#endif ++ }; ++ ++ /* +diff --git a/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch +new file mode 100644 +index 0000000..540a2ce +--- /dev/null ++++ b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch +@@ -0,0 +1,805 @@ ++diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h ++index 8aa865bce4f6..89178f78de8c 100644 ++--- a/include/linux/sunrpc/clnt.h +++++ b/include/linux/sunrpc/clnt.h ++@@ -70,6 +70,10 @@ struct rpc_clnt { ++ struct dentry *cl_debugfs; /* debugfs directory */ ++ #endif ++ struct rpc_xprt_iter cl_xpi; +++ +++#if IS_ENABLED(CONFIG_ENFS) +++ bool cl_enfs; +++#endif ++ }; ++ ++ /* ++@@ -124,6 +128,9 @@ struct rpc_create_args { ++ unsigned long flags; ++ char *client_name; ++ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ +++#if IS_ENABLED(CONFIG_ENFS) +++ void *multipath_option; +++#endif ++ }; ++ ++ struct rpc_add_xprt_test { ++@@ -221,6 +228,12 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, ++ const struct sockaddr *sap); ++ void rpc_cleanup_clids(void); ++ +++#if IS_ENABLED(CONFIG_ENFS) +++int +++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, +++ const struct rpc_call_ops *ops, void *data, int flags); +++#endif /* CONFIG_ENFS */ +++ ++ static inline int rpc_reply_expected(struct rpc_task *task) ++ { ++ return (task->tk_msg.rpc_proc != NULL) && ++diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h ++index ad2e243f3f03..124f5a0faf3e 100644 ++--- a/include/linux/sunrpc/sched.h +++++ b/include/linux/sunrpc/sched.h ++@@ -90,6 +90,9 @@ struct rpc_task { ++ tk_garb_retry : 2, ++ tk_cred_retry : 2, ++ tk_rebind_retry : 2; +++#if IS_ENABLED(CONFIG_ENFS) +++ unsigned long tk_major_timeo; /* major timeout ticks */ +++#endif ++ }; ++ ++ typedef void (*rpc_action)(struct rpc_task *); ++@@ -118,6 +121,9 @@ struct rpc_task_setup { ++ */ ++ #define RPC_TASK_ASYNC 0x0001 /* is an async task */ ++ #define RPC_TASK_SWAPPER 0x0002 /* is swapping in/out */ +++#if IS_ENABLED(CONFIG_ENFS) +++#define RPC_TASK_FIXED 0x0004 /* detect xprt status task */ +++#endif ++ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ ++ #define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ ++ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ ++@@ -257,6 +263,9 @@ void rpc_destroy_mempool(void); ++ extern struct workqueue_struct *rpciod_workqueue; ++ extern struct workqueue_struct *xprtiod_workqueue; ++ void rpc_prepare_task(struct rpc_task *task); +++#if IS_ENABLED(CONFIG_ENFS) +++void rpc_init_task_retry_counters(struct rpc_task *task); +++#endif ++ ++ static inline int rpc_wait_for_completion_task(struct rpc_task *task) ++ { ++diff --git a/include/linux/sunrpc/sunrpc_enfs_adapter.h b/include/linux/sunrpc/sunrpc_enfs_adapter.h ++new file mode 100644 ++index 000000000000..28abedcf5cf6 ++--- /dev/null +++++ b/include/linux/sunrpc/sunrpc_enfs_adapter.h ++@@ -0,0 +1,128 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* Client-side SUNRPC ENFS adapter header. +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _SUNRPC_ENFS_ADAPTER_H_ +++#define _SUNRPC_ENFS_ADAPTER_H_ +++#include <linux/sunrpc/clnt.h> +++ +++#if IS_ENABLED(CONFIG_ENFS) +++ +++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) +++{ +++ xps->xps_nactive--; +++} +++ +++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) +++{ +++ xps->xps_nactive--; +++} +++ +++struct rpc_xprt *rpc_task_get_xprt +++(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +++ +++struct rpc_multipath_ops { +++ struct module *owner; +++ void (*create_clnt)(struct rpc_create_args *args, +++ struct rpc_clnt *clnt); +++ void (*releas_clnt)(struct rpc_clnt *clnt); +++ void (*create_xprt)(struct rpc_xprt *xprt); +++ void (*destroy_xprt)(struct rpc_xprt *xprt); +++ void (*xprt_iostat)(struct rpc_task *task); +++ void (*failover_handle)(struct rpc_task *task); +++ bool (*task_need_call_start_again)(struct rpc_task *task); +++ void (*adjust_task_timeout)(struct rpc_task *task, void *condition); +++ void (*init_task_req)(struct rpc_task *task, struct rpc_rqst *req); +++ bool (*prepare_transmit)(struct rpc_task *task); +++}; +++ +++extern struct rpc_multipath_ops __rcu *multipath_ops; +++void rpc_init_task_retry_counters(struct rpc_task *task); +++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops); +++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops); +++struct rpc_multipath_ops *rpc_multipath_ops_get(void); +++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops); +++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, +++ struct rpc_clnt *clnt); +++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt); +++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt); +++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt); +++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task); +++void rpc_multipath_ops_failover_handle(struct rpc_task *task); +++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task); +++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, +++ void *condition); +++void rpc_multipath_ops_init_task_req(struct rpc_task *task, +++ struct rpc_rqst *req); +++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task); +++ +++#else +++static inline struct rpc_xprt *rpc_task_get_xprt(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt) +++{ +++ return NULL; +++} +++ +++static inline void rpc_task_release_xprt(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt) +++{ +++} +++ +++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) +++{ +++} +++ +++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) +++{ +++} +++ +++static inline void rpc_multipath_ops_create_clnt +++(struct rpc_create_args *args, struct rpc_clnt *clnt) +++{ +++} +++ +++static inline void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) +++{ +++} +++ +++static inline bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) +++{ +++ return false; +++} +++ +++static inline void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) +++{ +++} +++ +++static inline void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) +++{ +++} +++ +++static inline void rpc_multipath_ops_failover_handle(struct rpc_task *task) +++{ +++} +++ +++static inline +++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) +++{ +++ return false; +++} +++ +++static inline void +++rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, void *condition) +++{ +++} +++ +++static inline void +++rpc_multipath_ops_init_task_req(struct rpc_task *task, struct rpc_rqst *req) +++{ +++} +++ +++static inline bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) +++{ +++ return false; +++} +++ +++#endif +++#endif // _SUNRPC_ENFS_ADAPTER_H_ ++diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h ++index ccfacca1eba9..2e47b3577947 100644 ++--- a/include/linux/sunrpc/xprt.h +++++ b/include/linux/sunrpc/xprt.h ++@@ -279,6 +279,10 @@ struct rpc_xprt { ++ atomic_t inject_disconnect; ++ #endif ++ struct rcu_head rcu; +++#if IS_ENABLED(CONFIG_ENFS) +++ atomic_long_t queuelen; +++ void *multipath_context; +++#endif ++ }; ++ ++ #if defined(CONFIG_SUNRPC_BACKCHANNEL) ++diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h ++index af1257c030d2..d54e4dbbbf34 100644 ++--- a/include/linux/sunrpc/xprtmultipath.h +++++ b/include/linux/sunrpc/xprtmultipath.h ++@@ -22,6 +22,10 @@ struct rpc_xprt_switch { ++ const struct rpc_xprt_iter_ops *xps_iter_ops; ++ ++ struct rcu_head xps_rcu; +++#if IS_ENABLED(CONFIG_ENFS) +++ unsigned int xps_nactive; +++ atomic_long_t xps_queuelen; +++#endif ++ }; ++ ++ struct rpc_xprt_iter { ++@@ -69,4 +73,8 @@ extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); ++ ++ extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, ++ const struct sockaddr *sap); +++#if IS_ENABLED(CONFIG_ENFS) +++extern void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, +++ struct rpc_xprt *xprt); +++#endif ++ #endif ++diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c ++index 0fc540b0d183..d7ffee637148 100644 ++--- a/net/sunrpc/clnt.c +++++ b/net/sunrpc/clnt.c ++@@ -37,6 +37,7 @@ ++ #include <linux/sunrpc/rpc_pipe_fs.h> ++ #include <linux/sunrpc/metrics.h> ++ #include <linux/sunrpc/bc_xprt.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ #include <trace/events/sunrpc.h> ++ ++ #include "sunrpc.h" ++@@ -490,6 +491,8 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, ++ } ++ } ++ +++ rpc_multipath_ops_create_clnt(args, clnt); +++ ++ clnt->cl_softrtry = 1; ++ if (args->flags & RPC_CLNT_CREATE_HARDRTRY) ++ clnt->cl_softrtry = 0; ++@@ -869,6 +872,8 @@ void rpc_shutdown_client(struct rpc_clnt *clnt) ++ list_empty(&clnt->cl_tasks), 1*HZ); ++ } ++ +++ rpc_multipath_ops_releas_clnt(clnt); +++ ++ rpc_release_client(clnt); ++ } ++ EXPORT_SYMBOL_GPL(rpc_shutdown_client); ++@@ -981,7 +986,13 @@ void rpc_task_release_transport(struct rpc_task *task) ++ ++ if (xprt) { ++ task->tk_xprt = NULL; ++- xprt_put(xprt); +++#if IS_ENABLED(CONFIG_ENFS) +++ if (task->tk_client) { +++ rpc_task_release_xprt(task->tk_client, xprt); +++ return; +++ } +++#endif +++ xprt_put(xprt); ++ } ++ } ++ EXPORT_SYMBOL_GPL(rpc_task_release_transport); ++@@ -990,6 +1001,10 @@ void rpc_task_release_client(struct rpc_task *task) ++ { ++ struct rpc_clnt *clnt = task->tk_client; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ rpc_task_release_transport(task); +++#endif +++ ++ if (clnt != NULL) { ++ /* Remove from client task list */ ++ spin_lock(&clnt->cl_lock); ++@@ -999,14 +1014,29 @@ void rpc_task_release_client(struct rpc_task *task) ++ ++ rpc_release_client(clnt); ++ } +++#if IS_ENABLED(CONFIG_ENFS) +++#else ++ rpc_task_release_transport(task); +++#endif ++ } ++ +++#if IS_ENABLED(CONFIG_ENFS) +++static struct rpc_xprt * +++rpc_task_get_next_xprt(struct rpc_clnt *clnt) +++{ +++ return rpc_task_get_xprt(clnt, xprt_iter_get_next(&clnt->cl_xpi)); +++} +++#endif +++ ++ static ++ void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) ++ { ++ if (!task->tk_xprt) +++#if IS_ENABLED(CONFIG_ENFS) +++ task->tk_xprt = rpc_task_get_next_xprt(clnt); +++#else ++ task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); +++#endif ++ } ++ ++ static ++@@ -1597,6 +1627,14 @@ call_reserveresult(struct rpc_task *task) ++ return; ++ case -EIO: /* probably a shutdown */ ++ break; +++#if IS_ENABLED(CONFIG_ENFS) +++ case -ETIMEDOUT: /* woken up; restart */ +++ if (rpc_multipath_ops_task_need_call_start_again(task)) { +++ rpc_task_release_transport(task); +++ task->tk_action = call_start; +++ return; +++ } +++#endif ++ default: ++ printk(KERN_ERR "%s: unrecognized error %d, exiting\n", ++ __func__, status); ++@@ -1962,6 +2000,10 @@ call_transmit(struct rpc_task *task) ++ return; ++ if (!xprt_prepare_transmit(task)) ++ return; +++ +++ if (rpc_multipath_ops_prepare_transmit(task)) +++ return; +++ ++ task->tk_action = call_transmit_status; ++ /* Encode here so that rpcsec_gss can use correct sequence number. */ ++ if (rpc_task_need_encode(task)) { ++@@ -2277,6 +2319,9 @@ call_timeout(struct rpc_task *task) ++ ++ retry: ++ task->tk_action = call_bind; +++#if IS_ENABLED(CONFIG_ENFS) +++ rpc_multipath_ops_failover_handle(task); +++#endif ++ task->tk_status = 0; ++ } ++ ++@@ -2961,3 +3006,30 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) ++ } ++ EXPORT_SYMBOL_GPL(rpc_clnt_swap_deactivate); ++ #endif /* CONFIG_SUNRPC_SWAP */ +++ +++#if IS_ENABLED(CONFIG_ENFS) +++/* rpc_clnt_test_xprt - Test and add a new transport to a rpc_clnt +++ * @clnt: pointer to struct rpc_clnt +++ * @xprt: pointer struct rpc_xprt +++ * @ops: async operation +++ */ +++int +++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, +++ const struct rpc_call_ops *ops, void *data, int flags) +++{ +++ struct rpc_cred *cred; +++ struct rpc_task *task; +++ +++ cred = authnull_ops.lookup_cred(NULL, NULL, 0); +++ task = rpc_call_null_helper(clnt, xprt, cred, +++ RPC_TASK_SOFT | RPC_TASK_SOFTCONN | flags, +++ ops, data); +++ put_rpccred(cred); +++ if (IS_ERR(task)) +++ return PTR_ERR(task); +++ +++ rpc_put_task(task); +++ return 1; +++} +++EXPORT_SYMBOL_GPL(rpc_clnt_test_xprt); +++#endif ++diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c ++index a873c92a4898..2254fea0e863 100644 ++--- a/net/sunrpc/sched.c +++++ b/net/sunrpc/sched.c ++@@ -20,7 +20,7 @@ ++ #include <linux/mutex.h> ++ #include <linux/freezer.h> ++ ++-#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ ++ #include "sunrpc.h" ++ ++@@ -962,7 +962,12 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta ++ /* Initialize workqueue for async tasks */ ++ task->tk_workqueue = task_setup_data->workqueue; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ task->tk_xprt = rpc_task_get_xprt(task_setup_data->rpc_client, +++ xprt_get(task_setup_data->rpc_xprt)); +++#else ++ task->tk_xprt = xprt_get(task_setup_data->rpc_xprt); +++#endif ++ ++ if (task->tk_ops->rpc_call_prepare != NULL) ++ task->tk_action = rpc_prepare_task; ++diff --git a/net/sunrpc/sunrpc_enfs_adapter.c b/net/sunrpc/sunrpc_enfs_adapter.c ++new file mode 100644 ++index 000000000000..c1543545c6de ++--- /dev/null +++++ b/net/sunrpc/sunrpc_enfs_adapter.c ++@@ -0,0 +1,214 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* Client-side SUNRPC ENFS adapter header. +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> +++ +++struct rpc_multipath_ops __rcu *multipath_ops; +++ +++void rpc_init_task_retry_counters(struct rpc_task *task) +++{ +++ /* Initialize retry counters */ +++ task->tk_garb_retry = 2; +++ task->tk_cred_retry = 2; +++ task->tk_rebind_retry = 2; +++} +++EXPORT_SYMBOL_GPL(rpc_init_task_retry_counters); +++ +++struct rpc_xprt * +++rpc_task_get_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) +++{ +++ struct rpc_xprt_switch *xps; +++ +++ if (!xprt) +++ return NULL; +++ rcu_read_lock(); +++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); +++ atomic_long_inc(&xps->xps_queuelen); +++ rcu_read_unlock(); +++ atomic_long_inc(&xprt->queuelen); +++ +++ return xprt; +++} +++ +++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops) +++{ +++ struct rpc_multipath_ops *old; +++ +++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, NULL, ops); +++ if (!old || old == ops) +++ return 0; +++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_register); +++ +++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops) +++{ +++ struct rpc_multipath_ops *old; +++ +++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, ops, NULL); +++ if (!old || old == ops) +++ return 0; +++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_unregister); +++ +++struct rpc_multipath_ops *rpc_multipath_ops_get(void) +++{ +++ struct rpc_multipath_ops *ops; +++ +++ rcu_read_lock(); +++ ops = rcu_dereference(multipath_ops); +++ if (!ops) { +++ rcu_read_unlock(); +++ return NULL; +++ } +++ if (!try_module_get(ops->owner)) +++ ops = NULL; +++ rcu_read_unlock(); +++ return ops; +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_get); +++ +++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops) +++{ +++ if (ops) +++ module_put(ops->owner); +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_put); +++ +++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) +++{ +++ struct rpc_xprt_switch *xps; +++ +++ atomic_long_dec(&xprt->queuelen); +++ rcu_read_lock(); +++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); +++ atomic_long_dec(&xps->xps_queuelen); +++ rcu_read_unlock(); +++ +++ xprt_put(xprt); +++} +++ +++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, +++ struct rpc_clnt *clnt) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ if (args->multipath_option) { +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->create_clnt) +++ mops->create_clnt(args, clnt); +++ rpc_multipath_ops_put(mops); +++ } +++} +++ +++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->releas_clnt) +++ mops->releas_clnt(clnt); +++ +++ rpc_multipath_ops_put(mops); +++} +++ +++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->create_xprt) { +++ mops->create_xprt(xprt); +++ if (!xprt->multipath_context) { +++ rpc_multipath_ops_put(mops); +++ return true; +++ } +++ } +++ rpc_multipath_ops_put(mops); +++ return false; +++} +++ +++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ if (xprt->multipath_context) { +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->destroy_xprt) +++ mops->destroy_xprt(xprt); +++ rpc_multipath_ops_put(mops); +++ } +++} +++ +++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ mops = rpc_multipath_ops_get(); +++ if (task->tk_client && mops && mops->xprt_iostat) +++ mops->xprt_iostat(task); +++ rpc_multipath_ops_put(mops); +++} +++ +++void rpc_multipath_ops_failover_handle(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mpath_ops = NULL; +++ +++ mpath_ops = rpc_multipath_ops_get(); +++ if (mpath_ops && mpath_ops->failover_handle) +++ mpath_ops->failover_handle(task); +++ rpc_multipath_ops_put(mpath_ops); +++} +++ +++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mpath_ops = NULL; +++ bool ret = false; +++ +++ mpath_ops = rpc_multipath_ops_get(); +++ if (mpath_ops && mpath_ops->task_need_call_start_again) +++ ret = mpath_ops->task_need_call_start_again(task); +++ rpc_multipath_ops_put(mpath_ops); +++ return ret; +++} +++ +++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, +++ void *condition) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->adjust_task_timeout) +++ mops->adjust_task_timeout(task, NULL); +++ rpc_multipath_ops_put(mops); +++} +++ +++void rpc_multipath_ops_init_task_req(struct rpc_task *task, +++ struct rpc_rqst *req) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->init_task_req) +++ mops->init_task_req(task, req); +++ rpc_multipath_ops_put(mops); +++} +++ +++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->prepare_transmit) { +++ if (!(mops->prepare_transmit(task))) { +++ rpc_multipath_ops_put(mops); +++ return true; +++ } +++ } +++ rpc_multipath_ops_put(mops); +++ return false; +++} ++diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c ++index c912bf20faa2..c2b63b3d5217 100644 ++--- a/net/sunrpc/xprt.c +++++ b/net/sunrpc/xprt.c ++@@ -48,6 +48,7 @@ ++ #include <linux/sunrpc/clnt.h> ++ #include <linux/sunrpc/metrics.h> ++ #include <linux/sunrpc/bc_xprt.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ #include <linux/rcupdate.h> ++ ++ #include <trace/events/sunrpc.h> ++@@ -259,6 +260,9 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) ++ dprintk("RPC: %5u failed to lock transport %p\n", ++ task->tk_pid, xprt); ++ task->tk_timeout = 0; +++ +++ rpc_multipath_ops_adjust_task_timeout(task, NULL); +++ ++ task->tk_status = -EAGAIN; ++ if (req == NULL) ++ priority = RPC_PRIORITY_LOW; ++@@ -560,6 +564,9 @@ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action) ++ struct rpc_xprt *xprt = req->rq_xprt; ++ ++ task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0; +++ +++ rpc_multipath_ops_adjust_task_timeout(task, NULL); +++ ++ rpc_sleep_on(&xprt->pending, task, action); ++ } ++ EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space); ++@@ -1347,6 +1354,9 @@ xprt_request_init(struct rpc_task *task) ++ req->rq_rcv_buf.buflen = 0; ++ req->rq_release_snd_buf = NULL; ++ xprt_reset_majortimeo(req); +++ +++ rpc_multipath_ops_init_task_req(task, req); +++ ++ dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, ++ req, ntohl(req->rq_xid)); ++ } ++@@ -1427,6 +1437,9 @@ void xprt_release(struct rpc_task *task) ++ task->tk_ops->rpc_count_stats(task, task->tk_calldata); ++ else if (task->tk_client) ++ rpc_count_iostats(task, task->tk_client->cl_metrics); +++ +++ rpc_multipath_ops_xprt_iostat(task); +++ ++ spin_lock(&xprt->recv_lock); ++ if (!list_empty(&req->rq_list)) { ++ list_del_init(&req->rq_list); ++@@ -1455,6 +1468,7 @@ void xprt_release(struct rpc_task *task) ++ else ++ xprt_free_bc_request(req); ++ } +++EXPORT_SYMBOL_GPL(xprt_release); ++ ++ static void xprt_init(struct rpc_xprt *xprt, struct net *net) ++ { ++@@ -1528,6 +1542,10 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) ++ return ERR_PTR(-ENOMEM); ++ } ++ +++if (rpc_multipath_ops_create_xprt(xprt)) { +++ xprt_destroy(xprt); +++ return ERR_PTR(-ENOMEM); +++} ++ rpc_xprt_debugfs_register(xprt); ++ ++ dprintk("RPC: created transport %p with %u slots\n", xprt, ++@@ -1547,6 +1565,9 @@ static void xprt_destroy_cb(struct work_struct *work) ++ rpc_destroy_wait_queue(&xprt->sending); ++ rpc_destroy_wait_queue(&xprt->backlog); ++ kfree(xprt->servername); +++ +++ rpc_multipath_ops_destroy_xprt(xprt); +++ ++ /* ++ * Tear down transport state and free the rpc_xprt ++ */ ++diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c ++index 6ebaa58b4eff..6202a0be1327 100644 ++--- a/net/sunrpc/xprtmultipath.c +++++ b/net/sunrpc/xprtmultipath.c ++@@ -18,6 +18,7 @@ ++ #include <linux/sunrpc/xprt.h> ++ #include <linux/sunrpc/addr.h> ++ #include <linux/sunrpc/xprtmultipath.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ ++ typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct list_head *head, ++ const struct rpc_xprt *cur); ++@@ -26,8 +27,8 @@ static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular; ++ static const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin; ++ static const struct rpc_xprt_iter_ops rpc_xprt_iter_listall; ++ ++-static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++- struct rpc_xprt *xprt) +++void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, +++ struct rpc_xprt *xprt) ++ { ++ if (unlikely(xprt_get(xprt) == NULL)) ++ return; ++@@ -36,7 +37,9 @@ static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++ if (xps->xps_nxprts == 0) ++ xps->xps_net = xprt->xprt_net; ++ xps->xps_nxprts++; +++ rpc_xps_nactive_add_one(xps); ++ } +++EXPORT_SYMBOL(xprt_switch_add_xprt_locked); ++ ++ /** ++ * rpc_xprt_switch_add_xprt - Add a new rpc_xprt to an rpc_xprt_switch ++@@ -63,6 +66,7 @@ static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps, ++ if (unlikely(xprt == NULL)) ++ return; ++ xps->xps_nxprts--; +++ rpc_xps_nactive_sub_one(xps); ++ if (xps->xps_nxprts == 0) ++ xps->xps_net = NULL; ++ smp_wmb(); ++@@ -84,7 +88,7 @@ void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, ++ spin_unlock(&xps->xps_lock); ++ xprt_put(xprt); ++ } ++- +++EXPORT_SYMBOL(rpc_xprt_switch_remove_xprt); ++ /** ++ * xprt_switch_alloc - Allocate a new struct rpc_xprt_switch ++ * @xprt: pointer to struct rpc_xprt ++@@ -102,7 +106,13 @@ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, ++ if (xps != NULL) { ++ spin_lock_init(&xps->xps_lock); ++ kref_init(&xps->xps_kref); +++#if IS_ENABLED(CONFIG_ENFS) +++ xps->xps_nxprts = 0; +++ xps->xps_nactive = 0; +++ atomic_long_set(&xps->xps_queuelen, 0); +++#else ++ xps->xps_nxprts = 0; +++#endif ++ INIT_LIST_HEAD(&xps->xps_xprt_list); ++ xps->xps_iter_ops = &rpc_xprt_iter_singular; ++ xprt_switch_add_xprt_locked(xps, xprt); ++@@ -148,6 +158,7 @@ struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps) ++ return xps; ++ return NULL; ++ } +++EXPORT_SYMBOL(xprt_switch_get); ++ ++ /** ++ * xprt_switch_put - Release a reference to a rpc_xprt_switch ++@@ -160,6 +171,7 @@ void xprt_switch_put(struct rpc_xprt_switch *xps) ++ if (xps != NULL) ++ kref_put(&xps->xps_kref, xprt_switch_free); ++ } +++EXPORT_SYMBOL(xprt_switch_put); ++ ++ /** ++ * rpc_xprt_switch_set_roundrobin - Set a round-robin policy on rpc_xprt_switch +diff --git a/0003-add_enfs_module_for_nfs_mount_option.patch b/0003-add_enfs_module_for_nfs_mount_option.patch +new file mode 100644 +index 0000000..70753b5 +--- /dev/null ++++ b/0003-add_enfs_module_for_nfs_mount_option.patch +@@ -0,0 +1,1209 @@ ++diff --git a/fs/nfs/enfs/Makefile b/fs/nfs/enfs/Makefile ++new file mode 100644 ++index 000000000000..6e83eb23c668 ++--- /dev/null +++++ b/fs/nfs/enfs/Makefile ++@@ -0,0 +1,18 @@ +++obj-m += enfs.o +++ +++#EXTRA_CFLAGS += -I$(PWD)/.. +++ +++enfs-y := enfs_init.o +++enfs-y += enfs_config.o +++enfs-y += mgmt_init.o +++enfs-y += enfs_multipath_client.o +++enfs-y += enfs_multipath_parse.o +++enfs-y += failover_path.o +++enfs-y += failover_time.o +++enfs-y += enfs_roundrobin.o +++enfs-y += enfs_multipath.o +++enfs-y += enfs_path.o +++enfs-y += enfs_proc.o +++enfs-y += enfs_remount.o +++enfs-y += pm_ping.o +++enfs-y += pm_state.o ++diff --git a/fs/nfs/enfs/enfs.h b/fs/nfs/enfs/enfs.h ++new file mode 100644 ++index 000000000000..be3d95220088 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs.h ++@@ -0,0 +1,62 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS multipath adapt header. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++ +++#ifndef _ENFS_H_ +++#define _ENFS_H_ +++#include <linux/atomic.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs3.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include "../enfs_adapter.h" +++ +++#define IP_ADDRESS_LEN_MAX 64 +++#define MAX_IP_PAIR_PER_MOUNT 8 +++#define MAX_IP_INDEX (MAX_IP_PAIR_PER_MOUNT) +++#define MAX_SUPPORTED_LOCAL_IP_COUNT 8 +++#define MAX_SUPPORTED_REMOTE_IP_COUNT 32 +++#define MAX_DNS_NAME_LEN 512 +++#define MAX_DNS_SUPPORTED 2 +++#define EXTEND_CMD_MAX_BUF_LEN 65356 +++ +++ +++struct nfs_ip_list { +++ int count; +++ struct sockaddr_storage address[MAX_SUPPORTED_REMOTE_IP_COUNT]; +++ size_t addrlen[MAX_SUPPORTED_REMOTE_IP_COUNT]; +++}; +++ +++struct NFS_ROUTE_DNS_S { +++ char dnsname[MAX_DNS_NAME_LEN]; // valid only if dnsExist is true +++}; +++ +++struct NFS_ROUTE_DNS_INFO_S { +++ int dnsNameCount; // Count of DNS name in the list +++ // valid only if dnsExist is true +++ struct NFS_ROUTE_DNS_S routeRemoteDnsList[MAX_DNS_SUPPORTED]; +++}; +++ +++struct rpc_iostats; +++struct enfs_xprt_context { +++ struct sockaddr_storage srcaddr; +++ struct rpc_iostats *stats; +++ bool main; +++ atomic_t path_state; +++ atomic_t path_check_state; +++}; +++ +++static inline bool enfs_is_main_xprt(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = xprt->multipath_context; +++ +++ if (!ctx) +++ return false; +++ return ctx->main; +++} +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_init.c b/fs/nfs/enfs/enfs_init.c ++new file mode 100644 ++index 000000000000..4b55608191a7 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_init.c ++@@ -0,0 +1,98 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/module.h> +++#include <linux/sunrpc/sched.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs3.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include "enfs.h" +++#include "enfs_multipath_parse.h" +++#include "enfs_multipath_client.h" +++#include "enfs_remount.h" +++#include "init.h" +++#include "enfs_log.h" +++#include "enfs_multipath.h" +++#include "mgmt_init.h" +++ +++struct enfs_adapter_ops enfs_adapter = { +++ .name = "enfs", +++ .owner = THIS_MODULE, +++ .parse_mount_options = nfs_multipath_parse_options, +++ .free_mount_options = nfs_multipath_free_options, +++ .client_info_init = nfs_multipath_client_info_init, +++ .client_info_free = nfs_multipath_client_info_free, +++ .client_info_match = nfs_multipath_client_info_match, +++ .client_info_show = nfs_multipath_client_info_show, +++ .remount_ip_list = enfs_remount_iplist, +++}; +++ +++int32_t enfs_init(void) +++{ +++ int err; +++ +++ err = enfs_multipath_init(); +++ if (err) { +++ enfs_log_error("init multipath failed.\n"); +++ goto out; +++ } +++ +++ err = mgmt_init(); +++ if (err != 0) { +++ enfs_log_error("init mgmt failed.\n"); +++ goto out_tp_exit; +++ } +++ +++ return 0; +++ +++out_tp_exit: +++ enfs_multipath_exit(); +++out: +++ return err; +++} +++ +++void enfs_fini(void) +++{ +++ mgmt_fini(); +++ +++ enfs_multipath_exit(); +++} +++ +++static int __init init_enfs(void) +++{ +++ int ret; +++ +++ ret = enfs_adapter_register(&enfs_adapter); +++ if (ret) { +++ pr_err("regist enfs_adapter fail. ret %d\n", ret); +++ return -1; +++ } +++ +++ ret = enfs_init(); +++ if (ret) { +++ enfs_adapter_unregister(&enfs_adapter); +++ return -1; +++ } +++ +++ return 0; +++} +++ +++static void __exit exit_enfs(void) +++{ +++ enfs_fini(); +++ enfs_adapter_unregister(&enfs_adapter); +++} +++ +++MODULE_LICENSE("GPL"); +++MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +++MODULE_DESCRIPTION("Nfs client router"); +++MODULE_VERSION("1.0"); +++ +++module_init(init_enfs); +++module_exit(exit_enfs); ++diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c ++new file mode 100644 ++index 000000000000..63c02898a42c ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.c ++@@ -0,0 +1,340 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/proc_fs.h> +++#include <linux/seq_file.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/addr.h> +++#include "enfs_multipath_client.h" +++#include "enfs_multipath_parse.h" +++ +++int +++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, +++ const struct nfs_client_initdata *client_init_data) +++{ +++ struct multipath_mount_options *mount_options = +++ (struct multipath_mount_options *)client_init_data->enfs_option; +++ +++ if (mount_options->local_ip_list) { +++ client_info->local_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->local_ip_list) +++ return -ENOMEM; +++ +++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->remote_ip_list) { +++ +++ client_info->remote_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->remote_ip_list) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->remote_ip_list, +++ mount_options->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->pRemoteDnsInfo) { +++ client_info->pRemoteDnsInfo = +++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); +++ +++ if (!client_info->pRemoteDnsInfo) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ kfree(client_info->remote_ip_list); +++ client_info->remote_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->pRemoteDnsInfo, +++ mount_options->pRemoteDnsInfo, +++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); +++ } +++ return 0; +++} +++ +++void nfs_multipath_client_info_free_work(struct work_struct *work) +++{ +++ +++ struct multipath_client_info *clp_info; +++ +++ if (work == NULL) +++ return; +++ +++ clp_info = container_of(work, struct multipath_client_info, work); +++ +++ if (clp_info->local_ip_list != NULL) { +++ kfree(clp_info->local_ip_list); +++ clp_info->local_ip_list = NULL; +++ } +++ if (clp_info->remote_ip_list != NULL) { +++ kfree(clp_info->remote_ip_list); +++ clp_info->remote_ip_list = NULL; +++ } +++ kfree(clp_info); +++} +++ +++void nfs_multipath_client_info_free(void *data) +++{ +++ struct multipath_client_info *clp_info = +++ (struct multipath_client_info *)data; +++ +++ if (clp_info == NULL) +++ return; +++ pr_info("free client info %p.\n", clp_info); +++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); +++ schedule_work(&clp_info->work); +++} +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init) +++{ +++ int rc; +++ struct multipath_client_info *info; +++ struct multipath_client_info **enfs_info; +++ /* no multi path info, no need do multipath init */ +++ if (cl_init->enfs_option == NULL) +++ return 0; +++ enfs_info = (struct multipath_client_info **)data; +++ if (enfs_info == NULL) +++ return -EINVAL; +++ +++ if (*enfs_info == NULL) +++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), +++ GFP_KERNEL); +++ +++ if (*enfs_info == NULL) +++ return -ENOMEM; +++ +++ info = (struct multipath_client_info *)*enfs_info; +++ pr_info("init client info %p.\n", info); +++ rc = nfs_multipath_client_mount_info_init(info, cl_init); +++ if (rc) { +++ nfs_multipath_client_info_free((void *)info); +++ return rc; +++ } +++ return rc; +++} +++ +++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, +++ const struct nfs_ip_list *ip_list_dst) +++{ +++ int i; +++ int j; +++ bool is_find; +++ /* if both are equal or NULL, then return true. */ +++ if (ip_list_src == ip_list_dst) +++ return true; +++ +++ if ((ip_list_src == NULL || ip_list_dst == NULL)) +++ return false; +++ +++ if (ip_list_src->count != ip_list_dst->count) +++ return false; +++ +++ for (i = 0; i < ip_list_src->count; i++) { +++ is_find = false; +++ for (j = 0; j < ip_list_src->count; j++) { +++ if (rpc_cmp_addr_port( +++ (const struct sockaddr *) +++ &ip_list_src->address[i], +++ (const struct sockaddr *) +++ &ip_list_dst->address[j]) +++ ) { +++ is_find = true; +++ break; +++ } +++ } +++ if (is_find == false) +++ return false; +++ } +++ return true; +++} +++ +++int +++nfs_multipath_dns_list_info_match( +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) +++{ +++ int i; +++ +++ /* if both are equal or NULL, then return true. */ +++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) +++ return true; +++ +++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) +++ return false; +++ +++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) +++ return false; +++ +++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { +++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, +++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) +++ return false; +++ } +++ return true; +++} +++ +++int nfs_multipath_client_info_match(void *src, void *dst) +++{ +++ int ret = true; +++ +++ struct multipath_client_info *src_info; +++ struct multipath_mount_options *dst_info; +++ +++ src_info = (struct multipath_client_info *)src; +++ dst_info = (struct multipath_mount_options *)dst; +++ pr_info("try match client .\n"); +++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, +++ dst_info->local_ip_list); +++ if (ret == false) { +++ pr_err("local_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, +++ dst_info->remote_ip_list); +++ if (ret == false) { +++ pr_err("remote_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, +++ dst_info->pRemoteDnsInfo); +++ if (ret == false) { +++ pr_err("dns not match.\n"); +++ return ret; +++ } +++ pr_info("try match client ret %d.\n", ret); +++ return ret; +++} +++ +++void nfs_multipath_print_ip_info(struct seq_file *mount_option, +++ struct nfs_ip_list *ip_list, +++ const char *type) +++{ +++ char buf[IP_ADDRESS_LEN_MAX + 1]; +++ int len = 0; +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < ip_list->count; i++) { +++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], +++ buf, IP_ADDRESS_LEN_MAX); +++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) +++ buf[len] = '\0'; +++ +++ if (i == 0) +++ seq_printf(mount_option, "%s", buf); +++ else +++ seq_printf(mount_option, "~%s", buf); +++ dfprintk(MOUNT, +++ "NFS: show nfs mount option type:%s %s [%s]\n", +++ type, buf, __func__); +++ } +++} +++ +++void nfs_multipath_print_dns_info(struct seq_file *mount_option, +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, +++ const char *type) +++{ +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { +++ if (i == 0) +++ seq_printf(mount_option, +++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) +++ seq_printf(mount_option, ",%s]", +++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else +++ seq_printf(mount_option, +++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ } +++} +++ +++ +++static void multipath_print_sockaddr(struct seq_file *seq, +++ struct sockaddr *addr) +++{ +++ switch (addr->sa_family) { +++ case AF_INET: { +++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; +++ +++ seq_printf(seq, "%pI4", &sin->sin_addr); +++ return; +++ } +++ case AF_INET6: { +++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; +++ +++ seq_printf(seq, "%pI6", &sin6->sin6_addr); +++ return; +++ } +++ default: +++ break; +++ } +++ pr_err("unsupport family:%d\n", addr->sa_family); +++} +++ +++static void multipath_print_enfs_info(struct seq_file *seq, +++ struct nfs_server *server) +++{ +++ struct sockaddr_storage peeraddr; +++ struct rpc_clnt *next = server->client; +++ +++ rpc_peeraddr(server->client, +++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); +++ seq_puts(seq, ",enfs_info="); +++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); +++ +++ while (next->cl_parent) { +++ if (next == next->cl_parent) +++ break; +++ next = next->cl_parent; +++ } +++ seq_printf(seq, "_%u", next->cl_clid); +++} +++ +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) +++{ +++ struct nfs_server *server = data; +++ struct multipath_client_info *client_info = +++ server->nfs_client->cl_multipath_data; +++ +++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); +++ if ((client_info->remote_ip_list) && +++ (client_info->remote_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->remote_ip_list, +++ "remoteaddrs"); +++ +++ if ((client_info->local_ip_list) && +++ (client_info->local_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->local_ip_list, +++ "localaddrs"); +++ +++ if ((client_info->pRemoteDnsInfo) && +++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) +++ nfs_multipath_print_dns_info(mount_option, +++ client_info->pRemoteDnsInfo, +++ "remotednsname"); +++ +++ multipath_print_enfs_info(mount_option, server); +++} ++diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h ++new file mode 100644 ++index 000000000000..208f7260690d ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.h ++@@ -0,0 +1,26 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _ENFS_MULTIPATH_CLIENT_H_ +++#define _ENFS_MULTIPATH_CLIENT_H_ +++ +++#include "enfs.h" +++ +++struct multipath_client_info { +++ struct work_struct work; +++ struct nfs_ip_list *remote_ip_list; +++ struct nfs_ip_list *local_ip_list; +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; +++ s64 client_id; +++}; +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init); +++void nfs_multipath_client_info_free(void *data); +++int nfs_multipath_client_info_match(void *src, void *dst); +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_multipath_parse.c b/fs/nfs/enfs/enfs_multipath_parse.c ++new file mode 100644 ++index 000000000000..9c4c6c1880b6 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_parse.c ++@@ -0,0 +1,601 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/parser.h> +++#include <linux/kern_levels.h> +++#include <linux/sunrpc/addr.h> +++#include "enfs_multipath_parse.h" +++#include "enfs_log.h" +++ +++#define NFSDBG_FACILITY NFSDBG_CLIENT +++ +++void nfs_multipath_parse_ip_ipv6_add(struct sockaddr_in6 *sin6, int add_num) +++{ +++ int i; +++ +++ pr_info("NFS: before %08x%08x%08x%08x add_num: %d[%s]\n", +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), +++ add_num, __func__); +++ for (i = 0; i < add_num; i++) { +++ sin6->sin6_addr.in6_u.u6_addr32[3] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[3] != 0) +++ continue; +++ +++ sin6->sin6_addr.in6_u.u6_addr32[2] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[2] != 0) +++ continue; +++ +++ sin6->sin6_addr.in6_u.u6_addr32[1] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[1] != 0) +++ continue; +++ +++ sin6->sin6_addr.in6_u.u6_addr32[0] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[0] != 0) +++ continue; +++ } +++ +++ return; +++ +++} +++ +++static int nfs_multipath_parse_ip_range(struct net *net_ns, const char *cursor, +++ struct nfs_ip_list *ip_list, enum nfsmultipathoptions type) +++{ +++ struct sockaddr_storage addr; +++ struct sockaddr_storage tmp_addr; +++ int i; +++ size_t len; +++ int add_num = 1; +++ bool duplicate_flag = false; +++ bool is_complete = false; +++ struct sockaddr_in *sin4; +++ struct sockaddr_in6 *sin6; +++ +++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", +++ cursor, type, __func__); +++ len = rpc_pton(net_ns, cursor, strlen(cursor), +++ (struct sockaddr *)&addr, sizeof(addr)); +++ if (!len) +++ return -EINVAL; +++ +++ if (addr.ss_family != ip_list->address[ip_list->count - 1].ss_family) { +++ pr_info("NFS: %s parsing nfs mount option type: %d fail.\n", +++ __func__, type); +++ return -EINVAL; +++ } +++ +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &ip_list->address[ip_list->count - 1], +++ (const struct sockaddr *)&addr)) { +++ +++ pr_info("range ip is same ip.\n"); +++ return 0; +++ +++ } +++ +++ while (true) { +++ +++ tmp_addr = ip_list->address[ip_list->count - 1]; +++ +++ switch (addr.ss_family) { +++ case AF_INET: +++ sin4 = (struct sockaddr_in *)&tmp_addr; +++ +++ sin4->sin_addr.s_addr = +++ htonl(ntohl(sin4->sin_addr.s_addr) + add_num); +++ +++ pr_info("NFS: mount option ip%08x type: %d ipcont %d [%s]\n", +++ ntohl(sin4->sin_addr.s_addr), +++ type, ip_list->count, __func__); +++ break; +++ case AF_INET6: +++ sin6 = (struct sockaddr_in6 *)&tmp_addr; +++ nfs_multipath_parse_ip_ipv6_add(sin6, add_num); +++ pr_info("NFS: mount option ip %08x%08x%08x%08x type: %d ipcont %d [%s]\n", +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), +++ type, ip_list->count, __func__); +++ break; +++ // return -EOPNOTSUPP; +++ default: +++ return -EOPNOTSUPP; +++ } +++ +++ if (rpc_cmp_addr((const struct sockaddr *)&tmp_addr, +++ (const struct sockaddr *)&addr)) { +++ is_complete = true; +++ } +++ // delete duplicate ip, continuosly repeat, skip it +++ for (i = 0; i < ip_list->count; i++) { +++ duplicate_flag = false; +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &ip_list->address[i], +++ (const struct sockaddr *)&tmp_addr)) { +++ add_num++; +++ duplicate_flag = true; +++ break; +++ } +++ } +++ +++ if (duplicate_flag == false) { +++ pr_info("this ip not duplicate;"); +++ add_num = 1; +++ // if not repeat but omit limit return false +++ if ((type == LOCALADDR && +++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || +++ (type == REMOTEADDR && +++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { +++ +++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", +++ __func__, type, ip_list->count, +++ type == LOCALADDR ? +++ MAX_SUPPORTED_LOCAL_IP_COUNT : +++ MAX_SUPPORTED_REMOTE_IP_COUNT); +++ ip_list->count = 0; +++ return -ENOSPC; +++ } +++ ip_list->address[ip_list->count] = tmp_addr; +++ +++ ip_list->addrlen[ip_list->count] = +++ ip_list->addrlen[ip_list->count - 1]; +++ +++ ip_list->count += 1; +++ } +++ if (is_complete == true) +++ break; +++ } +++ return 0; +++} +++ +++int nfs_multipath_parse_ip_list_inter(struct nfs_ip_list *ip_list, +++ struct net *net_ns, +++ char *cursor, enum nfsmultipathoptions type) +++{ +++ int i = 0; +++ struct sockaddr_storage addr; +++ struct sockaddr_storage swap; +++ int len; +++ +++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", +++ cursor, type, __func__); +++ +++ len = rpc_pton(net_ns, cursor, +++ strlen(cursor), +++ (struct sockaddr *)&addr, sizeof(addr)); +++ if (!len) +++ return -EINVAL; +++ +++ // check repeated ip +++ for (i = 0; i < ip_list->count; i++) { +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &ip_list->address[i], +++ (const struct sockaddr *)&addr)) { +++ +++ pr_info("NFS: mount option '%s' type:%d index %d same as before index %d [%s]\n", +++ cursor, type, ip_list->count, i, __func__); +++ // prevent this ip is beginning +++ // if repeated take it to the end of list +++ swap = ip_list->address[i]; +++ +++ ip_list->address[i] = +++ ip_list->address[ip_list->count-1]; +++ +++ ip_list->address[ip_list->count-1] = swap; +++ return 0; +++ } +++ } +++ // if not repeated, check exceed limit +++ if ((type == LOCALADDR && +++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || +++ (type == REMOTEADDR && +++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { +++ +++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", +++ __func__, type, ip_list->count, +++ type == LOCALADDR ? +++ MAX_SUPPORTED_LOCAL_IP_COUNT : +++ MAX_SUPPORTED_REMOTE_IP_COUNT); +++ +++ ip_list->count = 0; +++ return -ENOSPC; +++ } +++ ip_list->address[ip_list->count] = addr; +++ ip_list->addrlen[ip_list->count] = len; +++ ip_list->count++; +++ +++ return 0; +++} +++ +++char *nfs_multipath_parse_ip_list_get_cursor(char **buf_to_parse, bool *single) +++{ +++ char *cursor = NULL; +++ const char *single_sep = strchr(*buf_to_parse, '~'); +++ const char *range_sep = strchr(*buf_to_parse, '-'); +++ +++ *single = true; +++ if (range_sep) { +++ if (range_sep > single_sep) { // A-B or A~B-C +++ if (single_sep == NULL) { // A-B +++ cursor = strsep(buf_to_parse, "-"); +++ if (cursor) +++ *single = false; +++ } else// A~B-C +++ cursor = strsep(buf_to_parse, "~"); +++ } else { // A-B~C +++ cursor = strsep(buf_to_parse, "-"); +++ if (cursor) +++ *single = false; +++ } +++ } else { // A~B~C +++ cursor = strsep(buf_to_parse, "~"); +++ } +++ return cursor; +++} +++ +++bool nfs_multipath_parse_param_check(enum nfsmultipathoptions type, +++ struct multipath_mount_options *options) +++{ +++ if (type == REMOUNTREMOTEADDR && options->remote_ip_list->count != 0) { +++ memset(options->remote_ip_list, 0, sizeof(struct nfs_ip_list)); +++ return true; +++ } +++ if (type == REMOUNTLOCALADDR && options->local_ip_list->count != 0) { +++ memset(options->local_ip_list, 0, sizeof(struct nfs_ip_list)); +++ return true; +++ } +++ if ((type == REMOTEADDR || type == REMOTEDNSNAME) && +++ options->pRemoteDnsInfo->dnsNameCount != 0) { +++ +++ pr_info("[MULTIPATH:%s] parse for %d ,already have dns\n", +++ __func__, type); +++ return false; +++ } else if ((type == REMOTEADDR || type == REMOTEDNSNAME) && +++ options->remote_ip_list->count != 0) { +++ +++ pr_info("[MULTIPATH:%s] parse for %d ,already have iplist\n", +++ __func__, type); +++ return false; +++ } +++ return true; +++} +++ +++int nfs_multipath_parse_ip_list(char *buffer, struct net *net_ns, +++ struct multipath_mount_options *options, +++ enum nfsmultipathoptions type) +++{ +++ char *buf_to_parse = NULL; +++ bool prev_range = false; +++ int ret = 0; +++ char *cursor = NULL; +++ bool single = true; +++ struct nfs_ip_list *ip_list_tmp = NULL; +++ +++ if (!nfs_multipath_parse_param_check(type, options)) +++ return -ENOTSUPP; +++ +++ if (type == REMOUNTREMOTEADDR) +++ type = REMOTEADDR; +++ +++ if (type == REMOUNTLOCALADDR) +++ type = LOCALADDR; +++ +++ if (type == LOCALADDR) +++ ip_list_tmp = options->local_ip_list; +++ else +++ ip_list_tmp = options->remote_ip_list; +++ +++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", +++ buffer, type, __func__); +++ +++ buf_to_parse = buffer; +++ while (buf_to_parse != NULL) { +++ cursor = +++ nfs_multipath_parse_ip_list_get_cursor(&buf_to_parse, &single); +++ if (!cursor) +++ break; +++ +++ if (single == false && prev_range == true) { +++ pr_info("NFS: mount option type: %d fail. Multiple Range.[%s]\n", +++ type, __func__); +++ +++ ret = -EINVAL; +++ goto out; +++ } +++ +++ if (prev_range == false) { +++ ret = nfs_multipath_parse_ip_list_inter(ip_list_tmp, +++ net_ns, cursor, type); +++ if (ret) +++ goto out; +++ if (single == false) +++ prev_range = true; +++ } else { +++ ret = nfs_multipath_parse_ip_range(net_ns, cursor, +++ ip_list_tmp, type); +++ if (ret != 0) +++ goto out; +++ prev_range = false; +++ } +++ } +++ +++out: +++ if (ret) +++ memset(ip_list_tmp, 0, sizeof(struct nfs_ip_list)); +++ +++ return ret; +++} +++ +++int nfs_multipath_parse_dns_list(char *buffer, struct net *net_ns, +++ struct multipath_mount_options *options) +++{ +++ struct NFS_ROUTE_DNS_INFO_S *dns_name_list_tmp = NULL; +++ char *cursor = NULL; +++ char *bufToParse; +++ +++ if (!nfs_multipath_parse_param_check(REMOTEDNSNAME, options)) +++ return -ENOTSUPP; +++ +++ pr_info("[MULTIPATH:%s] buffer %s\n", __func__, buffer); +++ // freed in nfs_free_parsed_mount_data +++ dns_name_list_tmp = kmalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), +++ GFP_KERNEL); +++ if (!dns_name_list_tmp) +++ return -ENOMEM; +++ +++ dns_name_list_tmp->dnsNameCount = 0; +++ bufToParse = buffer; +++ while (bufToParse) { +++ if (dns_name_list_tmp->dnsNameCount >= MAX_DNS_SUPPORTED) { +++ pr_err("%s: dnsname for %s reached %d,more than supported limit %d\n", +++ __func__, cursor, +++ dns_name_list_tmp->dnsNameCount, +++ MAX_DNS_SUPPORTED); +++ dns_name_list_tmp->dnsNameCount = 0; +++ return -ENOSPC; +++ } +++ cursor = strsep(&bufToParse, "~"); +++ if (!cursor) +++ break; +++ +++ strcpy(dns_name_list_tmp->routeRemoteDnsList +++ [dns_name_list_tmp->dnsNameCount].dnsname, +++ cursor); +++ dns_name_list_tmp->dnsNameCount++; +++ } +++ if (dns_name_list_tmp->dnsNameCount == 0) +++ return -EINVAL; +++ options->pRemoteDnsInfo = dns_name_list_tmp; +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check_ipv4_valid(struct sockaddr_in *addr) +++{ +++ if (addr->sin_addr.s_addr == 0 || addr->sin_addr.s_addr == 0xffffffff) +++ return -EINVAL; +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check_ipv6_valid(struct sockaddr_in6 *addr) +++{ +++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0 && +++ addr->sin6_addr.in6_u.u6_addr32[1] == 0 && +++ addr->sin6_addr.in6_u.u6_addr32[2] == 0 && +++ addr->sin6_addr.in6_u.u6_addr32[3] == 0) +++ return -EINVAL; +++ +++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0xffffffff && +++ addr->sin6_addr.in6_u.u6_addr32[1] == 0xffffffff && +++ addr->sin6_addr.in6_u.u6_addr32[2] == 0xffffffff && +++ addr->sin6_addr.in6_u.u6_addr32[3] == 0xffffffff) +++ return -EINVAL; +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check_ip_valid(struct sockaddr_storage *address) +++{ +++ int rc = 0; +++ +++ if (address->ss_family == AF_INET) +++ rc = nfs_multipath_parse_options_check_ipv4_valid( +++ (struct sockaddr_in *)address); +++ else if (address->ss_family == AF_INET6) +++ rc = nfs_multipath_parse_options_check_ipv6_valid( +++ (struct sockaddr_in6 *)address); +++ else +++ rc = -EINVAL; +++ +++ return rc; +++} +++ +++int nfs_multipath_parse_options_check_valid( +++ struct multipath_mount_options *options) +++{ +++ int rc; +++ int i; +++ +++ if (options == NULL) +++ return 0; +++ +++ for (i = 0; i < options->local_ip_list->count; i++) { +++ rc = nfs_multipath_parse_options_check_ip_valid( +++ &options->local_ip_list->address[i]); +++ if (rc != 0) +++ return rc; +++ } +++ +++ for (i = 0; i < options->remote_ip_list->count; i++) { +++ rc = nfs_multipath_parse_options_check_ip_valid( +++ &options->remote_ip_list->address[i]); +++ if (rc != 0) +++ return rc; +++ } +++ +++ return 0; +++} +++int nfs_multipath_parse_options_check_duplicate( +++ struct multipath_mount_options *options) +++{ +++ int i; +++ int j; +++ +++ if (options == NULL || +++ options->local_ip_list->count == 0 || +++ options->remote_ip_list->count == 0) +++ +++ return 0; +++ +++ for (i = 0; i < options->local_ip_list->count; i++) { +++ for (j = 0; j < options->remote_ip_list->count; j++) { +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &options->local_ip_list->address[i], +++ (const struct sockaddr *) +++ &options->remote_ip_list->address[j])) +++ return -ENOTSUPP; +++ } +++ } +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check(struct multipath_mount_options *options) +++{ +++ int rc = 0; +++ +++ rc = nfs_multipath_parse_options_check_valid(options); +++ +++ if (rc != 0) { +++ pr_err("has invaild ip.\n"); +++ return rc; +++ } +++ +++ rc = nfs_multipath_parse_options_check_duplicate(options); +++ if (rc != 0) +++ return rc; +++ return rc; +++} +++ +++int nfs_multipath_alloc_options(void **enfs_option) +++{ +++ struct multipath_mount_options *options = NULL; +++ +++ options = kzalloc(sizeof(struct multipath_mount_options), GFP_KERNEL); +++ +++ if (options == NULL) +++ return -ENOMEM; +++ +++ options->local_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ if (options->local_ip_list == NULL) { +++ kfree(options); +++ return -ENOMEM; +++ } +++ +++ options->remote_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ if (options->remote_ip_list == NULL) { +++ kfree(options->local_ip_list); +++ kfree(options); +++ return -ENOMEM; +++ } +++ +++ options->pRemoteDnsInfo = kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), +++ GFP_KERNEL); +++ if (options->pRemoteDnsInfo == NULL) { +++ kfree(options->remote_ip_list); +++ kfree(options->local_ip_list); +++ kfree(options); +++ return -ENOMEM; +++ } +++ +++ *enfs_option = options; +++ return 0; +++} +++ +++int nfs_multipath_parse_options(enum nfsmultipathoptions type, +++ char *str, void **enfs_option, struct net *net_ns) +++{ +++ int rc; +++ struct multipath_mount_options *options = NULL; +++ +++ if ((str == NULL) || (enfs_option == NULL) || (net_ns == NULL)) +++ return -EINVAL; +++ +++ if (*enfs_option == NULL) { +++ rc = nfs_multipath_alloc_options(enfs_option); +++ if (rc != 0) { +++ enfs_log_error( +++ "alloc enfs_options failed! errno:%d\n", rc); +++ return rc; +++ } +++ } +++ +++ options = (struct multipath_mount_options *)*enfs_option; +++ +++ if (type == LOCALADDR || type == REMOUNTLOCALADDR || +++ type == REMOTEADDR || type == REMOUNTREMOTEADDR) { +++ rc = nfs_multipath_parse_ip_list(str, net_ns, options, type); +++ } else if (type == REMOTEDNSNAME) { +++ /* alloc and release need to modify */ +++ rc = nfs_multipath_parse_dns_list(str, net_ns, options); +++ } else { +++ rc = -EOPNOTSUPP; +++ } +++ +++ // after parsing cmd, need checking local and remote +++ // IP is same. if not means illegal cmd +++ if (rc == 0) +++ rc = nfs_multipath_parse_options_check_duplicate(options); +++ +++ if (rc == 0) +++ rc = nfs_multipath_parse_options_check(options); +++ +++ return rc; +++} +++ +++void nfs_multipath_free_options(void **enfs_option) +++{ +++ struct multipath_mount_options *options; +++ +++ if (enfs_option == NULL || *enfs_option == NULL) +++ return; +++ +++ options = (struct multipath_mount_options *)*enfs_option; +++ +++ if (options->remote_ip_list != NULL) { +++ kfree(options->remote_ip_list); +++ options->remote_ip_list = NULL; +++ } +++ +++ if (options->local_ip_list != NULL) { +++ kfree(options->local_ip_list); +++ options->local_ip_list = NULL; +++ } +++ +++ if (options->pRemoteDnsInfo != NULL) { +++ kfree(options->pRemoteDnsInfo); +++ options->pRemoteDnsInfo = NULL; +++ } +++ +++ kfree(options); +++ *enfs_option = NULL; +++} ++diff --git a/fs/nfs/enfs/enfs_multipath_parse.h b/fs/nfs/enfs/enfs_multipath_parse.h ++new file mode 100644 ++index 000000000000..6f3e8703e3e2 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_parse.h ++@@ -0,0 +1,22 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _ENFS_MULTIPATH_PARSE_H_ +++#define _ENFS_MULTIPATH_PARSE_H_ +++ +++#include "enfs.h" +++ +++struct multipath_mount_options { +++ struct nfs_ip_list *remote_ip_list; +++ struct nfs_ip_list *local_ip_list; +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; +++}; +++ +++int nfs_multipath_parse_options(enum nfsmultipathoptions type, +++ char *str, void **enfs_option, struct net *net_ns); +++void nfs_multipath_free_options(void **enfs_option); +++ +++#endif +diff --git a/0004-add_enfs_module_for_sunrpc_multipatch.patch b/0004-add_enfs_module_for_sunrpc_multipatch.patch +new file mode 100644 +index 0000000..2c0fcc7 +--- /dev/null ++++ b/0004-add_enfs_module_for_sunrpc_multipatch.patch +@@ -0,0 +1,1581 @@ ++diff --git a/fs/nfs/enfs/enfs_multipath.h b/fs/nfs/enfs/enfs_multipath.h ++new file mode 100644 ++index 000000000000..e064c2929ced ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath.h ++@@ -0,0 +1,24 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: enfs multipath +++ * Author: +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef ENFS_MULTIPATH_H +++#define ENFS_MULTIPATH_H +++#include <linux/sunrpc/clnt.h> +++ +++#define MAX_XPRT_NUM_PER_CLIENT 32 +++ +++int enfs_multipath_init(void); +++void enfs_multipath_exit(void); +++void enfs_xprt_ippair_create(struct xprt_create *xprtargs, +++ struct rpc_clnt *clnt, void *data); +++int enfs_config_xprt_create_args(struct xprt_create *xprtargs, +++ struct rpc_create_args *args, +++ char *servername, size_t length); +++void print_enfs_multipath_addr(struct sockaddr *local, struct sockaddr *remote); +++ +++#endif // ENFS_MULTIPATH_H ++diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c ++new file mode 100644 ++index 000000000000..63c02898a42c ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.c ++@@ -0,0 +1,340 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/proc_fs.h> +++#include <linux/seq_file.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/addr.h> +++#include "enfs_multipath_client.h" +++#include "enfs_multipath_parse.h" +++ +++int +++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, +++ const struct nfs_client_initdata *client_init_data) +++{ +++ struct multipath_mount_options *mount_options = +++ (struct multipath_mount_options *)client_init_data->enfs_option; +++ +++ if (mount_options->local_ip_list) { +++ client_info->local_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->local_ip_list) +++ return -ENOMEM; +++ +++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->remote_ip_list) { +++ +++ client_info->remote_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->remote_ip_list) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->remote_ip_list, +++ mount_options->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->pRemoteDnsInfo) { +++ client_info->pRemoteDnsInfo = +++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); +++ +++ if (!client_info->pRemoteDnsInfo) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ kfree(client_info->remote_ip_list); +++ client_info->remote_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->pRemoteDnsInfo, +++ mount_options->pRemoteDnsInfo, +++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); +++ } +++ return 0; +++} +++ +++void nfs_multipath_client_info_free_work(struct work_struct *work) +++{ +++ +++ struct multipath_client_info *clp_info; +++ +++ if (work == NULL) +++ return; +++ +++ clp_info = container_of(work, struct multipath_client_info, work); +++ +++ if (clp_info->local_ip_list != NULL) { +++ kfree(clp_info->local_ip_list); +++ clp_info->local_ip_list = NULL; +++ } +++ if (clp_info->remote_ip_list != NULL) { +++ kfree(clp_info->remote_ip_list); +++ clp_info->remote_ip_list = NULL; +++ } +++ kfree(clp_info); +++} +++ +++void nfs_multipath_client_info_free(void *data) +++{ +++ struct multipath_client_info *clp_info = +++ (struct multipath_client_info *)data; +++ +++ if (clp_info == NULL) +++ return; +++ pr_info("free client info %p.\n", clp_info); +++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); +++ schedule_work(&clp_info->work); +++} +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init) +++{ +++ int rc; +++ struct multipath_client_info *info; +++ struct multipath_client_info **enfs_info; +++ /* no multi path info, no need do multipath init */ +++ if (cl_init->enfs_option == NULL) +++ return 0; +++ enfs_info = (struct multipath_client_info **)data; +++ if (enfs_info == NULL) +++ return -EINVAL; +++ +++ if (*enfs_info == NULL) +++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), +++ GFP_KERNEL); +++ +++ if (*enfs_info == NULL) +++ return -ENOMEM; +++ +++ info = (struct multipath_client_info *)*enfs_info; +++ pr_info("init client info %p.\n", info); +++ rc = nfs_multipath_client_mount_info_init(info, cl_init); +++ if (rc) { +++ nfs_multipath_client_info_free((void *)info); +++ return rc; +++ } +++ return rc; +++} +++ +++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, +++ const struct nfs_ip_list *ip_list_dst) +++{ +++ int i; +++ int j; +++ bool is_find; +++ /* if both are equal or NULL, then return true. */ +++ if (ip_list_src == ip_list_dst) +++ return true; +++ +++ if ((ip_list_src == NULL || ip_list_dst == NULL)) +++ return false; +++ +++ if (ip_list_src->count != ip_list_dst->count) +++ return false; +++ +++ for (i = 0; i < ip_list_src->count; i++) { +++ is_find = false; +++ for (j = 0; j < ip_list_src->count; j++) { +++ if (rpc_cmp_addr_port( +++ (const struct sockaddr *) +++ &ip_list_src->address[i], +++ (const struct sockaddr *) +++ &ip_list_dst->address[j]) +++ ) { +++ is_find = true; +++ break; +++ } +++ } +++ if (is_find == false) +++ return false; +++ } +++ return true; +++} +++ +++int +++nfs_multipath_dns_list_info_match( +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) +++{ +++ int i; +++ +++ /* if both are equal or NULL, then return true. */ +++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) +++ return true; +++ +++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) +++ return false; +++ +++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) +++ return false; +++ +++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { +++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, +++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) +++ return false; +++ } +++ return true; +++} +++ +++int nfs_multipath_client_info_match(void *src, void *dst) +++{ +++ int ret = true; +++ +++ struct multipath_client_info *src_info; +++ struct multipath_mount_options *dst_info; +++ +++ src_info = (struct multipath_client_info *)src; +++ dst_info = (struct multipath_mount_options *)dst; +++ pr_info("try match client .\n"); +++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, +++ dst_info->local_ip_list); +++ if (ret == false) { +++ pr_err("local_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, +++ dst_info->remote_ip_list); +++ if (ret == false) { +++ pr_err("remote_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, +++ dst_info->pRemoteDnsInfo); +++ if (ret == false) { +++ pr_err("dns not match.\n"); +++ return ret; +++ } +++ pr_info("try match client ret %d.\n", ret); +++ return ret; +++} +++ +++void nfs_multipath_print_ip_info(struct seq_file *mount_option, +++ struct nfs_ip_list *ip_list, +++ const char *type) +++{ +++ char buf[IP_ADDRESS_LEN_MAX + 1]; +++ int len = 0; +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < ip_list->count; i++) { +++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], +++ buf, IP_ADDRESS_LEN_MAX); +++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) +++ buf[len] = '\0'; +++ +++ if (i == 0) +++ seq_printf(mount_option, "%s", buf); +++ else +++ seq_printf(mount_option, "~%s", buf); +++ dfprintk(MOUNT, +++ "NFS: show nfs mount option type:%s %s [%s]\n", +++ type, buf, __func__); +++ } +++} +++ +++void nfs_multipath_print_dns_info(struct seq_file *mount_option, +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, +++ const char *type) +++{ +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { +++ if (i == 0) +++ seq_printf(mount_option, +++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) +++ seq_printf(mount_option, ",%s]", +++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else +++ seq_printf(mount_option, +++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ } +++} +++ +++ +++static void multipath_print_sockaddr(struct seq_file *seq, +++ struct sockaddr *addr) +++{ +++ switch (addr->sa_family) { +++ case AF_INET: { +++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; +++ +++ seq_printf(seq, "%pI4", &sin->sin_addr); +++ return; +++ } +++ case AF_INET6: { +++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; +++ +++ seq_printf(seq, "%pI6", &sin6->sin6_addr); +++ return; +++ } +++ default: +++ break; +++ } +++ pr_err("unsupport family:%d\n", addr->sa_family); +++} +++ +++static void multipath_print_enfs_info(struct seq_file *seq, +++ struct nfs_server *server) +++{ +++ struct sockaddr_storage peeraddr; +++ struct rpc_clnt *next = server->client; +++ +++ rpc_peeraddr(server->client, +++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); +++ seq_puts(seq, ",enfs_info="); +++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); +++ +++ while (next->cl_parent) { +++ if (next == next->cl_parent) +++ break; +++ next = next->cl_parent; +++ } +++ seq_printf(seq, "_%u", next->cl_clid); +++} +++ +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) +++{ +++ struct nfs_server *server = data; +++ struct multipath_client_info *client_info = +++ server->nfs_client->cl_multipath_data; +++ +++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); +++ if ((client_info->remote_ip_list) && +++ (client_info->remote_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->remote_ip_list, +++ "remoteaddrs"); +++ +++ if ((client_info->local_ip_list) && +++ (client_info->local_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->local_ip_list, +++ "localaddrs"); +++ +++ if ((client_info->pRemoteDnsInfo) && +++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) +++ nfs_multipath_print_dns_info(mount_option, +++ client_info->pRemoteDnsInfo, +++ "remotednsname"); +++ +++ multipath_print_enfs_info(mount_option, server); +++} ++diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h ++new file mode 100644 ++index 000000000000..208f7260690d ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.h ++@@ -0,0 +1,26 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _ENFS_MULTIPATH_CLIENT_H_ +++#define _ENFS_MULTIPATH_CLIENT_H_ +++ +++#include "enfs.h" +++ +++struct multipath_client_info { +++ struct work_struct work; +++ struct nfs_ip_list *remote_ip_list; +++ struct nfs_ip_list *local_ip_list; +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; +++ s64 client_id; +++}; +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init); +++void nfs_multipath_client_info_free(void *data); +++int nfs_multipath_client_info_match(void *src, void *dst); +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_path.c b/fs/nfs/enfs/enfs_path.c ++new file mode 100644 ++index 000000000000..7355f8c2f672 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_path.c ++@@ -0,0 +1,47 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++ +++#include <linux/sunrpc/metrics.h> +++#include <linux/sunrpc/xprt.h> +++ +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_path.h" +++ +++// only create ctx in this function +++// alloc iostat memory in create_clnt +++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx; +++ +++ if (!xprt) { +++ enfs_log_error("invalid xprt pointer.\n"); +++ return -EINVAL; +++ } +++ +++ ctx = kzalloc(sizeof(struct enfs_xprt_context), GFP_KERNEL); +++ if (!ctx) { +++ enfs_log_error("add xprt test failed.\n"); +++ return -ENOMEM; +++ } +++ +++ xprt->multipath_context = (void *)ctx; +++ return 0; +++} +++ +++// free multi_context and iostat memory +++void enfs_free_xprt_ctx(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = xprt->multipath_context; +++ +++ if (ctx) { +++ if (ctx->stats) { +++ rpc_free_iostats(ctx->stats); +++ ctx->stats = NULL; +++ } +++ kfree(xprt->multipath_context); +++ xprt->multipath_context = NULL; +++ } +++} ++diff --git a/fs/nfs/enfs/enfs_path.h b/fs/nfs/enfs/enfs_path.h ++new file mode 100644 ++index 000000000000..97b1ef3730b8 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_path.h ++@@ -0,0 +1,12 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++ +++#ifndef ENFS_PATH_H +++#define ENFS_PATH_H +++ +++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt); +++void enfs_free_xprt_ctx(struct rpc_xprt *xprt); +++ +++#endif // ENFS_PATH_H ++diff --git a/fs/nfs/enfs/enfs_proc.c b/fs/nfs/enfs/enfs_proc.c ++new file mode 100644 ++index 000000000000..53fa1a07642f ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_proc.c ++@@ -0,0 +1,545 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#include <linux/module.h> +++#include <linux/proc_fs.h> +++#include <linux/seq_file.h> +++#include <linux/spinlock.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/metrics.h> +++#include <linux/sunrpc/xprtsock.h> +++#include <net/netns/generic.h> +++ +++#include "../../../net/sunrpc/netns.h" +++ +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_proc.h" +++#include "enfs_multipath.h" +++#include "pm_state.h" +++ +++#define ENFS_PROC_DIR "enfs" +++#define ENFS_PROC_PATH_STATUS_LEN 256 +++ +++static struct proc_dir_entry *enfs_proc_parent; +++ +++void +++enfs_iterate_each_rpc_clnt(int (*fn)(struct rpc_clnt *clnt, void *data), +++ void *data) +++{ +++ struct net *net; +++ struct sunrpc_net *sn; +++ struct rpc_clnt *clnt; +++ +++ rcu_read_lock(); +++ for_each_net_rcu(net) { +++ sn = net_generic(net, sunrpc_net_id); +++ if (sn == NULL) +++ continue; +++ spin_lock(&sn->rpc_client_lock); +++ list_for_each_entry(clnt, &sn->all_clients, cl_clients) { +++ fn(clnt, data); +++ } +++ spin_unlock(&sn->rpc_client_lock); +++ } +++ rcu_read_unlock(); +++} +++ +++struct proc_dir_entry *enfs_get_proc_parent(void) +++{ +++ return enfs_proc_parent; +++} +++ +++static int sockaddr_ip_to_str(struct sockaddr *addr, char *buf, int len) +++{ +++ switch (addr->sa_family) { +++ case AF_INET: { +++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; +++ +++ snprintf(buf, len, "%pI4", &sin->sin_addr); +++ return 0; +++ } +++ case AF_INET6: { +++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; +++ +++ snprintf(buf, len, "%pI6", &sin6->sin6_addr); +++ return 0; +++ } +++ default: +++ break; +++ } +++ return 1; +++} +++ +++static bool should_print(const char *name) +++{ +++ int i; +++ static const char * const proc_names[] = { +++ "READ", +++ "WRITE", +++ }; +++ +++ if (name == NULL) +++ return false; +++ +++ for (i = 0; i < ARRAY_SIZE(proc_names); i++) { +++ if (strcmp(name, proc_names[i]) == 0) +++ return true; +++ } +++ return false; +++} +++ +++struct enfs_xprt_iter { +++ unsigned int id; +++ struct seq_file *seq; +++ unsigned int max_addrs_length; +++}; +++ +++static int debug_show_xprt(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ +++ if (xprt->multipath_context) +++ ctx = xprt->multipath_context; +++ +++ pr_info(" xprt:%p ctx:%p main:%d queue_len:%lu.\n", xprt, +++ xprt->multipath_context, +++ ctx ? ctx->main : false, +++ atomic_long_read(&xprt->queuelen)); +++ return 0; +++} +++ +++static int debug_show_clnt(struct rpc_clnt *clnt, void *data) +++{ +++ pr_info(" clnt %d addr:%p enfs:%d\n", +++ clnt->cl_clid, clnt, +++ clnt->cl_enfs); +++ rpc_clnt_iterate_for_each_xprt(clnt, debug_show_xprt, NULL); +++ return 0; +++} +++ +++static void debug_print_all_xprt(void) +++{ +++ enfs_iterate_each_rpc_clnt(debug_show_clnt, NULL); +++} +++ +++static +++void enfs_proc_format_xprt_addr_display(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ char *local_name_buf, +++ int local_name_buf_len, +++ char *remote_name_buf, +++ int remote_name_buf_len) +++{ +++ int err; +++ struct sockaddr_storage srcaddr; +++ struct enfs_xprt_context *ctx; +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ sockaddr_ip_to_str((struct sockaddr *)&xprt->addr, +++ remote_name_buf, remote_name_buf_len); +++ +++ // get local address depend one main or not +++ if (enfs_is_main_xprt(xprt)) { +++ err = rpc_localaddr(clnt, (struct sockaddr *)&srcaddr, +++ sizeof(srcaddr)); +++ if (err != 0) +++ (void)snprintf(local_name_buf, +++ local_name_buf_len, "Unknown"); +++ else +++ sockaddr_ip_to_str((struct sockaddr *)&srcaddr, +++ local_name_buf, +++ local_name_buf_len); +++ } else { +++ sockaddr_ip_to_str((struct sockaddr *)&ctx->srcaddr, +++ local_name_buf, +++ local_name_buf_len); +++ } +++} +++ +++static int enfs_show_xprt_stats(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ unsigned int op; +++ unsigned int maxproc = clnt->cl_maxproc; +++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; +++ struct enfs_xprt_context *ctx; +++ char local_name[INET6_ADDRSTRLEN]; +++ char remote_name[INET6_ADDRSTRLEN]; +++ +++ if (!xprt->multipath_context) +++ return 0; +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ enfs_proc_format_xprt_addr_display(clnt, xprt, local_name, +++ sizeof(local_name), +++ remote_name, sizeof(remote_name)); +++ +++ seq_printf(iter->seq, "%-6u%-*s%-*s", iter->id, +++ iter->max_addrs_length + 4, +++ local_name, +++ iter->max_addrs_length + 4, +++ remote_name); +++ +++ iter->id++; +++ +++ for (op = 0; op < maxproc; op++) { +++ if (!should_print(clnt->cl_procinfo[op].p_name)) +++ continue; +++ +++ seq_printf(iter->seq, "%-22lu%-22Lu%-22Lu", +++ ctx->stats[op].om_ops, +++ ctx->stats[op].om_ops == 0 ? 0 : +++ ktime_to_ms(ctx->stats[op].om_rtt) / +++ ctx->stats[op].om_ops, +++ ctx->stats[op].om_ops == 0 ? 0 : +++ ktime_to_ms(ctx->stats[op].om_execute) / +++ ctx->stats[op].om_ops); +++ } +++ seq_puts(iter->seq, "\n"); +++ return 0; +++} +++ +++static int rpc_proc_show_path_status(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; +++ struct enfs_xprt_context *ctx = NULL; +++ char local_name[INET6_ADDRSTRLEN] = {0}; +++ char remote_name[INET6_ADDRSTRLEN] = {0}; +++ char multiapth_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; +++ char xprt_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; +++ +++ if (!xprt->multipath_context) { +++ enfs_log_debug("multipath_context is null.\n"); +++ return 0; +++ } +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ enfs_proc_format_xprt_addr_display(clnt, xprt, +++ local_name, +++ sizeof(local_name), +++ remote_name, sizeof(remote_name)); +++ +++ pm_get_path_state_desc(xprt, +++ multiapth_status, +++ ENFS_PROC_PATH_STATUS_LEN); +++ +++ pm_get_xprt_state_desc(xprt, +++ xprt_status, +++ ENFS_PROC_PATH_STATUS_LEN); +++ +++ seq_printf(iter->seq, "%-6u%-*s%-*s%-12s%-12s\n", +++ iter->id, iter->max_addrs_length + 4, +++ local_name, iter->max_addrs_length + 4, +++ remote_name, multiapth_status, +++ xprt_status); +++ iter->id++; +++ return 0; +++} +++ +++static int enfs_get_max_addrs_length(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; +++ char local_name[INET6_ADDRSTRLEN]; +++ char remote_name[INET6_ADDRSTRLEN]; +++ +++ enfs_proc_format_xprt_addr_display(clnt, xprt, +++ local_name, sizeof(local_name), +++ remote_name, sizeof(remote_name)); +++ +++ if (iter->max_addrs_length < strlen(local_name)) +++ iter->max_addrs_length = strlen(local_name); +++ +++ if (iter->max_addrs_length < strlen(remote_name)) +++ iter->max_addrs_length = strlen(remote_name); +++ +++ return 0; +++} +++ +++static int rpc_proc_clnt_showpath(struct seq_file *seq, void *v) +++{ +++ struct rpc_clnt *clnt = seq->private; +++ struct enfs_xprt_iter iter; +++ +++ iter.seq = seq; +++ iter.id = 0; +++ iter.max_addrs_length = 0; +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ enfs_get_max_addrs_length, +++ (void *)&iter); +++ +++ seq_printf(seq, "%-6s%-*s%-*s%-12s%-12s\n", "id", +++ iter.max_addrs_length + 4, +++ "local_addr", +++ iter.max_addrs_length + 4, +++ "remote_addr", +++ "path_state", +++ "xprt_state"); +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ rpc_proc_show_path_status, +++ (void *)&iter); +++ return 0; +++} +++ +++static int enfs_rpc_proc_show(struct seq_file *seq, void *v) +++{ +++ struct rpc_clnt *clnt = seq->private; +++ struct enfs_xprt_iter iter; +++ +++ iter.seq = seq; +++ iter.id = 0; +++ iter.max_addrs_length = 0; +++ +++ debug_print_all_xprt(); +++ pr_info("enfs proc clnt:%p\n", clnt); +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ enfs_get_max_addrs_length, +++ (void *)&iter); +++ +++ seq_printf(seq, "%-6s%-*s%-*s%-22s%-22s%-22s%-22s%-22s%-22s\n", "id", +++ iter.max_addrs_length + 4, "local_addr", +++ iter.max_addrs_length + 4, +++ "remote_addr", "r_count", +++ "r_rtt", "r_exec", "w_count", "w_rtt", "w_exec"); +++ +++ // rpc_clnt_show_stats(seq, clnt); +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ enfs_show_xprt_stats, +++ (void *)&iter); +++ return 0; +++} +++ +++static int rpc_proc_open(struct inode *inode, struct file *file) +++{ +++ struct rpc_clnt *clnt = PDE_DATA(inode); +++ +++ pr_info("%s %p\n", __func__, clnt); +++ return single_open(file, enfs_rpc_proc_show, clnt); +++} +++ +++static int enfs_reset_xprt_stats(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ unsigned int op; +++ struct enfs_xprt_context *ctx; +++ unsigned int maxproc = clnt->cl_maxproc; +++ struct rpc_iostats stats = {0}; +++ +++ if (!xprt->multipath_context) +++ return 0; +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ for (op = 0; op < maxproc; op++) { +++ spin_lock(&ctx->stats[op].om_lock); +++ ctx->stats[op] = stats; +++ spin_unlock(&ctx->stats[op].om_lock); +++ } +++ return 0; +++} +++ +++static void trim_newline_ch(char *str, int len) +++{ +++ int i; +++ +++ for (i = 0; str[i] != '\0' && i < len; i++) { +++ if (str[i] == '\n') +++ str[i] = '\0'; +++ } +++} +++ +++static ssize_t enfs_proc_write(struct file *file, +++ const char __user *user_buf, +++ size_t len, +++ loff_t *offset) +++{ +++ char buffer[128]; +++ struct rpc_clnt *clnt = +++ ((struct seq_file *)file->private_data)->private; +++ +++ if (len >= sizeof(buffer)) +++ return -E2BIG; +++ +++ if (copy_from_user(buffer, user_buf, len) != 0) +++ return -EFAULT; +++ +++ buffer[len] = '\0'; +++ trim_newline_ch(buffer, len); +++ if (strcmp(buffer, "reset") != 0) +++ return -EINVAL; +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, enfs_reset_xprt_stats, NULL); +++ return len; +++} +++ +++static int rpc_proc_show_path(struct inode *inode, struct file *file) +++{ +++ struct rpc_clnt *clnt = PDE_DATA(inode); +++ +++ return single_open(file, rpc_proc_clnt_showpath, clnt); +++} +++ +++static const struct file_operations rpc_proc_fops = { +++ .owner = THIS_MODULE, +++ .open = rpc_proc_open, +++ .read = seq_read, +++ .llseek = seq_lseek, +++ .release = single_release, +++ .write = enfs_proc_write, +++}; +++ +++static const struct file_operations rpc_show_path_fops = { +++ .owner = THIS_MODULE, +++ .open = rpc_proc_show_path, +++ .read = seq_read, +++ .llseek = seq_lseek, +++ .release = single_release, +++}; +++ +++static int clnt_proc_name(struct rpc_clnt *clnt, char *buf, int len) +++{ +++ int ret; +++ +++ ret = snprintf(buf, len, "%s_%u", +++ rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR), +++ clnt->cl_clid); +++ if (ret > len) +++ return -E2BIG; +++ return 0; +++} +++ +++static int enfs_proc_create_file(struct rpc_clnt *clnt) +++{ +++ int err; +++ char buf[128]; +++ +++ struct proc_dir_entry *clnt_entry; +++ struct proc_dir_entry *stat_entry; +++ +++ err = clnt_proc_name(clnt, buf, sizeof(buf)); +++ if (err) +++ return err; +++ +++ clnt_entry = proc_mkdir(buf, enfs_proc_parent); +++ if (clnt_entry == NULL) +++ return -EINVAL; +++ +++ stat_entry = proc_create_data("stat", +++ 0, clnt_entry, +++ &rpc_proc_fops, clnt); +++ +++ if (stat_entry == NULL) +++ return -EINVAL; +++ +++ stat_entry = proc_create_data("path", +++ 0, clnt_entry, +++ &rpc_show_path_fops, clnt); +++ +++ if (stat_entry == NULL) +++ return -EINVAL; +++ +++ return 0; +++} +++ +++void enfs_count_iostat(struct rpc_task *task) +++{ +++ struct enfs_xprt_context *ctx = task->tk_xprt->multipath_context; +++ +++ if (!ctx || !ctx->stats) +++ return; +++ rpc_count_iostats(task, ctx->stats); +++} +++ +++static void enfs_proc_delete_file(struct rpc_clnt *clnt) +++{ +++ int err; +++ char buf[128]; +++ +++ err = clnt_proc_name(clnt, buf, sizeof(buf)); +++ if (err) { +++ pr_err("gen clnt name failed.\n"); +++ return; +++ } +++ remove_proc_subtree(buf, enfs_proc_parent); +++} +++ +++// create proc file "/porc/enfs/[mount_ip]_[id]/stat" +++int enfs_proc_create_clnt(struct rpc_clnt *clnt) +++{ +++ int err; +++ +++ err = enfs_proc_create_file(clnt); +++ if (err) { +++ pr_err("create client %d\n", err); +++ return err; +++ } +++ +++ return 0; +++} +++ +++void enfs_proc_delete_clnt(struct rpc_clnt *clnt) +++{ +++ if (clnt->cl_enfs) +++ enfs_proc_delete_file(clnt); +++} +++ +++static int enfs_proc_create_parent(void) +++{ +++ enfs_proc_parent = proc_mkdir(ENFS_PROC_DIR, NULL); +++ +++ if (enfs_proc_parent == NULL) { +++ pr_err("Enfs create proc dir err\n"); +++ return -ENOMEM; +++ } +++ return 0; +++} +++ +++static void enfs_proc_delete_parent(void) +++{ +++ remove_proc_entry(ENFS_PROC_DIR, NULL); +++} +++ +++static int enfs_proc_init_create_clnt(struct rpc_clnt *clnt, void *data) +++{ +++ if (clnt->cl_enfs) +++ enfs_proc_create_file(clnt); +++ return 0; +++} +++ +++static int enfs_proc_destroy_clnt(struct rpc_clnt *clnt, void *data) +++{ +++ if (clnt->cl_enfs) +++ enfs_proc_delete_file(clnt); +++ return 0; +++} +++ +++int enfs_proc_init(void) +++{ +++ int err; +++ +++ err = enfs_proc_create_parent(); +++ if (err) +++ return err; +++ +++ enfs_iterate_each_rpc_clnt(enfs_proc_init_create_clnt, NULL); +++ return 0; +++} +++ +++void enfs_proc_exit(void) +++{ +++ enfs_iterate_each_rpc_clnt(enfs_proc_destroy_clnt, NULL); +++ enfs_proc_delete_parent(); +++} ++diff --git a/fs/nfs/enfs/enfs_proc.h b/fs/nfs/enfs/enfs_proc.h ++new file mode 100644 ++index 000000000000..321951031c2e ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_proc.h ++@@ -0,0 +1,21 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS PROC. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef ENFS_PROC_H +++#define ENFS_PROC_H +++ +++struct rpc_clnt; +++struct rpc_task; +++struct proc_dir_entry; +++ +++int enfs_proc_init(void); +++void enfs_proc_exit(void); +++struct proc_dir_entry *enfs_get_proc_parent(void); +++int enfs_proc_create_clnt(struct rpc_clnt *clnt); +++void enfs_proc_delete_clnt(struct rpc_clnt *clnt); +++void enfs_count_iostat(struct rpc_task *task); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_remount.c b/fs/nfs/enfs/enfs_remount.c ++new file mode 100644 ++index 000000000000..2c3fe125c735 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_remount.c ++@@ -0,0 +1,221 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: remount ip source file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++#include "enfs_remount.h" +++ +++#include <linux/string.h> +++#include <linux/in.h> +++#include <linux/in6.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/spinlock.h> +++#include <linux/sunrpc/addr.h> +++#include <linux/sunrpc/metrics.h> +++#include <linux/sunrpc/xprtmultipath.h> +++#include <linux/sunrpc/xprtsock.h> +++#include <linux/sunrpc/xprt.h> +++#include <linux/smp.h> +++#include <linux/delay.h> +++ +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_multipath.h" +++#include "enfs_multipath_parse.h" +++#include "enfs_path.h" +++#include "enfs_proc.h" +++#include "enfs_multipath_client.h" +++ +++static bool enfs_rpc_xprt_switch_need_delete_addr( +++ struct multipath_mount_options *enfs_option, +++ struct sockaddr *dstaddr, struct sockaddr *srcaddr) +++{ +++ int i; +++ bool find_same_ip = false; +++ int32_t local_total; +++ int32_t remote_total; +++ +++ local_total = enfs_option->local_ip_list->count; +++ remote_total = enfs_option->remote_ip_list->count; +++ if (local_total == 0 || remote_total == 0) { +++ pr_err("no ip list is present.\n"); +++ return false; +++ } +++ +++ for (i = 0; i < local_total; i++) { +++ find_same_ip = +++ rpc_cmp_addr((struct sockaddr *) +++ &enfs_option->local_ip_list->address[i], +++ srcaddr); +++ if (find_same_ip) +++ break; +++ } +++ +++ if (find_same_ip == false) +++ return true; +++ +++ find_same_ip = false; +++ for (i = 0; i < remote_total; i++) { +++ find_same_ip = +++ rpc_cmp_addr((struct sockaddr *) +++ &enfs_option->remote_ip_list->address[i], +++ dstaddr); +++ if (find_same_ip) +++ break; +++ } +++ +++ if (find_same_ip == false) +++ return true; +++ +++ return false; +++} +++ +++// Used in rcu_lock +++static bool enfs_delete_xprt_from_switch(struct rpc_xprt *xprt, +++ void *enfs_option, +++ struct rpc_xprt_switch *xps) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ struct multipath_mount_options *mopt = +++ (struct multipath_mount_options *)enfs_option; +++ +++ if (enfs_is_main_xprt(xprt)) +++ return true; +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (enfs_rpc_xprt_switch_need_delete_addr(mopt, +++ (struct sockaddr *)&xprt->addr, +++ (struct sockaddr *)&ctx->srcaddr)) { +++ +++ print_enfs_multipath_addr((struct sockaddr *)&ctx->srcaddr, +++ (struct sockaddr *)&xprt->addr); +++ rpc_xprt_switch_remove_xprt(xps, xprt); +++ return true; +++ } +++ +++ return false; +++} +++ +++void enfs_clnt_delete_obsolete_xprts(struct nfs_client *nfs_client, +++ void *enfs_option) +++{ +++ int xprt_count = 0; +++ struct rpc_xprt *pos = NULL; +++ struct rpc_xprt_switch *xps = NULL; +++ +++ rcu_read_lock(); +++ xps = xprt_switch_get( +++ rcu_dereference( +++ nfs_client->cl_rpcclient->cl_xpi.xpi_xpswitch)); +++ if (xps == NULL) { +++ rcu_read_unlock(); +++ xprt_switch_put(xps); +++ return; +++ } +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (xprt_count < MAX_XPRT_NUM_PER_CLIENT) { +++ if (enfs_delete_xprt_from_switch( +++ pos, enfs_option, xps) == false) +++ xprt_count++; +++ } else +++ rpc_xprt_switch_remove_xprt(xps, pos); +++ } +++ rcu_read_unlock(); +++ xprt_switch_put(xps); +++} +++ +++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) +++{ +++ int errno = 0; +++ char servername[48]; +++ struct multipath_mount_options *remount_lists = +++ (struct multipath_mount_options *)enfs_option; +++ struct multipath_client_info *client_info = +++ (struct multipath_client_info *)nfs_client->cl_multipath_data; +++ struct xprt_create xprtargs; +++ struct rpc_create_args args = { +++ .protocol = nfs_client->cl_proto, +++ .net = nfs_client->cl_net, +++ .addrsize = nfs_client->cl_addrlen, +++ .servername = nfs_client->cl_hostname, +++ }; +++ +++ memset(&xprtargs, 0, sizeof(struct xprt_create)); +++ +++ //mount is not use multipath +++ if (client_info == NULL || enfs_option == NULL) { +++ enfs_log_error( +++ "mount information or remount information is empty.\n"); +++ return -EINVAL; +++ } +++ +++ //remount : localaddrs and remoteaddrs are empty +++ if (remount_lists->local_ip_list->count == 0 && +++ remount_lists->remote_ip_list->count == 0) { +++ enfs_log_info("remount local_ip_list and remote_ip_list are NULL\n"); +++ return 0; +++ } +++ +++ errno = enfs_config_xprt_create_args(&xprtargs, +++ &args, servername, sizeof(servername)); +++ +++ if (errno) { +++ enfs_log_error("config_xprt_create failed! errno:%d\n", errno); +++ return errno; +++ } +++ +++ if (remount_lists->local_ip_list->count == 0) { +++ if (client_info->local_ip_list->count == 0) { +++ errno = rpc_localaddr(nfs_client->cl_rpcclient, +++ (struct sockaddr *) +++ &remount_lists->local_ip_list->address[0], +++ sizeof(struct sockaddr_storage)); +++ if (errno) { +++ enfs_log_error("get clnt srcaddr errno:%d\n", +++ errno); +++ return errno; +++ } +++ remount_lists->local_ip_list->count = 1; +++ } else +++ memcpy(remount_lists->local_ip_list, +++ client_info->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (remount_lists->remote_ip_list->count == 0) { +++ if (client_info->remote_ip_list->count == 0) { +++ errno = rpc_peeraddr(nfs_client->cl_rpcclient, +++ (struct sockaddr *) +++ &remount_lists->remote_ip_list->address[0], +++ sizeof(struct sockaddr_storage)); +++ if (errno == 0) { +++ enfs_log_error("get clnt dstaddr errno:%d\n", +++ errno); +++ return errno; +++ } +++ remount_lists->remote_ip_list->count = 1; +++ } else +++ memcpy(remount_lists->remote_ip_list, +++ client_info->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ enfs_log_info("Remount creating new links...\n"); +++ enfs_xprt_ippair_create(&xprtargs, +++ nfs_client->cl_rpcclient, +++ remount_lists); +++ +++ enfs_log_info("Remount deleting obsolete links...\n"); +++ enfs_clnt_delete_obsolete_xprts(nfs_client, remount_lists); +++ +++ memcpy(client_info->local_ip_list, +++ remount_lists->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ memcpy(client_info->remote_ip_list, +++ remount_lists->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ +++ return 0; +++} ++diff --git a/fs/nfs/enfs/enfs_remount.h b/fs/nfs/enfs/enfs_remount.h ++new file mode 100644 ++index 000000000000..a663ed257004 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_remount.h ++@@ -0,0 +1,15 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: remount ip header file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++#ifndef _ENFS_REMOUNT_ +++#define _ENFS_REMOUNT_ +++#include <linux/string.h> +++#include "enfs.h" +++ +++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_roundrobin.c b/fs/nfs/enfs/enfs_roundrobin.c ++new file mode 100644 ++index 000000000000..4e4eda784a3e ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_roundrobin.c ++@@ -0,0 +1,255 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#include <linux/spinlock.h> +++#include <linux/module.h> +++#include <linux/printk.h> +++#include <linux/kref.h> +++#include <linux/rculist.h> +++#include <linux/types.h> +++#include <linux/sunrpc/xprt.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/xprtmultipath.h> +++#include "enfs_roundrobin.h" +++ +++#include "enfs.h" +++#include "enfs_config.h" +++#include "pm_state.h" +++ +++typedef struct rpc_xprt *(*enfs_xprt_switch_find_xprt_t)( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur); +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin; +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular; +++ +++static bool enfs_xprt_is_active(struct rpc_xprt *xprt) +++{ +++ enum pm_path_state state; +++ +++ if (kref_read(&xprt->kref) <= 0) +++ return false; +++ +++ state = pm_get_path_state(xprt); +++ if (state == PM_STATE_NORMAL) +++ return true; +++ +++ return false; +++} +++ +++static struct rpc_xprt *enfs_lb_set_cursor_xprt( +++ struct rpc_xprt_switch *xps, struct rpc_xprt **cursor, +++ enfs_xprt_switch_find_xprt_t find_next) +++{ +++ struct rpc_xprt *pos; +++ struct rpc_xprt *old; +++ +++ old = smp_load_acquire(cursor); /* read latest cursor */ +++ pos = find_next(xps, old); +++ smp_store_release(cursor, pos); /* let cursor point to pos */ +++ return pos; +++} +++ +++static +++struct rpc_xprt *enfs_lb_find_next_entry_roundrobin( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *pos; +++ struct rpc_xprt *prev = NULL; +++ bool found = false; +++ struct rpc_xprt *min_queuelen_xprt = NULL; +++ unsigned long pos_xprt_queuelen; +++ unsigned long min_xprt_queuelen = 0; +++ +++ unsigned long xps_queuelen = atomic_long_read(&xps->xps_queuelen); +++ // delete origin xprt +++ unsigned int multipath_nactive = READ_ONCE(xps->xps_nactive) - 1; +++ +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (enfs_is_main_xprt(pos) || !enfs_xprt_is_active(pos)) { +++ prev = pos; +++ continue; +++ } +++ +++ pos_xprt_queuelen = atomic_long_read(&pos->queuelen); +++ if (min_queuelen_xprt == NULL || +++ pos_xprt_queuelen < min_xprt_queuelen) { +++ +++ min_queuelen_xprt = pos; +++ min_xprt_queuelen = pos_xprt_queuelen; +++ } +++ +++ if (cur == prev) +++ found = true; +++ +++ if (found && pos_xprt_queuelen * +++ multipath_nactive <= xps_queuelen) +++ return pos; +++ prev = pos; +++ }; +++ +++ return min_queuelen_xprt; +++} +++ +++struct rpc_xprt *enfs_lb_switch_find_first_active_xprt( +++ struct rpc_xprt_switch *xps) +++{ +++ struct rpc_xprt *pos; +++ +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (enfs_xprt_is_active(pos)) +++ return pos; +++ }; +++ return NULL; +++} +++ +++struct rpc_xprt *enfs_lb_switch_get_main_xprt(struct rpc_xprt_switch *xps) +++{ +++ return list_first_or_null_rcu(&xps->xps_xprt_list, +++ struct rpc_xprt, xprt_switch); +++} +++ +++static struct rpc_xprt *enfs_lb_switch_get_next_xprt_roundrobin( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *xprt; +++ +++ // disable multipath +++ if (enfs_get_config_multipath_state()) +++ return enfs_lb_switch_get_main_xprt(xps); +++ +++ xprt = enfs_lb_find_next_entry_roundrobin(xps, cur); +++ if (xprt != NULL) +++ return xprt; +++ +++ return enfs_lb_switch_get_main_xprt(xps); +++} +++ +++static +++struct rpc_xprt *enfs_lb_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi) +++{ +++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); +++ +++ if (xps == NULL) +++ return NULL; +++ +++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, +++ enfs_lb_switch_get_next_xprt_roundrobin); +++} +++ +++static +++struct rpc_xprt *enfs_lb_switch_find_singular_entry( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *pos; +++ bool found = false; +++ +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (cur == pos) +++ found = true; +++ +++ if (found && enfs_xprt_is_active(pos)) +++ return pos; +++ } +++ return NULL; +++} +++ +++struct rpc_xprt *enfs_lb_get_singular_xprt( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *xprt; +++ +++ if (xps == NULL) +++ return NULL; +++ +++ // disable multipath +++ if (enfs_get_config_multipath_state()) +++ return enfs_lb_switch_get_main_xprt(xps); +++ +++ if (cur == NULL || xps->xps_nxprts < 2) +++ return enfs_lb_switch_find_first_active_xprt(xps); +++ +++ xprt = enfs_lb_switch_find_singular_entry(xps, cur); +++ if (!xprt) +++ return enfs_lb_switch_get_main_xprt(xps); +++ +++ return xprt; +++} +++ +++static +++struct rpc_xprt *enfs_lb_iter_next_entry_sigular(struct rpc_xprt_iter *xpi) +++{ +++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); +++ +++ if (xps == NULL) +++ return NULL; +++ +++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, +++ enfs_lb_get_singular_xprt); +++} +++ +++static void enfs_lb_iter_default_rewind(struct rpc_xprt_iter *xpi) +++{ +++ WRITE_ONCE(xpi->xpi_cursor, NULL); +++} +++ +++static void enfs_lb_switch_set_roundrobin(struct rpc_clnt *clnt) +++{ +++ struct rpc_xprt_switch *xps; +++ +++ rcu_read_lock(); +++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); +++ rcu_read_unlock(); +++ if (clnt->cl_vers == 3) { +++ +++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_roundrobin) +++ WRITE_ONCE(xps->xps_iter_ops, +++ &enfs_xprt_iter_roundrobin); +++ +++ return; +++ } +++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_singular) +++ WRITE_ONCE(xps->xps_iter_ops, &enfs_xprt_iter_singular); +++} +++ +++static +++struct rpc_xprt *enfs_lb_switch_find_current(struct list_head *head, +++ const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *pos; +++ +++ list_for_each_entry_rcu(pos, head, xprt_switch) { +++ if (cur == pos) +++ return pos; +++ } +++ return NULL; +++} +++ +++static struct rpc_xprt *enfs_lb_iter_current_entry(struct rpc_xprt_iter *xpi) +++{ +++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); +++ struct list_head *head; +++ +++ if (xps == NULL) +++ return NULL; +++ head = &xps->xps_xprt_list; +++ if (xpi->xpi_cursor == NULL || xps->xps_nxprts < 2) +++ return enfs_lb_switch_get_main_xprt(xps); +++ return enfs_lb_switch_find_current(head, xpi->xpi_cursor); +++} +++ +++void enfs_lb_set_policy(struct rpc_clnt *clnt) +++{ +++ enfs_lb_switch_set_roundrobin(clnt); +++} +++ +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin = { +++ .xpi_rewind = enfs_lb_iter_default_rewind, +++ .xpi_xprt = enfs_lb_iter_current_entry, +++ .xpi_next = enfs_lb_iter_next_entry_roundrobin, +++}; +++ +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular = { +++ .xpi_rewind = enfs_lb_iter_default_rewind, +++ .xpi_xprt = enfs_lb_iter_current_entry, +++ .xpi_next = enfs_lb_iter_next_entry_sigular, +++}; ++diff --git a/fs/nfs/enfs/enfs_roundrobin.h b/fs/nfs/enfs/enfs_roundrobin.h ++new file mode 100644 ++index 000000000000..b72b088a6258 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_roundrobin.h ++@@ -0,0 +1,9 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#ifndef ENFS_ROUNDROBIN_H +++#define ENFS_ROUNDROBIN_H +++ +++void enfs_lb_set_policy(struct rpc_clnt *clnt); +++#endif +diff --git a/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch +new file mode 100644 +index 0000000..cc6b677 +--- /dev/null ++++ b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch +@@ -0,0 +1,1607 @@ ++diff --git a/fs/nfs/enfs/enfs_config.c b/fs/nfs/enfs/enfs_config.c ++new file mode 100644 ++index 000000000000..11aa7a00385b ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_config.c ++@@ -0,0 +1,378 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#include <linux/cdev.h> +++#include <linux/errno.h> +++#include <linux/fcntl.h> +++#include <linux/fs.h> +++#include <linux/kernel.h> +++#include <linux/kthread.h> +++#include <linux/slab.h> +++#include <linux/string.h> +++#include <linux/uaccess.h> +++#include <linux/delay.h> +++ +++#include "enfs_errcode.h" +++#include "enfs_log.h" +++#include "enfs_config.h" +++ +++#define MAX_FILE_SIZE 8192 +++#define STRING_BUF_SIZE 128 +++#define CONFIG_FILE_PATH "/etc/enfs/config.ini" +++#define ENFS_NOTIFY_FILE_PERIOD 1000UL +++ +++#define MAX_PATH_DETECT_INTERVAL 300 +++#define MIN_PATH_DETECT_INTERVAL 5 +++#define MAX_PATH_DETECT_TIMEOUT 60 +++#define MIN_PATH_DETECT_TIMEOUT 1 +++#define MAX_MULTIPATH_TIMEOUT 60 +++#define MIN_MULTIPATH_TIMEOUT 0 +++#define MAX_MULTIPATH_STATE ENFS_MULTIPATH_DISABLE +++#define MIN_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE +++ +++#define DEFAULT_PATH_DETECT_INTERVAL 10 +++#define DEFAULT_PATH_DETECT_TIMEOUT 5 +++#define DEFAULT_MULTIPATH_TIMEOUT 0 +++#define DEFAULT_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE +++#define DEFAULT_LOADBALANCE_MODE ENFS_LOADBALANCE_RR +++ +++typedef int (*check_and_assign_func)(char *, char *, int, int); +++ +++struct enfs_config_info { +++ int32_t path_detect_interval; +++ int32_t path_detect_timeout; +++ int32_t multipath_timeout; +++ int32_t loadbalance_mode; +++ int32_t multipath_state; +++}; +++ +++struct check_and_assign_value { +++ char *field_name; +++ check_and_assign_func func; +++ int min_value; +++ int max_value; +++}; +++ +++static struct enfs_config_info g_enfs_config_info; +++static struct timespec64 modify_time; +++static struct task_struct *thread; +++ +++static int enfs_check_config_value(char *value, int min_value, int max_value) +++{ +++ unsigned long num_value; +++ int ret; +++ +++ ret = kstrtol(value, 10, &num_value); +++ if (ret != 0) { +++ enfs_log_error("Failed to convert string to int\n"); +++ return -EINVAL; +++ } +++ +++ if (num_value < min_value || num_value > max_value) +++ return -EINVAL; +++ +++ return num_value; +++} +++ +++static int32_t enfs_check_and_assign_int_value(char *field_name, char *value, +++ int min_value, int max_value) +++{ +++ int int_value = enfs_check_config_value(value, min_value, max_value); +++ +++ if (int_value < 0) +++ return -EINVAL; +++ +++ if (strcmp(field_name, "path_detect_interval") == 0) { +++ g_enfs_config_info.path_detect_interval = int_value; +++ return ENFS_RET_OK; +++ } +++ if (strcmp(field_name, "path_detect_timeout") == 0) { +++ g_enfs_config_info.path_detect_timeout = int_value; +++ return ENFS_RET_OK; +++ } +++ if (strcmp(field_name, "multipath_timeout") == 0) { +++ g_enfs_config_info.multipath_timeout = int_value; +++ return ENFS_RET_OK; +++ } +++ if (strcmp(field_name, "multipath_disable") == 0) { +++ g_enfs_config_info.multipath_state = int_value; +++ return ENFS_RET_OK; +++ } +++ return -EINVAL; +++} +++ +++static int32_t enfs_check_and_assign_loadbalance_mode(char *field_name, +++ char *value, +++ int min_value, +++ int max_value) +++{ +++ if (value == NULL) +++ return -EINVAL; +++ +++ if (strcmp(field_name, "multipath_select_policy") == 0) { +++ if (strcmp(value, "roundrobin") == 0) { +++ g_enfs_config_info.loadbalance_mode +++ = ENFS_LOADBALANCE_RR; +++ return ENFS_RET_OK; +++ } +++ } +++ return -EINVAL; +++} +++ +++static const struct check_and_assign_value g_check_and_assign_value[] = { +++ {"path_detect_interval", enfs_check_and_assign_int_value, +++ MIN_PATH_DETECT_INTERVAL, MAX_PATH_DETECT_INTERVAL}, +++ {"path_detect_timeout", enfs_check_and_assign_int_value, +++ MIN_PATH_DETECT_TIMEOUT, MAX_PATH_DETECT_TIMEOUT}, +++ {"multipath_timeout", enfs_check_and_assign_int_value, +++ MIN_MULTIPATH_TIMEOUT, MAX_MULTIPATH_TIMEOUT}, +++ {"multipath_disable", enfs_check_and_assign_int_value, +++ MIN_MULTIPATH_STATE, MAX_MULTIPATH_STATE}, +++ {"multipath_select_policy", enfs_check_and_assign_loadbalance_mode, +++ 0, 0}, +++}; +++ +++static int32_t enfs_read_config_file(char *buffer, char *file_path) +++{ +++ int ret; +++ struct file *filp = NULL; +++ loff_t f_pos = 0; +++ mm_segment_t fs; +++ +++ +++ filp = filp_open(file_path, O_RDONLY, 0); +++ +++ if (IS_ERR(filp)) { +++ enfs_log_error("Failed to open file %s\n", CONFIG_FILE_PATH); +++ ret = -ENOENT; +++ return ret; +++ } +++ +++ fs = get_fs(); +++ set_fs(get_ds()); +++ kernel_read(filp, buffer, MAX_FILE_SIZE, &f_pos); +++ set_fs(fs); +++ +++ ret = filp_close(filp, NULL); +++ if (ret) { +++ enfs_log_error("Close File:%s failed:%d.\n", +++ CONFIG_FILE_PATH, ret); +++ return -EINVAL; +++ } +++ return ENFS_RET_OK; +++} +++ +++static int32_t enfs_deal_with_comment_line(char *buffer) +++{ +++ int ret; +++ char *pos = strchr(buffer, '\n'); +++ +++ if (pos != NULL) +++ ret = strlen(buffer) - strlen(pos); +++ else +++ ret = strlen(buffer); +++ +++ return ret; +++} +++ +++static int32_t enfs_parse_key_value_from_config(char *buffer, char *key, +++ char *value, int keyLen, +++ int valueLen) +++{ +++ char *line; +++ char *tokenPtr; +++ int len; +++ char *tem; +++ char *pos = strchr(buffer, '\n'); +++ +++ if (pos != NULL) +++ len = strlen(buffer) - strlen(pos); +++ else +++ len = strlen(buffer); +++ +++ line = kmalloc(len + 1, GFP_KERNEL); +++ if (!line) { +++ enfs_log_error("Failed to allocate memory.\n"); +++ return -ENOMEM; +++ } +++ line[len] = '\0'; +++ strncpy(line, buffer, len); +++ +++ tem = line; +++ tokenPtr = strsep(&tem, "="); +++ if (tokenPtr == NULL || tem == NULL) { +++ kfree(line); +++ return len; +++ } +++ strncpy(key, strim(tokenPtr), keyLen); +++ strncpy(value, strim(tem), valueLen); +++ +++ kfree(line); +++ return len; +++} +++ +++static int32_t enfs_get_value_from_config_file(char *buffer, char *field_name, +++ char *value, int valueLen) +++{ +++ int ret; +++ char key[STRING_BUF_SIZE + 1] = {0}; +++ char val[STRING_BUF_SIZE + 1] = {0}; +++ +++ while (buffer[0] != '\0') { +++ if (buffer[0] == '\n') { +++ buffer++; +++ } else if (buffer[0] == '#') { +++ ret = enfs_deal_with_comment_line(buffer); +++ if (ret > 0) +++ buffer += ret; +++ } else { +++ ret = enfs_parse_key_value_from_config(buffer, key, val, +++ STRING_BUF_SIZE, +++ STRING_BUF_SIZE); +++ if (ret < 0) { +++ enfs_log_error("failed parse key value, %d\n" +++ , ret); +++ return ret; +++ } +++ key[STRING_BUF_SIZE] = '\0'; +++ val[STRING_BUF_SIZE] = '\0'; +++ +++ buffer += ret; +++ +++ if (strcmp(field_name, key) == 0) { +++ strncpy(value, val, valueLen); +++ return ENFS_RET_OK; +++ } +++ } +++ } +++ enfs_log_error("can not find value which matched field_name: %s.\n", +++ field_name); +++ return -EINVAL; +++} +++ +++int32_t enfs_config_load(void) +++{ +++ char value[STRING_BUF_SIZE + 1]; +++ int ret; +++ int table_len; +++ int min; +++ int max; +++ int i; +++ char *buffer; +++ +++ buffer = kmalloc(MAX_FILE_SIZE, GFP_KERNEL); +++ if (!buffer) { +++ enfs_log_error("Failed to allocate memory.\n"); +++ return -ENOMEM; +++ } +++ memset(buffer, 0, MAX_FILE_SIZE); +++ +++ g_enfs_config_info.path_detect_interval = DEFAULT_PATH_DETECT_INTERVAL; +++ g_enfs_config_info.path_detect_timeout = DEFAULT_PATH_DETECT_TIMEOUT; +++ g_enfs_config_info.multipath_timeout = DEFAULT_MULTIPATH_TIMEOUT; +++ g_enfs_config_info.multipath_state = DEFAULT_MULTIPATH_STATE; +++ g_enfs_config_info.loadbalance_mode = DEFAULT_LOADBALANCE_MODE; +++ +++ table_len = sizeof(g_check_and_assign_value) / +++ sizeof(g_check_and_assign_value[0]); +++ +++ ret = enfs_read_config_file(buffer, CONFIG_FILE_PATH); +++ if (ret != 0) { +++ kfree(buffer); +++ return ret; +++ } +++ +++ for (i = 0; i < table_len; i++) { +++ ret = enfs_get_value_from_config_file(buffer, +++ g_check_and_assign_value[i].field_name, +++ value, STRING_BUF_SIZE); +++ if (ret < 0) +++ continue; +++ +++ value[STRING_BUF_SIZE] = '\0'; +++ min = g_check_and_assign_value[i].min_value; +++ max = g_check_and_assign_value[i].max_value; +++ if (g_check_and_assign_value[i].func != NULL) +++ (*g_check_and_assign_value[i].func)( +++ g_check_and_assign_value[i].field_name, +++ value, min, max); +++ } +++ +++ kfree(buffer); +++ return ENFS_RET_OK; +++} +++ +++int32_t enfs_get_config_path_detect_interval(void) +++{ +++ return g_enfs_config_info.path_detect_interval; +++} +++ +++int32_t enfs_get_config_path_detect_timeout(void) +++{ +++ return g_enfs_config_info.path_detect_timeout; +++} +++ +++int32_t enfs_get_config_multipath_timeout(void) +++{ +++ return g_enfs_config_info.multipath_timeout; +++} +++ +++int32_t enfs_get_config_multipath_state(void) +++{ +++ return g_enfs_config_info.multipath_state; +++} +++ +++int32_t enfs_get_config_loadbalance_mode(void) +++{ +++ return g_enfs_config_info.loadbalance_mode; +++} +++ +++static bool enfs_file_changed(const char *filename) +++{ +++ int err; +++ struct kstat file_stat; +++ +++ err = vfs_stat(filename, &file_stat); +++ if (err) { +++ pr_err("failed to open file:%s err:%d\n", filename, err); +++ return false; +++ } +++ +++ if (timespec64_compare(&modify_time, &file_stat.mtime) == -1) { +++ modify_time = file_stat.mtime; +++ pr_info("file change: %lld %lld\n", modify_time.tv_sec, +++ file_stat.mtime.tv_sec); +++ return true; +++ } +++ +++ return false; +++} +++ +++static int enfs_thread_func(void *data) +++{ +++ while (!kthread_should_stop()) { +++ if (enfs_file_changed(CONFIG_FILE_PATH)) +++ enfs_config_load(); +++ +++ msleep(ENFS_NOTIFY_FILE_PERIOD); +++ } +++ return 0; +++} +++ +++int enfs_config_timer_init(void) +++{ +++ thread = kthread_run(enfs_thread_func, NULL, "enfs_notiy_file_thread"); +++ if (IS_ERR(thread)) { +++ pr_err("Failed to create kernel thread\n"); +++ return PTR_ERR(thread); +++ } +++ return 0; +++} +++ +++void enfs_config_timer_exit(void) +++{ +++ pr_info("enfs_notify_file_exit\n"); +++ if (thread) +++ kthread_stop(thread); +++} ++diff --git a/fs/nfs/enfs/enfs_config.h b/fs/nfs/enfs/enfs_config.h ++new file mode 100644 ++index 000000000000..752710129170 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_config.h ++@@ -0,0 +1,32 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs configuration +++ * Author: y00583252 +++ * Create: 2023-07-27 +++ */ +++ +++#ifndef ENFS_CONFIG_H +++#define ENFS_CONFIG_H +++ +++#include <linux/types.h> +++ +++enum enfs_multipath_state { +++ ENFS_MULTIPATH_ENABLE = 0, +++ ENFS_MULTIPATH_DISABLE = 1, +++}; +++ +++enum enfs_loadbalance_mode { +++ ENFS_LOADBALANCE_RR, +++}; +++ +++ +++int32_t enfs_get_config_path_detect_interval(void); +++int32_t enfs_get_config_path_detect_timeout(void); +++int32_t enfs_get_config_multipath_timeout(void); +++int32_t enfs_get_config_multipath_state(void); +++int32_t enfs_get_config_loadbalance_mode(void); +++int32_t enfs_config_load(void); +++int32_t enfs_config_timer_init(void); +++void enfs_config_timer_exit(void); +++#endif // ENFS_CONFIG_H ++diff --git a/fs/nfs/enfs/enfs_errcode.h b/fs/nfs/enfs/enfs_errcode.h ++new file mode 100644 ++index 000000000000..cca47ab9a191 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_errcode.h ++@@ -0,0 +1,17 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs errocode +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef ENFS_ERRCODE_H +++#define ENFS_ERRCODE_H +++ +++enum { +++ ENFS_RET_OK = 0, +++ ENFS_RET_FAIL +++}; +++ +++#endif // ENFS_ERRCODE_H ++diff --git a/fs/nfs/enfs/enfs_log.h b/fs/nfs/enfs/enfs_log.h ++new file mode 100644 ++index 000000000000..177b404f05df ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_log.h ++@@ -0,0 +1,25 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: enfs log +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++#ifndef ENFS_LOG_H +++#define ENFS_LOG_H +++ +++#include <linux/printk.h> +++ +++#define enfs_log_info(fmt, ...) \ +++ pr_info("enfs:[%s]" pr_fmt(fmt), \ +++ __func__, ##__VA_ARGS__) +++ +++#define enfs_log_error(fmt, ...) \ +++ pr_err("enfs:[%s]" pr_fmt(fmt), \ +++ __func__, ##__VA_ARGS__) +++ +++#define enfs_log_debug(fmt, ...) \ +++ pr_debug("enfs:[%s]" pr_fmt(fmt), \ +++ __func__, ##__VA_ARGS__) +++ +++#endif // ENFS_ERRCODE_H ++diff --git a/fs/nfs/enfs/failover_com.h b/fs/nfs/enfs/failover_com.h ++new file mode 100644 ++index 000000000000..c52940da232e ++--- /dev/null +++++ b/fs/nfs/enfs/failover_com.h ++@@ -0,0 +1,23 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: failover time commont header file +++ * Create: 2023-08-02 +++ */ +++#ifndef FAILOVER_COMMON_H +++#define FAILOVER_COMMON_H +++ +++static inline bool failover_is_enfs_clnt(struct rpc_clnt *clnt) +++{ +++ struct rpc_clnt *next = clnt->cl_parent; +++ +++ while (next) { +++ if (next == next->cl_parent) +++ break; +++ next = next->cl_parent; +++ } +++ +++ return next != NULL ? next->cl_enfs : clnt->cl_enfs; +++} +++ +++#endif // FAILOVER_COMMON_H ++diff --git a/fs/nfs/enfs/failover_path.c b/fs/nfs/enfs/failover_path.c ++new file mode 100644 ++index 000000000000..93b454de29d1 ++--- /dev/null +++++ b/fs/nfs/enfs/failover_path.c ++@@ -0,0 +1,207 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs path failover file +++ * Author: y00583252 +++ * Create: 2023-08-02 +++ */ +++ +++#include "failover_path.h" +++#include <linux/nfs.h> +++#include <linux/nfs3.h> +++#include <linux/nfs4.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/sched.h> +++#include <linux/sunrpc/xprt.h> +++#include "enfs_config.h" +++#include "enfs_log.h" +++#include "failover_com.h" +++#include "pm_state.h" +++#include "pm_ping.h" +++ +++enum failover_policy_t { +++ FAILOVER_NOACTION = 1, +++ FAILOVER_RETRY, +++ FAILOVER_RETRY_DELAY, +++}; +++ +++static void failover_retry_path(struct rpc_task *task) +++{ +++ xprt_release(task); +++ rpc_init_task_retry_counters(task); +++ rpc_task_release_transport(task); +++ rpc_restart_call(task); +++} +++ +++static void failover_retry_path_delay(struct rpc_task *task, int32_t delay) +++{ +++ failover_retry_path(task); +++ rpc_delay(task, delay); +++} +++ +++static void failover_retry_path_by_policy(struct rpc_task *task, +++ enum failover_policy_t policy) +++{ +++ if (policy == FAILOVER_RETRY) +++ failover_retry_path(task); +++ else if (policy == FAILOVER_RETRY_DELAY) +++ failover_retry_path_delay(task, 3 * HZ); // delay 3s +++} +++ +++static +++enum failover_policy_t failover_get_nfs3_retry_policy(struct rpc_task *task) +++{ +++ enum failover_policy_t policy = FAILOVER_NOACTION; +++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; +++ u32 proc; +++ +++ if (unlikely(procinfo == NULL)) { +++ enfs_log_error("the task contains no valid proc.\n"); +++ return FAILOVER_NOACTION; +++ } +++ +++ proc = procinfo->p_proc; +++ +++ switch (proc) { +++ case NFS3PROC_CREATE: +++ case NFS3PROC_MKDIR: +++ case NFS3PROC_REMOVE: +++ case NFS3PROC_RMDIR: +++ case NFS3PROC_SYMLINK: +++ case NFS3PROC_LINK: +++ case NFS3PROC_SETATTR: +++ case NFS3PROC_WRITE: +++ policy = FAILOVER_RETRY_DELAY; +++ default: +++ policy = FAILOVER_RETRY; +++ } +++ return policy; +++} +++ +++static +++enum failover_policy_t failover_get_nfs4_retry_policy(struct rpc_task *task) +++{ +++ enum failover_policy_t policy = FAILOVER_NOACTION; +++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; +++ u32 proc_idx; +++ +++ if (unlikely(procinfo == NULL)) { +++ enfs_log_error("the task contains no valid proc.\n"); +++ return FAILOVER_NOACTION; +++ } +++ +++ proc_idx = procinfo->p_statidx; +++ +++ switch (proc_idx) { +++ case NFSPROC4_CLNT_CREATE: +++ case NFSPROC4_CLNT_REMOVE: +++ case NFSPROC4_CLNT_LINK: +++ case NFSPROC4_CLNT_SYMLINK: +++ case NFSPROC4_CLNT_SETATTR: +++ case NFSPROC4_CLNT_WRITE: +++ case NFSPROC4_CLNT_RENAME: +++ case NFSPROC4_CLNT_SETACL: +++ policy = FAILOVER_RETRY_DELAY; +++ default: +++ policy = FAILOVER_RETRY; +++ } +++ return policy; +++} +++ +++static enum failover_policy_t failover_get_retry_policy(struct rpc_task *task) +++{ +++ struct rpc_clnt *clnt = task->tk_client; +++ u32 version = clnt->cl_vers; +++ enum failover_policy_t policy = FAILOVER_NOACTION; +++ +++ // 1. if the task meant to send to certain xprt, take no action +++ if (task->tk_flags & RPC_TASK_FIXED) +++ return FAILOVER_NOACTION; +++ +++ // 2. get policy by different version of nfs protocal +++ if (version == 3) // nfs v3 +++ policy = failover_get_nfs3_retry_policy(task); +++ else if (version == 4) // nfs v4 +++ policy = failover_get_nfs4_retry_policy(task); +++ else +++ return FAILOVER_NOACTION; +++ +++ // 3. if the task is not send to target, retry immediately +++ if (!RPC_WAS_SENT(task)) +++ policy = FAILOVER_RETRY; +++ +++ return policy; +++} +++ +++static int failover_check_task(struct rpc_task *task) +++{ +++ struct rpc_clnt *clnt = NULL; +++ int disable_mpath = enfs_get_config_multipath_state(); +++ +++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return -EINVAL; +++ } +++ +++ if (unlikely((task == NULL) || (task->tk_client == NULL))) { +++ enfs_log_error("The task is not valid.\n"); +++ return -EINVAL; +++ } +++ +++ clnt = task->tk_client; +++ +++ if (clnt->cl_prog != NFS_PROGRAM) { +++ enfs_log_debug("The clnt is not prog{%u} type.\n", +++ clnt->cl_prog); +++ return -EINVAL; +++ } +++ +++ if (!failover_is_enfs_clnt(clnt)) { +++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); +++ return -EINVAL; +++ } +++ return 0; +++} +++ +++void failover_handle(struct rpc_task *task) +++{ +++ enum failover_policy_t policy; +++ int ret; +++ +++ ret = failover_check_task(task); +++ if (ret != 0) +++ return; +++ +++ pm_set_path_state(task->tk_xprt, PM_STATE_FAULT); +++ +++ policy = failover_get_retry_policy(task); +++ +++ failover_retry_path_by_policy(task, policy); +++} +++ +++bool failover_task_need_call_start_again(struct rpc_task *task) +++{ +++ int ret; +++ +++ ret = failover_check_task(task); +++ if (ret != 0) +++ return false; +++ +++ return true; +++} +++ +++bool failover_prepare_transmit(struct rpc_task *task) +++{ +++ if (task->tk_flags & RPC_TASK_FIXED) +++ return true; +++ +++ if (pm_ping_is_test_xprt_task(task)) +++ return true; +++ +++ if (pm_get_path_state(task->tk_xprt) == PM_STATE_FAULT) { +++ task->tk_status = -ETIMEDOUT; +++ return false; +++ } +++ +++ return true; +++} ++diff --git a/fs/nfs/enfs/failover_path.h b/fs/nfs/enfs/failover_path.h ++new file mode 100644 ++index 000000000000..6f1294829a6e ++--- /dev/null +++++ b/fs/nfs/enfs/failover_path.h ++@@ -0,0 +1,17 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs path failover header file +++ * Author: y00583252 +++ * Create: 2023-08-02 +++ */ +++ +++#ifndef FAILOVER_PATH_H +++#define FAILOVER_PATH_H +++ +++#include <linux/sunrpc/sched.h> +++ +++void failover_handle(struct rpc_task *task); +++bool failover_prepare_transmit(struct rpc_task *task); +++ +++#endif // FAILOVER_PATH_H ++diff --git a/fs/nfs/enfs/failover_time.c b/fs/nfs/enfs/failover_time.c ++new file mode 100644 ++index 000000000000..866ea82d13fc ++--- /dev/null +++++ b/fs/nfs/enfs/failover_time.c ++@@ -0,0 +1,99 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: failover time file +++ * Create: 2023-08-02 +++ */ +++ +++#include "failover_time.h" +++#include <linux/jiffies.h> +++#include <linux/sunrpc/clnt.h> +++#include "enfs_config.h" +++#include "enfs_log.h" +++#include "failover_com.h" +++#include "pm_ping.h" +++ +++static unsigned long failover_get_mulitipath_timeout(struct rpc_clnt *clnt) +++{ +++ unsigned long config_tmo = enfs_get_config_multipath_timeout() * HZ; +++ unsigned long clnt_tmo = clnt->cl_timeout->to_initval; +++ +++ if (config_tmo == 0) +++ return clnt_tmo; +++ +++ return config_tmo > clnt_tmo ? clnt_tmo : config_tmo; +++} +++ +++void failover_adjust_task_timeout(struct rpc_task *task, void *condition) +++{ +++ struct rpc_clnt *clnt = NULL; +++ unsigned long tmo; +++ int disable_mpath = enfs_get_config_multipath_state(); +++ +++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return; +++ } +++ +++ clnt = task->tk_client; +++ if (unlikely(clnt == NULL)) { +++ enfs_log_error("task associate client is NULL.\n"); +++ return; +++ } +++ +++ if (!failover_is_enfs_clnt(clnt)) { +++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); +++ return; +++ } +++ +++ tmo = failover_get_mulitipath_timeout(clnt); +++ if (tmo == 0) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return; +++ } +++ +++ if (task->tk_timeout != 0) +++ task->tk_timeout = +++ task->tk_timeout < tmo ? task->tk_timeout : tmo; +++ else +++ task->tk_timeout = tmo; +++} +++ +++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req) +++{ +++ struct rpc_clnt *clnt = NULL; +++ int disable_mpath = enfs_get_config_multipath_state(); +++ +++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return; +++ } +++ +++ clnt = task->tk_client; +++ if (unlikely(clnt == NULL)) { +++ enfs_log_error("task associate client is NULL.\n"); +++ return; +++ } +++ +++ if (!failover_is_enfs_clnt(clnt)) { +++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); +++ return; +++ } +++ +++ if (!pm_ping_is_test_xprt_task(task)) +++ req->rq_timeout = failover_get_mulitipath_timeout(clnt); +++ else { +++ req->rq_timeout = enfs_get_config_path_detect_timeout() * HZ; +++ req->rq_majortimeo = req->rq_timeout + jiffies; +++ } +++ +++ /* +++ * when task is retried, the req is new, we lost major-timeout times, +++ * so we have to restore req major +++ * timeouts from the task, if it is stored. +++ */ +++ if (task->tk_major_timeo != 0) +++ req->rq_majortimeo = task->tk_major_timeo; +++ else +++ task->tk_major_timeo = req->rq_majortimeo; +++} ++diff --git a/fs/nfs/enfs/failover_time.h b/fs/nfs/enfs/failover_time.h ++new file mode 100644 ++index 000000000000..ede25b577a2a ++--- /dev/null +++++ b/fs/nfs/enfs/failover_time.h ++@@ -0,0 +1,16 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: failover time header file +++ * Create: 2023-08-02 +++ */ +++ +++#ifndef FAILOVER_TIME_H +++#define FAILOVER_TIME_H +++ +++#include <linux/sunrpc/sched.h> +++ +++void failover_adjust_task_timeout(struct rpc_task *task, void *condition); +++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req); +++ +++#endif // FAILOVER_TIME_H ++diff --git a/fs/nfs/enfs/init.h b/fs/nfs/enfs/init.h ++new file mode 100644 ++index 000000000000..fdabb9084e19 ++--- /dev/null +++++ b/fs/nfs/enfs/init.h ++@@ -0,0 +1,17 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs client init +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef ENFS_INIT_H +++#define ENFS_INIT_H +++ +++#include <linux/types.h> +++ +++int32_t enfs_init(void); +++void enfs_fini(void); +++ +++#endif ++diff --git a/fs/nfs/enfs/mgmt_init.c b/fs/nfs/enfs/mgmt_init.c ++new file mode 100644 ++index 000000000000..75a40c5e0f6c ++--- /dev/null +++++ b/fs/nfs/enfs/mgmt_init.c ++@@ -0,0 +1,22 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: mgmt component init +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#include "mgmt_init.h" +++#include <linux/printk.h> +++#include "enfs_errcode.h" +++#include "enfs_config.h" +++ +++int32_t mgmt_init(void) +++{ +++ return enfs_config_timer_init(); +++} +++ +++void mgmt_fini(void) +++{ +++ enfs_config_timer_exit(); +++} ++diff --git a/fs/nfs/enfs/mgmt_init.h b/fs/nfs/enfs/mgmt_init.h ++new file mode 100644 ++index 000000000000..aa78303b9f01 ++--- /dev/null +++++ b/fs/nfs/enfs/mgmt_init.h ++@@ -0,0 +1,18 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: mgmt component init +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef MGMT_INIT_H +++#define MGMT_INIT_H +++ +++#include <linux/types.h> +++ +++int32_t mgmt_init(void); +++void mgmt_fini(void); +++ +++ +++#endif // MGMT_INIT_H ++diff --git a/fs/nfs/enfs/pm_ping.c b/fs/nfs/enfs/pm_ping.c ++new file mode 100644 ++index 000000000000..24153cd4c7f3 ++--- /dev/null +++++ b/fs/nfs/enfs/pm_ping.c ++@@ -0,0 +1,421 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: path state header file +++ * Author: x00833432 +++ * Create: 2023-08-21 +++ */ +++ +++#include "pm_ping.h" +++#include <linux/err.h> +++#include <linux/spinlock.h> +++#include <linux/slab.h> +++#include <linux/module.h> +++#include <linux/printk.h> +++#include <linux/kthread.h> +++#include <linux/nfs.h> +++#include <linux/errno.h> +++#include <linux/rcupdate.h> +++#include <linux/workqueue.h> +++#include <net/netns/generic.h> +++#include <linux/atomic.h> +++#include <linux/sunrpc/clnt.h> +++ +++#include "../../../net/sunrpc/netns.h" +++#include "pm_state.h" +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_config.h" +++ +++#define SLEEP_INTERVAL 2 +++extern unsigned int sunrpc_net_id; +++ +++static struct task_struct *pm_ping_timer_thread; +++//protect pint_execute_workq +++static spinlock_t ping_execute_workq_lock; +++// timer for test xprt workqueue +++static struct workqueue_struct *ping_execute_workq; +++// count the ping xprt work on flight +++static atomic_t check_xprt_count; +++ +++struct ping_xprt_work { +++ struct rpc_xprt *xprt; // use this specific xprt +++ struct rpc_clnt *clnt; // use this specific rpc_client +++ struct work_struct ping_work; +++}; +++ +++struct pm_ping_async_callback { +++ void *data; +++ void (*func)(void *data); +++}; +++ +++// set xprt's enum pm_check_state +++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, +++ enum pm_check_state state) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ +++ if (IS_ERR(xprt)) { +++ enfs_log_error("The xprt ptr is not exist.\n"); +++ return; +++ } +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ xprt_get(xprt); +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ xprt_put(xprt); +++ return; +++ } +++ +++ atomic_set(&ctx->path_check_state, state); +++ xprt_put(xprt); +++} +++ +++// get xprt's enum pm_check_state +++static enum pm_check_state pm_ping_get_path_check_state(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ enum pm_check_state state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return PM_CHECK_UNDEFINE; +++ } +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ return PM_CHECK_UNDEFINE; +++ } +++ +++ state = atomic_read(&ctx->path_check_state); +++ +++ return state; +++} +++ +++static void pm_ping_call_done_callback(void *data) +++{ +++ struct pm_ping_async_callback *callback_data = +++ (struct pm_ping_async_callback *)data; +++ +++ if (callback_data == NULL) +++ return; +++ +++ callback_data->func(callback_data->data); +++ +++ kfree(callback_data); +++} +++ +++// Default callback for async RPC calls +++static void pm_ping_call_done(struct rpc_task *task, void *data) +++{ +++ struct rpc_xprt *xprt = task->tk_xprt; +++ +++ atomic_dec(&check_xprt_count); +++ if (task->tk_status >= 0) +++ pm_set_path_state(xprt, PM_STATE_NORMAL); +++ else +++ pm_set_path_state(xprt, PM_STATE_FAULT); +++ +++ pm_ping_set_path_check_state(xprt, PM_CHECK_FINISH); +++ +++ pm_ping_call_done_callback(data); +++} +++ +++// register func to rpc_call_done +++static const struct rpc_call_ops pm_ping_set_status_ops = { +++ .rpc_call_done = pm_ping_call_done, +++}; +++ +++// execute work which in work_queue +++static void pm_ping_execute_work(struct work_struct *work) +++{ +++ int ret = 0; +++ +++ // get the work information +++ struct ping_xprt_work *work_info = +++ container_of(work, struct ping_xprt_work, ping_work); +++ +++ // if check state is pending +++ if (pm_ping_get_path_check_state(work_info->xprt) == PM_CHECK_WAITING) { +++ +++ pm_ping_set_path_check_state(work_info->xprt, +++ PM_CHECK_CHECKING); +++ +++ ret = rpc_clnt_test_xprt(work_info->clnt, +++ work_info->xprt, +++ &pm_ping_set_status_ops, +++ NULL, +++ RPC_TASK_ASYNC | RPC_TASK_FIXED); +++ +++ if (ret < 0) { +++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); +++ +++ pm_ping_set_path_check_state(work_info->xprt, +++ PM_CHECK_FINISH); +++ +++ } else +++ atomic_inc(&check_xprt_count); +++ +++ } +++ +++ atomic_dec(&work_info->clnt->cl_count); +++ xprt_put(work_info->xprt); +++ kfree(work_info); +++ work_info = NULL; +++} +++ +++static bool pm_ping_workqueue_queue_work(struct work_struct *work) +++{ +++ bool ret = false; +++ +++ spin_lock(&ping_execute_workq_lock); +++ +++ if (ping_execute_workq != NULL) +++ ret = queue_work(ping_execute_workq, work); +++ +++ spin_unlock(&ping_execute_workq_lock); +++ return ret; +++} +++ +++// init test work and add this work to workqueue +++static int pm_ping_add_work(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, void *data) +++{ +++ struct ping_xprt_work *work_info; +++ bool ret = false; +++ +++ if (IS_ERR(xprt) || xprt == NULL) { +++ enfs_log_error("The xprt ptr is not exist.\n"); +++ return -EINVAL; +++ } +++ +++ if (IS_ERR(clnt) || clnt == NULL) { +++ enfs_log_error("The clnt ptr is not exist.\n"); +++ return -EINVAL; +++ } +++ +++ if (!xprt->multipath_context) { +++ enfs_log_error("multipath_context is null.\n"); +++ return -EINVAL; +++ } +++ +++ // check xprt pending status, if pending status equals Finish +++ // means this xprt can inster to work queue +++ if (pm_ping_get_path_check_state(xprt) == +++ PM_CHECK_FINISH || +++ pm_ping_get_path_check_state(xprt) == +++ PM_CHECK_INIT) { +++ +++ enfs_log_debug("find xprt pointer. %p\n", xprt); +++ work_info = kzalloc(sizeof(struct ping_xprt_work), GFP_ATOMIC); +++ if (work_info == NULL) +++ return -ENOMEM; +++ work_info->clnt = clnt; +++ atomic_inc(&clnt->cl_count); +++ work_info->xprt = xprt; +++ xprt_get(xprt); +++ INIT_WORK(&work_info->ping_work, pm_ping_execute_work); +++ pm_ping_set_path_check_state(xprt, PM_CHECK_WAITING); +++ +++ ret = pm_ping_workqueue_queue_work(&work_info->ping_work); +++ if (!ret) { +++ atomic_dec(&work_info->clnt->cl_count); +++ xprt_put(work_info->xprt); +++ kfree(work_info); +++ return -EINVAL; +++ } +++ } +++ return 0; +++} +++ +++// encapsulate pm_ping_add_work() +++static int pm_ping_execute_xprt_test(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, void *data) +++{ +++ pm_ping_add_work(clnt, xprt, NULL); +++ // return 0 for rpc_clnt_iterate_for_each_xprt(); +++ // because negative value will stop iterate all xprt +++ // and we need return negative value for debug +++ // Therefore, we need this function to iterate all xprt +++ return 0; +++} +++ +++// export to other module add ping work to workqueue +++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) +++{ +++ int ret; +++ +++ ret = pm_ping_add_work(clnt, xprt, NULL); +++ return ret; +++} +++ +++// iterate xprt in the client +++static void pm_ping_loop_rpclnt(struct sunrpc_net *sn) +++{ +++ struct rpc_clnt *clnt; +++ +++ spin_lock(&sn->rpc_client_lock); +++ list_for_each_entry_rcu(clnt, &sn->all_clients, cl_clients) { +++ if (clnt->cl_enfs) { +++ enfs_log_debug("find rpc_clnt. %p\n", clnt); +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ pm_ping_execute_xprt_test, NULL); +++ } +++ } +++ spin_unlock(&sn->rpc_client_lock); +++} +++ +++// iterate each clnt in the sunrpc_net +++static void pm_ping_loop_sunrpc_net(void) +++{ +++ struct net *net; +++ struct sunrpc_net *sn; +++ +++ rcu_read_lock(); +++ for_each_net_rcu(net) { +++ sn = net_generic(net, sunrpc_net_id); +++ if (sn == NULL) +++ continue; +++ pm_ping_loop_rpclnt(sn); +++ } +++ rcu_read_unlock(); +++} +++ +++static int pm_ping_routine(void *data) +++{ +++ while (!kthread_should_stop()) { +++ // equale 0 means open multipath +++ if (enfs_get_config_multipath_state() == +++ ENFS_MULTIPATH_ENABLE) +++ pm_ping_loop_sunrpc_net(); +++ +++ msleep((unsigned int) +++ enfs_get_config_path_detect_interval() * 1000); +++ } +++ return 0; +++} +++ +++// start thread to cycly ping +++static int pm_ping_start(void) +++{ +++ pm_ping_timer_thread = +++ kthread_run(pm_ping_routine, NULL, "pm_ping_routine"); +++ if (IS_ERR(pm_ping_timer_thread)) { +++ enfs_log_error("Failed to create kernel thread\n"); +++ return PTR_ERR(pm_ping_timer_thread); +++ } +++ return 0; +++} +++ +++// initialize workqueue +++static int pm_ping_workqueue_init(void) +++{ +++ struct workqueue_struct *queue = NULL; +++ +++ queue = create_workqueue("pm_ping_workqueue"); +++ +++ if (queue == NULL) { +++ enfs_log_error("create workqueue failed.\n"); +++ return -ENOMEM; +++ } +++ +++ spin_lock(&ping_execute_workq_lock); +++ ping_execute_workq = queue; +++ spin_unlock(&ping_execute_workq_lock); +++ enfs_log_info("create workqueue succeeeded.\n"); +++ return 0; +++} +++ +++static void pm_ping_workqueue_fini(void) +++{ +++ struct workqueue_struct *queue = NULL; +++ +++ spin_lock(&ping_execute_workq_lock); +++ queue = ping_execute_workq; +++ ping_execute_workq = NULL; +++ spin_unlock(&ping_execute_workq_lock); +++ +++ enfs_log_info("delete work queue\n"); +++ +++ if (queue != NULL) { +++ flush_workqueue(queue); +++ destroy_workqueue(queue); +++ } +++} +++ +++// module exit func +++void pm_ping_fini(void) +++{ +++ if (pm_ping_timer_thread) +++ kthread_stop(pm_ping_timer_thread); +++ +++ pm_ping_workqueue_fini(); +++ +++ while (atomic_read(&check_xprt_count) != 0) +++ msleep(SLEEP_INTERVAL); +++} +++ +++// module init func +++int pm_ping_init(void) +++{ +++ int ret; +++ +++ atomic_set(&check_xprt_count, 0); +++ ret = pm_ping_workqueue_init(); +++ if (ret != 0) { +++ enfs_log_error("PM_PING Module loading failed.\n"); +++ return ret; +++ } +++ ret = pm_ping_start(); +++ if (ret != 0) { +++ enfs_log_error("PM_PING Module loading failed.\n"); +++ pm_ping_workqueue_fini(); +++ return ret; +++ } +++ +++ return ret; +++} +++ +++bool pm_ping_is_test_xprt_task(struct rpc_task *task) +++{ +++ return task->tk_ops == &pm_ping_set_status_ops ? true : false; +++} +++ +++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void (*func)(void *data), +++ void *data) +++{ +++ int ret; +++ +++ struct pm_ping_async_callback *callback_data = +++ kzalloc(sizeof(struct pm_ping_async_callback), GFP_KERNEL); +++ +++ if (callback_data == NULL) { +++ enfs_log_error("failed to mzalloc mem\n"); +++ return -ENOMEM; +++ } +++ +++ callback_data->data = data; +++ callback_data->func = func; +++ atomic_inc(&check_xprt_count); +++ ret = rpc_clnt_test_xprt(clnt, xprt, +++ &pm_ping_set_status_ops, +++ callback_data, +++ RPC_TASK_ASYNC | RPC_TASK_FIXED); +++ +++ if (ret < 0) { +++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); +++ atomic_dec(&check_xprt_count); +++ } +++ +++ return ret; +++} ++diff --git a/fs/nfs/enfs/pm_ping.h b/fs/nfs/enfs/pm_ping.h ++new file mode 100644 ++index 000000000000..6bcb94bfc836 ++--- /dev/null +++++ b/fs/nfs/enfs/pm_ping.h ++@@ -0,0 +1,33 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs configuration +++ * Author: x00833432 +++ * Create: 2023-07-27 +++ */ +++ +++#ifndef PM_PING_H +++#define PM_PING_H +++ +++#include <linux/sunrpc/clnt.h> +++ +++enum pm_check_state { +++ PM_CHECK_INIT, // this xprt never been queued +++ PM_CHECK_WAITING, // this xprt waiting in the queue +++ PM_CHECK_CHECKING, // this xprt is testing +++ PM_CHECK_FINISH, // this xprt has been finished +++ PM_CHECK_UNDEFINE, // undefine multipath struct +++}; +++ +++int pm_ping_init(void); +++void pm_ping_fini(void); +++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, +++ enum pm_check_state state); +++bool pm_ping_is_test_xprt_task(struct rpc_task *task); +++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void (*func)(void *data), +++ void *data); +++ +++#endif // PM_PING_H ++diff --git a/fs/nfs/enfs/pm_state.c b/fs/nfs/enfs/pm_state.c ++new file mode 100644 ++index 000000000000..220621a207a2 ++--- /dev/null +++++ b/fs/nfs/enfs/pm_state.c ++@@ -0,0 +1,158 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: path state file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++#include "pm_state.h" +++#include <linux/sunrpc/xprt.h> +++ +++#include "enfs.h" +++#include "enfs_log.h" +++ +++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ enum pm_path_state state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return PM_STATE_UNDEFINED; +++ } +++ +++ xprt_get(xprt); +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ xprt_put(xprt); +++ return PM_STATE_UNDEFINED; +++ } +++ +++ state = atomic_read(&ctx->path_state); +++ +++ xprt_put(xprt); +++ +++ return state; +++} +++ +++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ enum pm_path_state cur_state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ xprt_get(xprt); +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ xprt_put(xprt); +++ return; +++ } +++ +++ cur_state = atomic_read(&ctx->path_state); +++ if (cur_state == state) { +++ enfs_log_debug("The xprt is already {%d}.\n", state); +++ xprt_put(xprt); +++ return; +++ } +++ +++ atomic_set(&ctx->path_state, state); +++ enfs_log_info("The xprt {%p} path state change from {%d} to {%d}.\n", +++ xprt, cur_state, state); +++ +++ xprt_put(xprt); +++} +++ +++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len) +++{ +++ enum pm_path_state state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ if ((buf == NULL) || (len <= 0)) { +++ enfs_log_error("Buffer is not valid, len=%d.\n", len); +++ return; +++ } +++ +++ state = pm_get_path_state(xprt); +++ +++ switch (state) { +++ case PM_STATE_INIT: +++ (void)snprintf(buf, len, "Init"); +++ break; +++ case PM_STATE_NORMAL: +++ (void)snprintf(buf, len, "Normal"); +++ break; +++ case PM_STATE_FAULT: +++ (void)snprintf(buf, len, "Fault"); +++ break; +++ default: +++ (void)snprintf(buf, len, "Unknown"); +++ break; +++ } +++} +++ +++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len) +++{ +++ int i; +++ unsigned long state; +++ static unsigned long xprt_mask[] = { +++ XPRT_LOCKED, XPRT_CONNECTED, +++ XPRT_CONNECTING, XPRT_CLOSE_WAIT, +++ XPRT_BOUND, XPRT_BINDING, XPRT_CLOSING, +++ XPRT_CONGESTED}; +++ +++ static const char *const xprt_state_desc[] = { +++ "LOCKED", "CONNECTED", "CONNECTING", +++ "CLOSE_WAIT", "BOUND", "BINDING", +++ "CLOSING", "CONGESTED"}; +++ int pos = 0; +++ int ret = 0; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ if ((buf == NULL) || (len <= 0)) { +++ enfs_log_error( +++ "Xprt state buffer is not valid, len=%d.\n", +++ len); +++ return; +++ } +++ +++ xprt_get(xprt); +++ state = READ_ONCE(xprt->state); +++ xprt_put(xprt); +++ +++ for (i = 0; i < ARRAY_SIZE(xprt_mask); ++i) { +++ if (pos >= len) +++ break; +++ +++ if (!test_bit(xprt_mask[i], &state)) +++ continue; +++ +++ if (pos == 0) +++ ret = snprintf(buf, len, "%s", xprt_state_desc[i]); +++ else +++ ret = snprintf(buf + pos, len - pos, "|%s", +++ xprt_state_desc[i]); +++ +++ if (ret < 0) { +++ enfs_log_error("format state failed, ret %d.\n", ret); +++ break; +++ } +++ +++ pos += ret; +++ } +++} ++diff --git a/fs/nfs/enfs/pm_state.h b/fs/nfs/enfs/pm_state.h ++new file mode 100644 ++index 000000000000..f5f52e5ab91d ++--- /dev/null +++++ b/fs/nfs/enfs/pm_state.h ++@@ -0,0 +1,28 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: path state header file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++ +++#ifndef PM_STATE_H +++#define PM_STATE_H +++ +++#include <linux/types.h> +++#include <linux/sunrpc/xprt.h> +++ +++enum pm_path_state { +++ PM_STATE_INIT, +++ PM_STATE_NORMAL, +++ PM_STATE_FAULT, +++ PM_STATE_UNDEFINED // xprt is not multipath xprt +++}; +++ +++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state); +++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt); +++ +++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len); +++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len); +++ +++#endif // PM_STATE_H +diff --git a/0006-add_enfs_compile_option.patch b/0006-add_enfs_compile_option.patch +new file mode 100644 +index 0000000..ff3bc0e +--- /dev/null ++++ b/0006-add_enfs_compile_option.patch +@@ -0,0 +1,70 @@ ++diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig ++index b04256636d4b..ae53510c0627 100644 ++--- a/arch/arm64/configs/openeuler_defconfig +++++ b/arch/arm64/configs/openeuler_defconfig ++@@ -5344,6 +5344,7 @@ CONFIG_LOCKD=m ++ CONFIG_LOCKD_V4=y ++ CONFIG_NFS_ACL_SUPPORT=m ++ CONFIG_NFS_COMMON=y +++# CONFIG_ENFS is not set ++ CONFIG_SUNRPC=m ++ CONFIG_SUNRPC_GSS=m ++ CONFIG_SUNRPC_BACKCHANNEL=y ++diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig ++index 59baeb2973af..ccc317f7fdb2 100644 ++--- a/arch/x86/configs/openeuler_defconfig +++++ b/arch/x86/configs/openeuler_defconfig ++@@ -6825,6 +6825,7 @@ CONFIG_LOCKD=m ++ CONFIG_LOCKD_V4=y ++ CONFIG_NFS_ACL_SUPPORT=m ++ CONFIG_NFS_COMMON=y +++# CONFIG_ENFS is not set ++ CONFIG_SUNRPC=m ++ CONFIG_SUNRPC_GSS=m ++ CONFIG_SUNRPC_BACKCHANNEL=y ++diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig ++index e55f86713948..872c9b7671b1 100644 ++--- a/fs/nfs/Kconfig +++++ b/fs/nfs/Kconfig ++@@ -196,3 +196,14 @@ config NFS_DEBUG ++ depends on NFS_FS && SUNRPC_DEBUG ++ select CRC32 ++ default y +++ +++config ENFS +++ tristate "NFS client support for ENFS" +++ depends on NFS_FS +++ default n +++ help +++ This option enables support multipath of the NFS protocol +++ in the kernel's NFS client. +++ This feature will improve performance and reliability. +++ +++ If sure, say Y. ++diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile ++index c587e3c4c6a6..19d0ac2ba3b8 100644 ++--- a/fs/nfs/Makefile +++++ b/fs/nfs/Makefile ++@@ -12,6 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ ++ nfs-$(CONFIG_ROOT_NFS) += nfsroot.o ++ nfs-$(CONFIG_SYSCTL) += sysctl.o ++ nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o +++nfs-$(CONFIG_ENFS) += enfs_adapter.o ++ ++ obj-$(CONFIG_NFS_V2) += nfsv2.o ++ nfsv2-y := nfs2super.o proc.o nfs2xdr.o ++@@ -34,3 +35,5 @@ nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o ++ obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ ++ obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ ++ obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ +++ +++obj-$(CONFIG_ENFS) += enfs/ ++diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile ++index 090658c3da12..fe4e3b28c5d1 100644 ++--- a/net/sunrpc/Makefile +++++ b/net/sunrpc/Makefile ++@@ -19,3 +19,4 @@ sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o ++ sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o ++ sunrpc-$(CONFIG_PROC_FS) += stats.o ++ sunrpc-$(CONFIG_SYSCTL) += sysctl.o +++sunrpc-$(CONFIG_ENFS) += sunrpc_enfs_adapter.o +diff --git a/kernel.spec b/kernel.spec +index 3215446..e242c00 100644 +--- a/kernel.spec ++++ b/kernel.spec +@@ -60,6 +60,13 @@ Source9002: series.conf + Source9998: patches.tar.bz2 + %endif + ++Patch0001: 0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch ++Patch0002: 0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch ++Patch0003: 0003-add_enfs_module.patch ++Patch0004: 0004-add_enfs_module_for_sunrpc_multipatch.patch ++Patch0005: 0005-add_enfs_module_for_sunrpc_failover_and_configure.patch ++Patch0006: 0006-add_enfs_compile_option.patch ++ + #BuildRequires: + BuildRequires: module-init-tools, patch >= 2.5.4, bash >= 2.03, tar + BuildRequires: bzip2, xz, findutils, gzip, m4, perl, make >= 3.78, diffutils, gawk +@@ -256,6 +263,12 @@ Applypatches() + Applypatches series.conf %{_builddir}/kernel-%{version}/linux-%{KernelVer} + %endif + ++%patch0001 -p1 ++%patch0002 -p1 ++%patch0003 -p1 ++%patch0004 -p1 ++%patch0005 -p1 ++%patch0006 -p1 + touch .scmversion + + find . $ -name "*.orig" -o -name "*~" $ -exec rm -f {} \; >/dev/null +-- +2.25.0.windows.1 + diff --git a/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch new file mode 100644 index 0000000..38e57a9 --- /dev/null +++ b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch @@ -0,0 +1,757 @@ +diff --git a/fs/nfs/client.c b/fs/nfs/client.c +index 7d02dc52209d..50820a8a684a 100644 +--- a/fs/nfs/client.c ++++ b/fs/nfs/client.c +@@ -48,7 +48,7 @@ + #include "callback.h" + #include "delegation.h" + #include "iostat.h" +-#include "internal.h" ++#include "enfs_adapter.h" + #include "fscache.h" + #include "pnfs.h" + #include "nfs.h" +@@ -255,6 +255,7 @@ void nfs_free_client(struct nfs_client *clp) + put_nfs_version(clp->cl_nfs_mod); + kfree(clp->cl_hostname); + kfree(clp->cl_acceptor); ++ nfs_free_multi_path_client(clp); + kfree(clp); + } + EXPORT_SYMBOL_GPL(nfs_free_client); +@@ -330,6 +331,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat + sap)) + continue; + ++ if (!nfs_multipath_client_match(clp, data)) ++ continue; ++ + refcount_inc(&clp->cl_count); + return clp; + } +@@ -512,6 +516,9 @@ int nfs_create_rpc_client(struct nfs_client *clp, + .program = &nfs_program, + .version = clp->rpc_ops->version, + .authflavor = flavor, ++#if IS_ENABLED(CONFIG_ENFS) ++ .multipath_option = cl_init->enfs_option, ++#endif + }; + + if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) +@@ -634,6 +641,13 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp, + /* the client is already initialised */ + if (clp->cl_cons_state == NFS_CS_READY) + return clp; ++ error = nfs_create_multi_path_client(clp, cl_init); ++ if (error < 0) { ++ dprintk("%s: create failed.%d!\n", __func__, error); ++ nfs_put_client(clp); ++ clp = ERR_PTR(error); ++ return clp; ++ } + + /* + * Create a client RPC handle for doing FSSTAT with UNIX auth only +@@ -666,6 +680,9 @@ static int nfs_init_server(struct nfs_server *server, + .net = data->net, + .timeparms = &timeparms, + .init_flags = (1UL << NFS_CS_REUSEPORT), ++#if IS_ENABLED(CONFIG_ENFS) ++ .enfs_option = data->enfs_option, ++#endif + }; + struct nfs_client *clp; + int error; +diff --git a/fs/nfs/enfs_adapter.c b/fs/nfs/enfs_adapter.c +new file mode 100644 +index 000000000000..7f471f2072c4 +--- /dev/null ++++ b/fs/nfs/enfs_adapter.c +@@ -0,0 +1,230 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs3.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/sunrpc/sched.h> ++#include <linux/nfs_iostat.h> ++#include "enfs_adapter.h" ++#include "iostat.h" ++ ++struct enfs_adapter_ops __rcu *enfs_adapter; ++ ++int enfs_adapter_register(struct enfs_adapter_ops *ops) ++{ ++ struct enfs_adapter_ops *old; ++ ++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, NULL, ops); ++ if (old == NULL || old == ops) ++ return 0; ++ pr_err("regist %s ops %p failed. old %p\n", __func__, ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(enfs_adapter_register); ++ ++int enfs_adapter_unregister(struct enfs_adapter_ops *ops) ++{ ++ struct enfs_adapter_ops *old; ++ ++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, ops, NULL); ++ if (old == ops || old == NULL) ++ return 0; ++ pr_err("unregist %s ops %p failed. old %p\n", __func__, ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(enfs_adapter_unregister); ++ ++struct enfs_adapter_ops *nfs_multipath_router_get(void) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ rcu_read_lock(); ++ ops = rcu_dereference(enfs_adapter); ++ if (ops == NULL) { ++ rcu_read_unlock(); ++ return NULL; ++ } ++ if (!try_module_get(ops->owner)) ++ ops = NULL; ++ rcu_read_unlock(); ++ return ops; ++} ++ ++void nfs_multipath_router_put(struct enfs_adapter_ops *ops) ++{ ++ if (ops) ++ module_put(ops->owner); ++} ++ ++bool is_valid_option(enum nfsmultipathoptions option) ++{ ++ if (option < REMOTEADDR || option >= INVALID_OPTION) { ++ pr_warn("%s: ENFS invalid option %d\n", __func__, option); ++ return false; ++ } ++ ++ return true; ++} ++ ++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, ++ struct nfs_parsed_mount_data *mnt) ++{ ++ ++ //parseMultiPathOptions(getNfsMultiPathOpt(token), string, mnt); ++ ++ int rc; ++ struct enfs_adapter_ops *ops; ++ ++ ops = nfs_multipath_router_get(); ++ if ((ops == NULL) || (ops->parse_mount_options == NULL) || ++ !is_valid_option(option)) { ++ nfs_multipath_router_put(ops); ++ dfprintk(MOUNT, ++ "NFS: parsing nfs mount option enfs not load[%s]\n" ++ , __func__); ++ return -EOPNOTSUPP; ++ } ++ // nfs_multipath_parse_options ++ dfprintk(MOUNT, "NFS: parsing nfs mount option '%s' type: %d[%s]\n" ++ , str, option, __func__); ++ rc = ops->parse_mount_options(option, str, &mnt->enfs_option, mnt->net); ++ nfs_multipath_router_put(ops); ++ return rc; ++} ++ ++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ if (data->enfs_option == NULL) ++ return; ++ ++ ops = nfs_multipath_router_get(); ++ if ((ops == NULL) || (ops->free_mount_options == NULL)) { ++ nfs_multipath_router_put(ops); ++ return; ++ } ++ ops->free_mount_options((void *)&data->enfs_option); ++ nfs_multipath_router_put(ops); ++} ++ ++int nfs_create_multi_path_client(struct nfs_client *client, ++ const struct nfs_client_initdata *cl_init) ++{ ++ int ret = 0; ++ struct enfs_adapter_ops *ops; ++ ++ if (cl_init->enfs_option == NULL) ++ return 0; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_init != NULL) ++ ret = ops->client_info_init( ++ (void *)&client->cl_multipath_data, cl_init); ++ nfs_multipath_router_put(ops); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(nfs_create_multi_path_client); ++ ++void nfs_free_multi_path_client(struct nfs_client *clp) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ if (clp->cl_multipath_data == NULL) ++ return; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_free != NULL) ++ ops->client_info_free(clp->cl_multipath_data); ++ nfs_multipath_router_put(ops); ++} ++ ++int nfs_multipath_client_match(struct nfs_client *clp, ++ const struct nfs_client_initdata *sap) ++{ ++ int ret = true; ++ struct enfs_adapter_ops *ops; ++ ++ pr_info("%s src %p dst %p\n.", __func__, ++ clp->cl_multipath_data, sap->enfs_option); ++ ++ if (clp->cl_multipath_data == NULL && sap->enfs_option == NULL) ++ return true; ++ ++ if ((clp->cl_multipath_data == NULL && sap->enfs_option) || ++ (clp->cl_multipath_data && sap->enfs_option == NULL)) { ++ pr_err("not match client src %p dst %p\n.", ++ clp->cl_multipath_data, sap->enfs_option); ++ return false; ++ } ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_match != NULL) ++ ret = ops->client_info_match(clp->cl_multipath_data, ++ sap->enfs_option); ++ nfs_multipath_router_put(ops); ++ ++ return ret; ++} ++ ++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst) ++{ ++ int ret = true; ++ struct enfs_adapter_ops *ops; ++ ++ if (src->cl_multipath_data == NULL && dst->cl_multipath_data == NULL) ++ return true; ++ ++ if (src->cl_multipath_data == NULL || dst->cl_multipath_data == NULL) ++ return false; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->nfs4_client_info_match != NULL) ++ ret = ops->nfs4_client_info_match(src->cl_multipath_data, ++ src->cl_multipath_data); ++ nfs_multipath_router_put(ops); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(nfs4_multipath_client_match); ++ ++void nfs_multipath_show_client_info(struct seq_file *mount_option, ++ struct nfs_server *server) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ if (mount_option == NULL || server == NULL || ++ server->client == NULL || ++ server->nfs_client->cl_multipath_data == NULL) ++ return; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_show != NULL) ++ ops->client_info_show(mount_option, server); ++ nfs_multipath_router_put(ops); ++} ++ ++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) ++{ ++ int ret = 0; ++ struct enfs_adapter_ops *ops; ++ ++ if (nfs_client == NULL || nfs_client->cl_rpcclient == NULL) ++ return 0; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->remount_ip_list != NULL) ++ ret = ops->remount_ip_list(nfs_client, enfs_option); ++ nfs_multipath_router_put(ops); ++ return ret; ++} ++EXPORT_SYMBOL_GPL(nfs_remount_iplist); +diff --git a/fs/nfs/enfs_adapter.h b/fs/nfs/enfs_adapter.h +new file mode 100644 +index 000000000000..752544e18056 +--- /dev/null ++++ b/fs/nfs/enfs_adapter.h +@@ -0,0 +1,101 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapt header. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _NFS_MULTIPATH_H_ ++#define _NFS_MULTIPATH_H_ ++ ++#include "internal.h" ++ ++#if IS_ENABLED(CONFIG_ENFS) ++enum nfsmultipathoptions { ++ REMOTEADDR, ++ LOCALADDR, ++ REMOTEDNSNAME, ++ REMOUNTREMOTEADDR, ++ REMOUNTLOCALADDR, ++ INVALID_OPTION ++}; ++ ++ ++struct enfs_adapter_ops { ++ const char *name; ++ struct module *owner; ++ int (*parse_mount_options)(enum nfsmultipathoptions option, ++ char *str, void **enfs_option, struct net *net_ns); ++ ++ void (*free_mount_options)(void **data); ++ ++ int (*client_info_init)(void **data, ++ const struct nfs_client_initdata *cl_init); ++ void (*client_info_free)(void *data); ++ int (*client_info_match)(void *src, void *dst); ++ int (*nfs4_client_info_match)(void *src, void *dst); ++ void (*client_info_show)(struct seq_file *mount_option, void *data); ++ int (*remount_ip_list)(struct nfs_client *nfs_client, ++ void *enfs_option); ++}; ++ ++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, ++ struct nfs_parsed_mount_data *mnt); ++void enfs_free_mount_options(struct nfs_parsed_mount_data *data); ++int nfs_create_multi_path_client(struct nfs_client *client, ++ const struct nfs_client_initdata *cl_init); ++void nfs_free_multi_path_client(struct nfs_client *clp); ++int nfs_multipath_client_match(struct nfs_client *clp, ++ const struct nfs_client_initdata *sap); ++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst); ++void nfs_multipath_show_client_info(struct seq_file *mount_option, ++ struct nfs_server *server); ++int enfs_adapter_register(struct enfs_adapter_ops *ops); ++int enfs_adapter_unregister(struct enfs_adapter_ops *ops); ++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); ++int nfs4_create_multi_path(struct nfs_server *server, ++ struct nfs_parsed_mount_data *data, ++ const struct rpc_timeout *timeparms); ++ ++#else ++static inline ++void nfs_free_multi_path_client(struct nfs_client *clp) ++{ ++ ++} ++ ++static inline ++int nfs_multipath_client_match(struct nfs_client *clp, ++ const struct nfs_client_initdata *sap) ++{ ++ return 1; ++} ++ ++static inline ++int nfs_create_multi_path_client(struct nfs_client *client, ++ const struct nfs_client_initdata *cl_init) ++{ ++ return 0; ++} ++ ++static inline ++void nfs_multipath_show_client_info(struct seq_file *mount_option, ++ struct nfs_server *server) ++{ ++ ++} ++ ++static inline ++int nfs4_multipath_client_match(struct nfs_client *src, ++ struct nfs_client *dst) ++{ ++ return 1; ++} ++ ++static inline ++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) ++{ ++ ++} ++ ++#endif // CONFIG_ENFS ++#endif // _NFS_MULTIPATH_H_ +diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h +index 0ce5a90640c4..c696693edc7b 100644 +--- a/fs/nfs/internal.h ++++ b/fs/nfs/internal.h +@@ -93,6 +93,9 @@ struct nfs_client_initdata { + u32 minorversion; + struct net *net; + const struct rpc_timeout *timeparms; ++#if IS_ENABLED(CONFIG_ENFS) ++ void *enfs_option; /* struct multipath_mount_options * */ ++#endif + }; + + /* +@@ -135,6 +138,9 @@ struct nfs_parsed_mount_data { + + struct security_mnt_opts lsm_opts; + struct net *net; ++#if IS_ENABLED(CONFIG_ENFS) ++ void *enfs_option; /* struct multipath_mount_options * */ ++#endif + }; + + /* mount_clnt.c */ +diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c +index 1350ea673672..4aa6e1f961f7 100644 +--- a/fs/nfs/nfs4client.c ++++ b/fs/nfs/nfs4client.c +@@ -10,7 +10,7 @@ + #include <linux/sunrpc/xprt.h> + #include <linux/sunrpc/bc_xprt.h> + #include <linux/sunrpc/rpc_pipe_fs.h> +-#include "internal.h" ++#include "enfs_adapter.h" + #include "callback.h" + #include "delegation.h" + #include "nfs4session.h" +@@ -225,6 +225,16 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); + ++#if IS_ENABLED(CONFIG_ENFS) ++ err = nfs_create_multi_path_client(clp, cl_init); ++ if (err < 0) { ++ dprintk("%s: create failed.%d\n", __func__, err); ++ nfs_put_client(clp); ++ clp = ERR_PTR(err); ++ return clp; ++ } ++#endif ++ + /* + * Set up the connection to the server before we add add to the + * global list. +@@ -529,6 +539,9 @@ static int nfs4_match_client(struct nfs_client *pos, struct nfs_client *new, + if (!nfs4_match_client_owner_id(pos, new)) + return 1; + ++ if (!nfs4_multipath_client_match(pos, new)) ++ return 1; ++ + return 0; + } + +@@ -860,7 +873,7 @@ static int nfs4_set_client(struct nfs_server *server, + const size_t addrlen, + const char *ip_addr, + int proto, const struct rpc_timeout *timeparms, +- u32 minorversion, struct net *net) ++ u32 minorversion, struct net *net, void *enfs_option) + { + struct nfs_client_initdata cl_init = { + .hostname = hostname, +@@ -872,6 +885,9 @@ static int nfs4_set_client(struct nfs_server *server, + .minorversion = minorversion, + .net = net, + .timeparms = timeparms, ++#if IS_ENABLED(CONFIG_ENFS) ++ .enfs_option = enfs_option, ++#endif + }; + struct nfs_client *clp; + +@@ -1042,6 +1058,30 @@ static int nfs4_server_common_setup(struct nfs_server *server, + return error; + } + ++int nfs4_create_multi_path(struct nfs_server *server, ++ struct nfs_parsed_mount_data *data, ++ const struct rpc_timeout *timeparms) ++{ ++ struct nfs_client_initdata cl_init = { ++ .hostname = data->nfs_server.hostname, ++ .addr = (const struct sockaddr *)&data->nfs_server.address, ++ .addrlen = data->nfs_server.addrlen, ++ .ip_addr = data->client_address, ++ .nfs_mod = &nfs_v4, ++ .proto = data->nfs_server.protocol, ++ .minorversion = data->minorversion, ++ .net = data->net, ++ .timeparms = timeparms, ++#if IS_ENABLED(CONFIG_ENFS) ++ .enfs_option = data->enfs_option, ++#endif // CONFIG_ENFS ++ }; ++ ++ return nfs_create_multi_path_client(server->nfs_client, &cl_init); ++ ++} ++EXPORT_SYMBOL_GPL(nfs4_create_multi_path); ++ + /* + * Create a version 4 volume record + */ +@@ -1050,6 +1090,7 @@ static int nfs4_init_server(struct nfs_server *server, + { + struct rpc_timeout timeparms; + int error; ++ void *enfs_option = NULL; + + nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, + data->timeo, data->retrans); +@@ -1067,6 +1108,10 @@ static int nfs4_init_server(struct nfs_server *server, + else + data->selected_flavor = RPC_AUTH_UNIX; + ++#if IS_ENABLED(CONFIG_ENFS) ++ enfs_option = data->enfs_option; ++#endif ++ + /* Get a client record */ + error = nfs4_set_client(server, + data->nfs_server.hostname, +@@ -1076,7 +1121,7 @@ static int nfs4_init_server(struct nfs_server *server, + data->nfs_server.protocol, + &timeparms, + data->minorversion, +- data->net); ++ data->net, enfs_option); + if (error < 0) + return error; + +@@ -1161,7 +1206,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, + XPRT_TRANSPORT_RDMA, + parent_server->client->cl_timeout, + parent_client->cl_mvops->minor_version, +- parent_client->cl_net); ++ parent_client->cl_net, NULL); + if (!error) + goto init_server; + #endif /* IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) */ +@@ -1174,7 +1219,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, + XPRT_TRANSPORT_TCP, + parent_server->client->cl_timeout, + parent_client->cl_mvops->minor_version, +- parent_client->cl_net); ++ parent_client->cl_net, NULL); + if (error < 0) + goto error; + +@@ -1269,7 +1314,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, + set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); + error = nfs4_set_client(server, hostname, sap, salen, buf, + clp->cl_proto, clnt->cl_timeout, +- clp->cl_minorversion, net); ++ clp->cl_minorversion, net, NULL); + clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); + if (error != 0) { + nfs_server_insert_lists(server); +diff --git a/fs/nfs/super.c b/fs/nfs/super.c +index a05e1eb2c3fd..83cd294aca15 100644 +--- a/fs/nfs/super.c ++++ b/fs/nfs/super.c +@@ -61,7 +61,7 @@ + #include "callback.h" + #include "delegation.h" + #include "iostat.h" +-#include "internal.h" ++#include "enfs_adapter.h" + #include "fscache.h" + #include "nfs4session.h" + #include "pnfs.h" +@@ -113,6 +113,12 @@ enum { + + /* Special mount options */ + Opt_userspace, Opt_deprecated, Opt_sloppy, ++#if IS_ENABLED(CONFIG_ENFS) ++ Opt_remote_iplist, ++ Opt_local_iplist, ++ Opt_remote_dnslist, ++ Opt_enfs_info, ++#endif + + Opt_err + }; +@@ -183,6 +189,13 @@ static const match_table_t nfs_mount_option_tokens = { + { Opt_fscache_uniq, "fsc=%s" }, + { Opt_local_lock, "local_lock=%s" }, + ++#if IS_ENABLED(CONFIG_ENFS) ++ { Opt_remote_iplist, "remoteaddrs=%s" }, ++ { Opt_local_iplist, "localaddrs=%s" }, ++ { Opt_remote_dnslist, "remotednsname=%s" }, ++ { Opt_enfs_info, "enfs_info=%s" }, ++#endif ++ + /* The following needs to be listed after all other options */ + { Opt_nfsvers, "v%s" }, + +@@ -365,6 +378,21 @@ static struct shrinker acl_shrinker = { + .seeks = DEFAULT_SEEKS, + }; + ++#if IS_ENABLED(CONFIG_ENFS) ++enum nfsmultipathoptions getNfsMultiPathOpt(int token) ++{ ++ switch (token) { ++ case Opt_remote_iplist: ++ return REMOUNTREMOTEADDR; ++ case Opt_local_iplist: ++ return REMOUNTLOCALADDR; ++ case Opt_remote_dnslist: ++ return REMOTEDNSNAME; ++ } ++ return INVALID_OPTION; ++} ++#endif ++ + /* + * Register the NFS filesystems + */ +@@ -758,6 +786,9 @@ int nfs_show_options(struct seq_file *m, struct dentry *root) + seq_printf(m, ",addr=%s", + rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient, + RPC_DISPLAY_ADDR)); ++ ++ nfs_multipath_show_client_info(m, nfss); ++ + rcu_read_unlock(); + + return 0; +@@ -853,6 +884,8 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) + seq_puts(m, root->d_sb->s_flags & SB_NODIRATIME ? ",nodiratime" : ""); + nfs_show_mount_options(m, nfss, 1); + ++ nfs_multipath_show_client_info(m, nfss); ++ + seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); + + show_implementation_id(m, nfss); +@@ -977,6 +1010,7 @@ static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data) + kfree(data->nfs_server.export_path); + kfree(data->nfs_server.hostname); + kfree(data->fscache_uniq); ++ enfs_free_mount_options(data); + security_free_mnt_opts(&data->lsm_opts); + kfree(data); + } +@@ -1641,7 +1675,34 @@ static int nfs_parse_mount_options(char *raw, + return 0; + }; + break; +- ++#if IS_ENABLED(CONFIG_ENFS) ++ case Opt_remote_iplist: ++ case Opt_local_iplist: ++ case Opt_remote_dnslist: ++ string = match_strdup(args); ++ if (string == NULL) ++ goto out_nomem; ++ rc = enfs_parse_mount_options(getNfsMultiPathOpt(token), ++ string, mnt); ++ kfree(string); ++ switch (rc) { ++ case 0: ++ break; ++ case -ENOMEM: ++ goto out_nomem; ++ case -ENOSPC: ++ goto out_limit; ++ case -EINVAL: ++ goto out_invalid_address; ++ case -ENOTSUPP: ++ goto out_invalid_address; ++ case -EOPNOTSUPP: ++ goto out_invalid_address; ++ } ++ break; ++ case Opt_enfs_info: ++ break; ++#endif + /* + * Special options + */ +@@ -1720,6 +1781,11 @@ static int nfs_parse_mount_options(char *raw, + free_secdata(secdata); + printk(KERN_INFO "NFS: security options invalid: %d\n", rc); + return 0; ++#if IS_ENABLED(CONFIG_ENFS) ++out_limit: ++ dprintk("NFS: param is more than supported limit: %d\n", rc); ++ return 0; ++#endif + } + + /* +@@ -2335,6 +2401,14 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) + if (!nfs_parse_mount_options((char *)options, data)) + goto out; + ++#if IS_ENABLED(CONFIG_ENFS) ++ if (data->enfs_option) { ++ error = nfs_remount_iplist(nfss->nfs_client, data->enfs_option); ++ if (error) ++ goto out; ++ } ++#endif ++ + /* + * noac is a special case. It implies -o sync, but that's not + * necessarily reflected in the mtab options. do_remount_sb +@@ -2347,6 +2421,11 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) + /* compare new mount options with old ones */ + error = nfs_compare_remount_data(nfss, data); + out: ++#if IS_ENABLED(CONFIG_ENFS) ++ /* release remount option member */ ++ if (data->enfs_option) ++ enfs_free_mount_options(data); ++#endif + nfs_free_parsed_mount_data(data); + return error; + } +diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h +index 7023ae64e3d7..2c19678afe8d 100644 +--- a/include/linux/nfs_fs_sb.h ++++ b/include/linux/nfs_fs_sb.h +@@ -123,6 +123,11 @@ struct nfs_client { + + struct net *cl_net; + struct list_head pending_cb_stateids; ++ ++#if IS_ENABLED(CONFIG_ENFS) ++ /* multi path private structure (struct multipath_client_info *) */ ++ void *cl_multipath_data; ++#endif + }; + + /* diff --git a/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch new file mode 100644 index 0000000..540a2ce --- /dev/null +++ b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch @@ -0,0 +1,805 @@ +diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h +index 8aa865bce4f6..89178f78de8c 100644 +--- a/include/linux/sunrpc/clnt.h ++++ b/include/linux/sunrpc/clnt.h +@@ -70,6 +70,10 @@ struct rpc_clnt { + struct dentry *cl_debugfs; /* debugfs directory */ + #endif + struct rpc_xprt_iter cl_xpi; ++ ++#if IS_ENABLED(CONFIG_ENFS) ++ bool cl_enfs; ++#endif + }; + + /* +@@ -124,6 +128,9 @@ struct rpc_create_args { + unsigned long flags; + char *client_name; + struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ ++#if IS_ENABLED(CONFIG_ENFS) ++ void *multipath_option; ++#endif + }; + + struct rpc_add_xprt_test { +@@ -221,6 +228,12 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, + const struct sockaddr *sap); + void rpc_cleanup_clids(void); + ++#if IS_ENABLED(CONFIG_ENFS) ++int ++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, ++ const struct rpc_call_ops *ops, void *data, int flags); ++#endif /* CONFIG_ENFS */ ++ + static inline int rpc_reply_expected(struct rpc_task *task) + { + return (task->tk_msg.rpc_proc != NULL) && +diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h +index ad2e243f3f03..124f5a0faf3e 100644 +--- a/include/linux/sunrpc/sched.h ++++ b/include/linux/sunrpc/sched.h +@@ -90,6 +90,9 @@ struct rpc_task { + tk_garb_retry : 2, + tk_cred_retry : 2, + tk_rebind_retry : 2; ++#if IS_ENABLED(CONFIG_ENFS) ++ unsigned long tk_major_timeo; /* major timeout ticks */ ++#endif + }; + + typedef void (*rpc_action)(struct rpc_task *); +@@ -118,6 +121,9 @@ struct rpc_task_setup { + */ + #define RPC_TASK_ASYNC 0x0001 /* is an async task */ + #define RPC_TASK_SWAPPER 0x0002 /* is swapping in/out */ ++#if IS_ENABLED(CONFIG_ENFS) ++#define RPC_TASK_FIXED 0x0004 /* detect xprt status task */ ++#endif + #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ + #define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ + #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ +@@ -257,6 +263,9 @@ void rpc_destroy_mempool(void); + extern struct workqueue_struct *rpciod_workqueue; + extern struct workqueue_struct *xprtiod_workqueue; + void rpc_prepare_task(struct rpc_task *task); ++#if IS_ENABLED(CONFIG_ENFS) ++void rpc_init_task_retry_counters(struct rpc_task *task); ++#endif + + static inline int rpc_wait_for_completion_task(struct rpc_task *task) + { +diff --git a/include/linux/sunrpc/sunrpc_enfs_adapter.h b/include/linux/sunrpc/sunrpc_enfs_adapter.h +new file mode 100644 +index 000000000000..28abedcf5cf6 +--- /dev/null ++++ b/include/linux/sunrpc/sunrpc_enfs_adapter.h +@@ -0,0 +1,128 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* Client-side SUNRPC ENFS adapter header. ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _SUNRPC_ENFS_ADAPTER_H_ ++#define _SUNRPC_ENFS_ADAPTER_H_ ++#include <linux/sunrpc/clnt.h> ++ ++#if IS_ENABLED(CONFIG_ENFS) ++ ++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) ++{ ++ xps->xps_nactive--; ++} ++ ++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) ++{ ++ xps->xps_nactive--; ++} ++ ++struct rpc_xprt *rpc_task_get_xprt ++(struct rpc_clnt *clnt, struct rpc_xprt *xprt); ++ ++struct rpc_multipath_ops { ++ struct module *owner; ++ void (*create_clnt)(struct rpc_create_args *args, ++ struct rpc_clnt *clnt); ++ void (*releas_clnt)(struct rpc_clnt *clnt); ++ void (*create_xprt)(struct rpc_xprt *xprt); ++ void (*destroy_xprt)(struct rpc_xprt *xprt); ++ void (*xprt_iostat)(struct rpc_task *task); ++ void (*failover_handle)(struct rpc_task *task); ++ bool (*task_need_call_start_again)(struct rpc_task *task); ++ void (*adjust_task_timeout)(struct rpc_task *task, void *condition); ++ void (*init_task_req)(struct rpc_task *task, struct rpc_rqst *req); ++ bool (*prepare_transmit)(struct rpc_task *task); ++}; ++ ++extern struct rpc_multipath_ops __rcu *multipath_ops; ++void rpc_init_task_retry_counters(struct rpc_task *task); ++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops); ++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops); ++struct rpc_multipath_ops *rpc_multipath_ops_get(void); ++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops); ++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); ++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, ++ struct rpc_clnt *clnt); ++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt); ++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt); ++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt); ++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task); ++void rpc_multipath_ops_failover_handle(struct rpc_task *task); ++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task); ++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, ++ void *condition); ++void rpc_multipath_ops_init_task_req(struct rpc_task *task, ++ struct rpc_rqst *req); ++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task); ++ ++#else ++static inline struct rpc_xprt *rpc_task_get_xprt(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt) ++{ ++ return NULL; ++} ++ ++static inline void rpc_task_release_xprt(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt) ++{ ++} ++ ++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) ++{ ++} ++ ++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) ++{ ++} ++ ++static inline void rpc_multipath_ops_create_clnt ++(struct rpc_create_args *args, struct rpc_clnt *clnt) ++{ ++} ++ ++static inline void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) ++{ ++} ++ ++static inline bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) ++{ ++ return false; ++} ++ ++static inline void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) ++{ ++} ++ ++static inline void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) ++{ ++} ++ ++static inline void rpc_multipath_ops_failover_handle(struct rpc_task *task) ++{ ++} ++ ++static inline ++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) ++{ ++ return false; ++} ++ ++static inline void ++rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, void *condition) ++{ ++} ++ ++static inline void ++rpc_multipath_ops_init_task_req(struct rpc_task *task, struct rpc_rqst *req) ++{ ++} ++ ++static inline bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) ++{ ++ return false; ++} ++ ++#endif ++#endif // _SUNRPC_ENFS_ADAPTER_H_ +diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h +index ccfacca1eba9..2e47b3577947 100644 +--- a/include/linux/sunrpc/xprt.h ++++ b/include/linux/sunrpc/xprt.h +@@ -279,6 +279,10 @@ struct rpc_xprt { + atomic_t inject_disconnect; + #endif + struct rcu_head rcu; ++#if IS_ENABLED(CONFIG_ENFS) ++ atomic_long_t queuelen; ++ void *multipath_context; ++#endif + }; + + #if defined(CONFIG_SUNRPC_BACKCHANNEL) +diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h +index af1257c030d2..d54e4dbbbf34 100644 +--- a/include/linux/sunrpc/xprtmultipath.h ++++ b/include/linux/sunrpc/xprtmultipath.h +@@ -22,6 +22,10 @@ struct rpc_xprt_switch { + const struct rpc_xprt_iter_ops *xps_iter_ops; + + struct rcu_head xps_rcu; ++#if IS_ENABLED(CONFIG_ENFS) ++ unsigned int xps_nactive; ++ atomic_long_t xps_queuelen; ++#endif + }; + + struct rpc_xprt_iter { +@@ -69,4 +73,8 @@ extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); + + extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap); ++#if IS_ENABLED(CONFIG_ENFS) ++extern void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++ struct rpc_xprt *xprt); ++#endif + #endif +diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c +index 0fc540b0d183..d7ffee637148 100644 +--- a/net/sunrpc/clnt.c ++++ b/net/sunrpc/clnt.c +@@ -37,6 +37,7 @@ + #include <linux/sunrpc/rpc_pipe_fs.h> + #include <linux/sunrpc/metrics.h> + #include <linux/sunrpc/bc_xprt.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + #include <trace/events/sunrpc.h> + + #include "sunrpc.h" +@@ -490,6 +491,8 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, + } + } + ++ rpc_multipath_ops_create_clnt(args, clnt); ++ + clnt->cl_softrtry = 1; + if (args->flags & RPC_CLNT_CREATE_HARDRTRY) + clnt->cl_softrtry = 0; +@@ -869,6 +872,8 @@ void rpc_shutdown_client(struct rpc_clnt *clnt) + list_empty(&clnt->cl_tasks), 1*HZ); + } + ++ rpc_multipath_ops_releas_clnt(clnt); ++ + rpc_release_client(clnt); + } + EXPORT_SYMBOL_GPL(rpc_shutdown_client); +@@ -981,7 +986,13 @@ void rpc_task_release_transport(struct rpc_task *task) + + if (xprt) { + task->tk_xprt = NULL; +- xprt_put(xprt); ++#if IS_ENABLED(CONFIG_ENFS) ++ if (task->tk_client) { ++ rpc_task_release_xprt(task->tk_client, xprt); ++ return; ++ } ++#endif ++ xprt_put(xprt); + } + } + EXPORT_SYMBOL_GPL(rpc_task_release_transport); +@@ -990,6 +1001,10 @@ void rpc_task_release_client(struct rpc_task *task) + { + struct rpc_clnt *clnt = task->tk_client; + ++#if IS_ENABLED(CONFIG_ENFS) ++ rpc_task_release_transport(task); ++#endif ++ + if (clnt != NULL) { + /* Remove from client task list */ + spin_lock(&clnt->cl_lock); +@@ -999,14 +1014,29 @@ void rpc_task_release_client(struct rpc_task *task) + + rpc_release_client(clnt); + } ++#if IS_ENABLED(CONFIG_ENFS) ++#else + rpc_task_release_transport(task); ++#endif + } + ++#if IS_ENABLED(CONFIG_ENFS) ++static struct rpc_xprt * ++rpc_task_get_next_xprt(struct rpc_clnt *clnt) ++{ ++ return rpc_task_get_xprt(clnt, xprt_iter_get_next(&clnt->cl_xpi)); ++} ++#endif ++ + static + void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) + { + if (!task->tk_xprt) ++#if IS_ENABLED(CONFIG_ENFS) ++ task->tk_xprt = rpc_task_get_next_xprt(clnt); ++#else + task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); ++#endif + } + + static +@@ -1597,6 +1627,14 @@ call_reserveresult(struct rpc_task *task) + return; + case -EIO: /* probably a shutdown */ + break; ++#if IS_ENABLED(CONFIG_ENFS) ++ case -ETIMEDOUT: /* woken up; restart */ ++ if (rpc_multipath_ops_task_need_call_start_again(task)) { ++ rpc_task_release_transport(task); ++ task->tk_action = call_start; ++ return; ++ } ++#endif + default: + printk(KERN_ERR "%s: unrecognized error %d, exiting\n", + __func__, status); +@@ -1962,6 +2000,10 @@ call_transmit(struct rpc_task *task) + return; + if (!xprt_prepare_transmit(task)) + return; ++ ++ if (rpc_multipath_ops_prepare_transmit(task)) ++ return; ++ + task->tk_action = call_transmit_status; + /* Encode here so that rpcsec_gss can use correct sequence number. */ + if (rpc_task_need_encode(task)) { +@@ -2277,6 +2319,9 @@ call_timeout(struct rpc_task *task) + + retry: + task->tk_action = call_bind; ++#if IS_ENABLED(CONFIG_ENFS) ++ rpc_multipath_ops_failover_handle(task); ++#endif + task->tk_status = 0; + } + +@@ -2961,3 +3006,30 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) + } + EXPORT_SYMBOL_GPL(rpc_clnt_swap_deactivate); + #endif /* CONFIG_SUNRPC_SWAP */ ++ ++#if IS_ENABLED(CONFIG_ENFS) ++/* rpc_clnt_test_xprt - Test and add a new transport to a rpc_clnt ++ * @clnt: pointer to struct rpc_clnt ++ * @xprt: pointer struct rpc_xprt ++ * @ops: async operation ++ */ ++int ++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, ++ const struct rpc_call_ops *ops, void *data, int flags) ++{ ++ struct rpc_cred *cred; ++ struct rpc_task *task; ++ ++ cred = authnull_ops.lookup_cred(NULL, NULL, 0); ++ task = rpc_call_null_helper(clnt, xprt, cred, ++ RPC_TASK_SOFT | RPC_TASK_SOFTCONN | flags, ++ ops, data); ++ put_rpccred(cred); ++ if (IS_ERR(task)) ++ return PTR_ERR(task); ++ ++ rpc_put_task(task); ++ return 1; ++} ++EXPORT_SYMBOL_GPL(rpc_clnt_test_xprt); ++#endif +diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c +index a873c92a4898..2254fea0e863 100644 +--- a/net/sunrpc/sched.c ++++ b/net/sunrpc/sched.c +@@ -20,7 +20,7 @@ + #include <linux/mutex.h> + #include <linux/freezer.h> + +-#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + + #include "sunrpc.h" + +@@ -962,7 +962,12 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta + /* Initialize workqueue for async tasks */ + task->tk_workqueue = task_setup_data->workqueue; + ++#if IS_ENABLED(CONFIG_ENFS) ++ task->tk_xprt = rpc_task_get_xprt(task_setup_data->rpc_client, ++ xprt_get(task_setup_data->rpc_xprt)); ++#else + task->tk_xprt = xprt_get(task_setup_data->rpc_xprt); ++#endif + + if (task->tk_ops->rpc_call_prepare != NULL) + task->tk_action = rpc_prepare_task; +diff --git a/net/sunrpc/sunrpc_enfs_adapter.c b/net/sunrpc/sunrpc_enfs_adapter.c +new file mode 100644 +index 000000000000..c1543545c6de +--- /dev/null ++++ b/net/sunrpc/sunrpc_enfs_adapter.c +@@ -0,0 +1,214 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* Client-side SUNRPC ENFS adapter header. ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ ++struct rpc_multipath_ops __rcu *multipath_ops; ++ ++void rpc_init_task_retry_counters(struct rpc_task *task) ++{ ++ /* Initialize retry counters */ ++ task->tk_garb_retry = 2; ++ task->tk_cred_retry = 2; ++ task->tk_rebind_retry = 2; ++} ++EXPORT_SYMBOL_GPL(rpc_init_task_retry_counters); ++ ++struct rpc_xprt * ++rpc_task_get_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) ++{ ++ struct rpc_xprt_switch *xps; ++ ++ if (!xprt) ++ return NULL; ++ rcu_read_lock(); ++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ++ atomic_long_inc(&xps->xps_queuelen); ++ rcu_read_unlock(); ++ atomic_long_inc(&xprt->queuelen); ++ ++ return xprt; ++} ++ ++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops) ++{ ++ struct rpc_multipath_ops *old; ++ ++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, NULL, ops); ++ if (!old || old == ops) ++ return 0; ++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_register); ++ ++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops) ++{ ++ struct rpc_multipath_ops *old; ++ ++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, ops, NULL); ++ if (!old || old == ops) ++ return 0; ++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_unregister); ++ ++struct rpc_multipath_ops *rpc_multipath_ops_get(void) ++{ ++ struct rpc_multipath_ops *ops; ++ ++ rcu_read_lock(); ++ ops = rcu_dereference(multipath_ops); ++ if (!ops) { ++ rcu_read_unlock(); ++ return NULL; ++ } ++ if (!try_module_get(ops->owner)) ++ ops = NULL; ++ rcu_read_unlock(); ++ return ops; ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_get); ++ ++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops) ++{ ++ if (ops) ++ module_put(ops->owner); ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_put); ++ ++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) ++{ ++ struct rpc_xprt_switch *xps; ++ ++ atomic_long_dec(&xprt->queuelen); ++ rcu_read_lock(); ++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ++ atomic_long_dec(&xps->xps_queuelen); ++ rcu_read_unlock(); ++ ++ xprt_put(xprt); ++} ++ ++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, ++ struct rpc_clnt *clnt) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ if (args->multipath_option) { ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->create_clnt) ++ mops->create_clnt(args, clnt); ++ rpc_multipath_ops_put(mops); ++ } ++} ++ ++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->releas_clnt) ++ mops->releas_clnt(clnt); ++ ++ rpc_multipath_ops_put(mops); ++} ++ ++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->create_xprt) { ++ mops->create_xprt(xprt); ++ if (!xprt->multipath_context) { ++ rpc_multipath_ops_put(mops); ++ return true; ++ } ++ } ++ rpc_multipath_ops_put(mops); ++ return false; ++} ++ ++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ if (xprt->multipath_context) { ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->destroy_xprt) ++ mops->destroy_xprt(xprt); ++ rpc_multipath_ops_put(mops); ++ } ++} ++ ++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ mops = rpc_multipath_ops_get(); ++ if (task->tk_client && mops && mops->xprt_iostat) ++ mops->xprt_iostat(task); ++ rpc_multipath_ops_put(mops); ++} ++ ++void rpc_multipath_ops_failover_handle(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mpath_ops = NULL; ++ ++ mpath_ops = rpc_multipath_ops_get(); ++ if (mpath_ops && mpath_ops->failover_handle) ++ mpath_ops->failover_handle(task); ++ rpc_multipath_ops_put(mpath_ops); ++} ++ ++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mpath_ops = NULL; ++ bool ret = false; ++ ++ mpath_ops = rpc_multipath_ops_get(); ++ if (mpath_ops && mpath_ops->task_need_call_start_again) ++ ret = mpath_ops->task_need_call_start_again(task); ++ rpc_multipath_ops_put(mpath_ops); ++ return ret; ++} ++ ++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, ++ void *condition) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->adjust_task_timeout) ++ mops->adjust_task_timeout(task, NULL); ++ rpc_multipath_ops_put(mops); ++} ++ ++void rpc_multipath_ops_init_task_req(struct rpc_task *task, ++ struct rpc_rqst *req) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->init_task_req) ++ mops->init_task_req(task, req); ++ rpc_multipath_ops_put(mops); ++} ++ ++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->prepare_transmit) { ++ if (!(mops->prepare_transmit(task))) { ++ rpc_multipath_ops_put(mops); ++ return true; ++ } ++ } ++ rpc_multipath_ops_put(mops); ++ return false; ++} +diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c +index c912bf20faa2..c2b63b3d5217 100644 +--- a/net/sunrpc/xprt.c ++++ b/net/sunrpc/xprt.c +@@ -48,6 +48,7 @@ + #include <linux/sunrpc/clnt.h> + #include <linux/sunrpc/metrics.h> + #include <linux/sunrpc/bc_xprt.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + #include <linux/rcupdate.h> + + #include <trace/events/sunrpc.h> +@@ -259,6 +260,9 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) + dprintk("RPC: %5u failed to lock transport %p\n", + task->tk_pid, xprt); + task->tk_timeout = 0; ++ ++ rpc_multipath_ops_adjust_task_timeout(task, NULL); ++ + task->tk_status = -EAGAIN; + if (req == NULL) + priority = RPC_PRIORITY_LOW; +@@ -560,6 +564,9 @@ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action) + struct rpc_xprt *xprt = req->rq_xprt; + + task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0; ++ ++ rpc_multipath_ops_adjust_task_timeout(task, NULL); ++ + rpc_sleep_on(&xprt->pending, task, action); + } + EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space); +@@ -1347,6 +1354,9 @@ xprt_request_init(struct rpc_task *task) + req->rq_rcv_buf.buflen = 0; + req->rq_release_snd_buf = NULL; + xprt_reset_majortimeo(req); ++ ++ rpc_multipath_ops_init_task_req(task, req); ++ + dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, + req, ntohl(req->rq_xid)); + } +@@ -1427,6 +1437,9 @@ void xprt_release(struct rpc_task *task) + task->tk_ops->rpc_count_stats(task, task->tk_calldata); + else if (task->tk_client) + rpc_count_iostats(task, task->tk_client->cl_metrics); ++ ++ rpc_multipath_ops_xprt_iostat(task); ++ + spin_lock(&xprt->recv_lock); + if (!list_empty(&req->rq_list)) { + list_del_init(&req->rq_list); +@@ -1455,6 +1468,7 @@ void xprt_release(struct rpc_task *task) + else + xprt_free_bc_request(req); + } ++EXPORT_SYMBOL_GPL(xprt_release); + + static void xprt_init(struct rpc_xprt *xprt, struct net *net) + { +@@ -1528,6 +1542,10 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) + return ERR_PTR(-ENOMEM); + } + ++if (rpc_multipath_ops_create_xprt(xprt)) { ++ xprt_destroy(xprt); ++ return ERR_PTR(-ENOMEM); ++} + rpc_xprt_debugfs_register(xprt); + + dprintk("RPC: created transport %p with %u slots\n", xprt, +@@ -1547,6 +1565,9 @@ static void xprt_destroy_cb(struct work_struct *work) + rpc_destroy_wait_queue(&xprt->sending); + rpc_destroy_wait_queue(&xprt->backlog); + kfree(xprt->servername); ++ ++ rpc_multipath_ops_destroy_xprt(xprt); ++ + /* + * Tear down transport state and free the rpc_xprt + */ +diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c +index 6ebaa58b4eff..6202a0be1327 100644 +--- a/net/sunrpc/xprtmultipath.c ++++ b/net/sunrpc/xprtmultipath.c +@@ -18,6 +18,7 @@ + #include <linux/sunrpc/xprt.h> + #include <linux/sunrpc/addr.h> + #include <linux/sunrpc/xprtmultipath.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + + typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct list_head *head, + const struct rpc_xprt *cur); +@@ -26,8 +27,8 @@ static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular; + static const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin; + static const struct rpc_xprt_iter_ops rpc_xprt_iter_listall; + +-static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, +- struct rpc_xprt *xprt) ++void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++ struct rpc_xprt *xprt) + { + if (unlikely(xprt_get(xprt) == NULL)) + return; +@@ -36,7 +37,9 @@ static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, + if (xps->xps_nxprts == 0) + xps->xps_net = xprt->xprt_net; + xps->xps_nxprts++; ++ rpc_xps_nactive_add_one(xps); + } ++EXPORT_SYMBOL(xprt_switch_add_xprt_locked); + + /** + * rpc_xprt_switch_add_xprt - Add a new rpc_xprt to an rpc_xprt_switch +@@ -63,6 +66,7 @@ static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps, + if (unlikely(xprt == NULL)) + return; + xps->xps_nxprts--; ++ rpc_xps_nactive_sub_one(xps); + if (xps->xps_nxprts == 0) + xps->xps_net = NULL; + smp_wmb(); +@@ -84,7 +88,7 @@ void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, + spin_unlock(&xps->xps_lock); + xprt_put(xprt); + } +- ++EXPORT_SYMBOL(rpc_xprt_switch_remove_xprt); + /** + * xprt_switch_alloc - Allocate a new struct rpc_xprt_switch + * @xprt: pointer to struct rpc_xprt +@@ -102,7 +106,13 @@ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, + if (xps != NULL) { + spin_lock_init(&xps->xps_lock); + kref_init(&xps->xps_kref); ++#if IS_ENABLED(CONFIG_ENFS) ++ xps->xps_nxprts = 0; ++ xps->xps_nactive = 0; ++ atomic_long_set(&xps->xps_queuelen, 0); ++#else + xps->xps_nxprts = 0; ++#endif + INIT_LIST_HEAD(&xps->xps_xprt_list); + xps->xps_iter_ops = &rpc_xprt_iter_singular; + xprt_switch_add_xprt_locked(xps, xprt); +@@ -148,6 +158,7 @@ struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps) + return xps; + return NULL; + } ++EXPORT_SYMBOL(xprt_switch_get); + + /** + * xprt_switch_put - Release a reference to a rpc_xprt_switch +@@ -160,6 +171,7 @@ void xprt_switch_put(struct rpc_xprt_switch *xps) + if (xps != NULL) + kref_put(&xps->xps_kref, xprt_switch_free); + } ++EXPORT_SYMBOL(xprt_switch_put); + + /** + * rpc_xprt_switch_set_roundrobin - Set a round-robin policy on rpc_xprt_switch diff --git a/0003-add_enfs_module_for_nfs_mount_option.patch b/0003-add_enfs_module_for_nfs_mount_option.patch new file mode 100644 index 0000000..70753b5 --- /dev/null +++ b/0003-add_enfs_module_for_nfs_mount_option.patch @@ -0,0 +1,1209 @@ +diff --git a/fs/nfs/enfs/Makefile b/fs/nfs/enfs/Makefile +new file mode 100644 +index 000000000000..6e83eb23c668 +--- /dev/null ++++ b/fs/nfs/enfs/Makefile +@@ -0,0 +1,18 @@ ++obj-m += enfs.o ++ ++#EXTRA_CFLAGS += -I$(PWD)/.. ++ ++enfs-y := enfs_init.o ++enfs-y += enfs_config.o ++enfs-y += mgmt_init.o ++enfs-y += enfs_multipath_client.o ++enfs-y += enfs_multipath_parse.o ++enfs-y += failover_path.o ++enfs-y += failover_time.o ++enfs-y += enfs_roundrobin.o ++enfs-y += enfs_multipath.o ++enfs-y += enfs_path.o ++enfs-y += enfs_proc.o ++enfs-y += enfs_remount.o ++enfs-y += pm_ping.o ++enfs-y += pm_state.o +diff --git a/fs/nfs/enfs/enfs.h b/fs/nfs/enfs/enfs.h +new file mode 100644 +index 000000000000..be3d95220088 +--- /dev/null ++++ b/fs/nfs/enfs/enfs.h +@@ -0,0 +1,62 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS multipath adapt header. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++ ++#ifndef _ENFS_H_ ++#define _ENFS_H_ ++#include <linux/atomic.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs3.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include "../enfs_adapter.h" ++ ++#define IP_ADDRESS_LEN_MAX 64 ++#define MAX_IP_PAIR_PER_MOUNT 8 ++#define MAX_IP_INDEX (MAX_IP_PAIR_PER_MOUNT) ++#define MAX_SUPPORTED_LOCAL_IP_COUNT 8 ++#define MAX_SUPPORTED_REMOTE_IP_COUNT 32 ++#define MAX_DNS_NAME_LEN 512 ++#define MAX_DNS_SUPPORTED 2 ++#define EXTEND_CMD_MAX_BUF_LEN 65356 ++ ++ ++struct nfs_ip_list { ++ int count; ++ struct sockaddr_storage address[MAX_SUPPORTED_REMOTE_IP_COUNT]; ++ size_t addrlen[MAX_SUPPORTED_REMOTE_IP_COUNT]; ++}; ++ ++struct NFS_ROUTE_DNS_S { ++ char dnsname[MAX_DNS_NAME_LEN]; // valid only if dnsExist is true ++}; ++ ++struct NFS_ROUTE_DNS_INFO_S { ++ int dnsNameCount; // Count of DNS name in the list ++ // valid only if dnsExist is true ++ struct NFS_ROUTE_DNS_S routeRemoteDnsList[MAX_DNS_SUPPORTED]; ++}; ++ ++struct rpc_iostats; ++struct enfs_xprt_context { ++ struct sockaddr_storage srcaddr; ++ struct rpc_iostats *stats; ++ bool main; ++ atomic_t path_state; ++ atomic_t path_check_state; ++}; ++ ++static inline bool enfs_is_main_xprt(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = xprt->multipath_context; ++ ++ if (!ctx) ++ return false; ++ return ctx->main; ++} ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_init.c b/fs/nfs/enfs/enfs_init.c +new file mode 100644 +index 000000000000..4b55608191a7 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_init.c +@@ -0,0 +1,98 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/module.h> ++#include <linux/sunrpc/sched.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs3.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include "enfs.h" ++#include "enfs_multipath_parse.h" ++#include "enfs_multipath_client.h" ++#include "enfs_remount.h" ++#include "init.h" ++#include "enfs_log.h" ++#include "enfs_multipath.h" ++#include "mgmt_init.h" ++ ++struct enfs_adapter_ops enfs_adapter = { ++ .name = "enfs", ++ .owner = THIS_MODULE, ++ .parse_mount_options = nfs_multipath_parse_options, ++ .free_mount_options = nfs_multipath_free_options, ++ .client_info_init = nfs_multipath_client_info_init, ++ .client_info_free = nfs_multipath_client_info_free, ++ .client_info_match = nfs_multipath_client_info_match, ++ .client_info_show = nfs_multipath_client_info_show, ++ .remount_ip_list = enfs_remount_iplist, ++}; ++ ++int32_t enfs_init(void) ++{ ++ int err; ++ ++ err = enfs_multipath_init(); ++ if (err) { ++ enfs_log_error("init multipath failed.\n"); ++ goto out; ++ } ++ ++ err = mgmt_init(); ++ if (err != 0) { ++ enfs_log_error("init mgmt failed.\n"); ++ goto out_tp_exit; ++ } ++ ++ return 0; ++ ++out_tp_exit: ++ enfs_multipath_exit(); ++out: ++ return err; ++} ++ ++void enfs_fini(void) ++{ ++ mgmt_fini(); ++ ++ enfs_multipath_exit(); ++} ++ ++static int __init init_enfs(void) ++{ ++ int ret; ++ ++ ret = enfs_adapter_register(&enfs_adapter); ++ if (ret) { ++ pr_err("regist enfs_adapter fail. ret %d\n", ret); ++ return -1; ++ } ++ ++ ret = enfs_init(); ++ if (ret) { ++ enfs_adapter_unregister(&enfs_adapter); ++ return -1; ++ } ++ ++ return 0; ++} ++ ++static void __exit exit_enfs(void) ++{ ++ enfs_fini(); ++ enfs_adapter_unregister(&enfs_adapter); ++} ++ ++MODULE_LICENSE("GPL"); ++MODULE_AUTHOR("Huawei Tech. Co., Ltd."); ++MODULE_DESCRIPTION("Nfs client router"); ++MODULE_VERSION("1.0"); ++ ++module_init(init_enfs); ++module_exit(exit_enfs); +diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c +new file mode 100644 +index 000000000000..63c02898a42c +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.c +@@ -0,0 +1,340 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/proc_fs.h> ++#include <linux/seq_file.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/addr.h> ++#include "enfs_multipath_client.h" ++#include "enfs_multipath_parse.h" ++ ++int ++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, ++ const struct nfs_client_initdata *client_init_data) ++{ ++ struct multipath_mount_options *mount_options = ++ (struct multipath_mount_options *)client_init_data->enfs_option; ++ ++ if (mount_options->local_ip_list) { ++ client_info->local_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->local_ip_list) ++ return -ENOMEM; ++ ++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->remote_ip_list) { ++ ++ client_info->remote_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->remote_ip_list) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->remote_ip_list, ++ mount_options->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->pRemoteDnsInfo) { ++ client_info->pRemoteDnsInfo = ++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); ++ ++ if (!client_info->pRemoteDnsInfo) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ kfree(client_info->remote_ip_list); ++ client_info->remote_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->pRemoteDnsInfo, ++ mount_options->pRemoteDnsInfo, ++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); ++ } ++ return 0; ++} ++ ++void nfs_multipath_client_info_free_work(struct work_struct *work) ++{ ++ ++ struct multipath_client_info *clp_info; ++ ++ if (work == NULL) ++ return; ++ ++ clp_info = container_of(work, struct multipath_client_info, work); ++ ++ if (clp_info->local_ip_list != NULL) { ++ kfree(clp_info->local_ip_list); ++ clp_info->local_ip_list = NULL; ++ } ++ if (clp_info->remote_ip_list != NULL) { ++ kfree(clp_info->remote_ip_list); ++ clp_info->remote_ip_list = NULL; ++ } ++ kfree(clp_info); ++} ++ ++void nfs_multipath_client_info_free(void *data) ++{ ++ struct multipath_client_info *clp_info = ++ (struct multipath_client_info *)data; ++ ++ if (clp_info == NULL) ++ return; ++ pr_info("free client info %p.\n", clp_info); ++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); ++ schedule_work(&clp_info->work); ++} ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init) ++{ ++ int rc; ++ struct multipath_client_info *info; ++ struct multipath_client_info **enfs_info; ++ /* no multi path info, no need do multipath init */ ++ if (cl_init->enfs_option == NULL) ++ return 0; ++ enfs_info = (struct multipath_client_info **)data; ++ if (enfs_info == NULL) ++ return -EINVAL; ++ ++ if (*enfs_info == NULL) ++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), ++ GFP_KERNEL); ++ ++ if (*enfs_info == NULL) ++ return -ENOMEM; ++ ++ info = (struct multipath_client_info *)*enfs_info; ++ pr_info("init client info %p.\n", info); ++ rc = nfs_multipath_client_mount_info_init(info, cl_init); ++ if (rc) { ++ nfs_multipath_client_info_free((void *)info); ++ return rc; ++ } ++ return rc; ++} ++ ++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, ++ const struct nfs_ip_list *ip_list_dst) ++{ ++ int i; ++ int j; ++ bool is_find; ++ /* if both are equal or NULL, then return true. */ ++ if (ip_list_src == ip_list_dst) ++ return true; ++ ++ if ((ip_list_src == NULL || ip_list_dst == NULL)) ++ return false; ++ ++ if (ip_list_src->count != ip_list_dst->count) ++ return false; ++ ++ for (i = 0; i < ip_list_src->count; i++) { ++ is_find = false; ++ for (j = 0; j < ip_list_src->count; j++) { ++ if (rpc_cmp_addr_port( ++ (const struct sockaddr *) ++ &ip_list_src->address[i], ++ (const struct sockaddr *) ++ &ip_list_dst->address[j]) ++ ) { ++ is_find = true; ++ break; ++ } ++ } ++ if (is_find == false) ++ return false; ++ } ++ return true; ++} ++ ++int ++nfs_multipath_dns_list_info_match( ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) ++{ ++ int i; ++ ++ /* if both are equal or NULL, then return true. */ ++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) ++ return true; ++ ++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) ++ return false; ++ ++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) ++ return false; ++ ++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { ++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, ++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) ++ return false; ++ } ++ return true; ++} ++ ++int nfs_multipath_client_info_match(void *src, void *dst) ++{ ++ int ret = true; ++ ++ struct multipath_client_info *src_info; ++ struct multipath_mount_options *dst_info; ++ ++ src_info = (struct multipath_client_info *)src; ++ dst_info = (struct multipath_mount_options *)dst; ++ pr_info("try match client .\n"); ++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, ++ dst_info->local_ip_list); ++ if (ret == false) { ++ pr_err("local_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, ++ dst_info->remote_ip_list); ++ if (ret == false) { ++ pr_err("remote_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, ++ dst_info->pRemoteDnsInfo); ++ if (ret == false) { ++ pr_err("dns not match.\n"); ++ return ret; ++ } ++ pr_info("try match client ret %d.\n", ret); ++ return ret; ++} ++ ++void nfs_multipath_print_ip_info(struct seq_file *mount_option, ++ struct nfs_ip_list *ip_list, ++ const char *type) ++{ ++ char buf[IP_ADDRESS_LEN_MAX + 1]; ++ int len = 0; ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < ip_list->count; i++) { ++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], ++ buf, IP_ADDRESS_LEN_MAX); ++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) ++ buf[len] = '\0'; ++ ++ if (i == 0) ++ seq_printf(mount_option, "%s", buf); ++ else ++ seq_printf(mount_option, "~%s", buf); ++ dfprintk(MOUNT, ++ "NFS: show nfs mount option type:%s %s [%s]\n", ++ type, buf, __func__); ++ } ++} ++ ++void nfs_multipath_print_dns_info(struct seq_file *mount_option, ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, ++ const char *type) ++{ ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { ++ if (i == 0) ++ seq_printf(mount_option, ++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) ++ seq_printf(mount_option, ",%s]", ++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else ++ seq_printf(mount_option, ++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ } ++} ++ ++ ++static void multipath_print_sockaddr(struct seq_file *seq, ++ struct sockaddr *addr) ++{ ++ switch (addr->sa_family) { ++ case AF_INET: { ++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; ++ ++ seq_printf(seq, "%pI4", &sin->sin_addr); ++ return; ++ } ++ case AF_INET6: { ++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; ++ ++ seq_printf(seq, "%pI6", &sin6->sin6_addr); ++ return; ++ } ++ default: ++ break; ++ } ++ pr_err("unsupport family:%d\n", addr->sa_family); ++} ++ ++static void multipath_print_enfs_info(struct seq_file *seq, ++ struct nfs_server *server) ++{ ++ struct sockaddr_storage peeraddr; ++ struct rpc_clnt *next = server->client; ++ ++ rpc_peeraddr(server->client, ++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); ++ seq_puts(seq, ",enfs_info="); ++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); ++ ++ while (next->cl_parent) { ++ if (next == next->cl_parent) ++ break; ++ next = next->cl_parent; ++ } ++ seq_printf(seq, "_%u", next->cl_clid); ++} ++ ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) ++{ ++ struct nfs_server *server = data; ++ struct multipath_client_info *client_info = ++ server->nfs_client->cl_multipath_data; ++ ++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); ++ if ((client_info->remote_ip_list) && ++ (client_info->remote_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->remote_ip_list, ++ "remoteaddrs"); ++ ++ if ((client_info->local_ip_list) && ++ (client_info->local_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->local_ip_list, ++ "localaddrs"); ++ ++ if ((client_info->pRemoteDnsInfo) && ++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) ++ nfs_multipath_print_dns_info(mount_option, ++ client_info->pRemoteDnsInfo, ++ "remotednsname"); ++ ++ multipath_print_enfs_info(mount_option, server); ++} +diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h +new file mode 100644 +index 000000000000..208f7260690d +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.h +@@ -0,0 +1,26 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _ENFS_MULTIPATH_CLIENT_H_ ++#define _ENFS_MULTIPATH_CLIENT_H_ ++ ++#include "enfs.h" ++ ++struct multipath_client_info { ++ struct work_struct work; ++ struct nfs_ip_list *remote_ip_list; ++ struct nfs_ip_list *local_ip_list; ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; ++ s64 client_id; ++}; ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init); ++void nfs_multipath_client_info_free(void *data); ++int nfs_multipath_client_info_match(void *src, void *dst); ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_multipath_parse.c b/fs/nfs/enfs/enfs_multipath_parse.c +new file mode 100644 +index 000000000000..9c4c6c1880b6 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_parse.c +@@ -0,0 +1,601 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/parser.h> ++#include <linux/kern_levels.h> ++#include <linux/sunrpc/addr.h> ++#include "enfs_multipath_parse.h" ++#include "enfs_log.h" ++ ++#define NFSDBG_FACILITY NFSDBG_CLIENT ++ ++void nfs_multipath_parse_ip_ipv6_add(struct sockaddr_in6 *sin6, int add_num) ++{ ++ int i; ++ ++ pr_info("NFS: before %08x%08x%08x%08x add_num: %d[%s]\n", ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), ++ add_num, __func__); ++ for (i = 0; i < add_num; i++) { ++ sin6->sin6_addr.in6_u.u6_addr32[3] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[3] != 0) ++ continue; ++ ++ sin6->sin6_addr.in6_u.u6_addr32[2] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[2] != 0) ++ continue; ++ ++ sin6->sin6_addr.in6_u.u6_addr32[1] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[1] != 0) ++ continue; ++ ++ sin6->sin6_addr.in6_u.u6_addr32[0] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[0] != 0) ++ continue; ++ } ++ ++ return; ++ ++} ++ ++static int nfs_multipath_parse_ip_range(struct net *net_ns, const char *cursor, ++ struct nfs_ip_list *ip_list, enum nfsmultipathoptions type) ++{ ++ struct sockaddr_storage addr; ++ struct sockaddr_storage tmp_addr; ++ int i; ++ size_t len; ++ int add_num = 1; ++ bool duplicate_flag = false; ++ bool is_complete = false; ++ struct sockaddr_in *sin4; ++ struct sockaddr_in6 *sin6; ++ ++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", ++ cursor, type, __func__); ++ len = rpc_pton(net_ns, cursor, strlen(cursor), ++ (struct sockaddr *)&addr, sizeof(addr)); ++ if (!len) ++ return -EINVAL; ++ ++ if (addr.ss_family != ip_list->address[ip_list->count - 1].ss_family) { ++ pr_info("NFS: %s parsing nfs mount option type: %d fail.\n", ++ __func__, type); ++ return -EINVAL; ++ } ++ ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &ip_list->address[ip_list->count - 1], ++ (const struct sockaddr *)&addr)) { ++ ++ pr_info("range ip is same ip.\n"); ++ return 0; ++ ++ } ++ ++ while (true) { ++ ++ tmp_addr = ip_list->address[ip_list->count - 1]; ++ ++ switch (addr.ss_family) { ++ case AF_INET: ++ sin4 = (struct sockaddr_in *)&tmp_addr; ++ ++ sin4->sin_addr.s_addr = ++ htonl(ntohl(sin4->sin_addr.s_addr) + add_num); ++ ++ pr_info("NFS: mount option ip%08x type: %d ipcont %d [%s]\n", ++ ntohl(sin4->sin_addr.s_addr), ++ type, ip_list->count, __func__); ++ break; ++ case AF_INET6: ++ sin6 = (struct sockaddr_in6 *)&tmp_addr; ++ nfs_multipath_parse_ip_ipv6_add(sin6, add_num); ++ pr_info("NFS: mount option ip %08x%08x%08x%08x type: %d ipcont %d [%s]\n", ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), ++ type, ip_list->count, __func__); ++ break; ++ // return -EOPNOTSUPP; ++ default: ++ return -EOPNOTSUPP; ++ } ++ ++ if (rpc_cmp_addr((const struct sockaddr *)&tmp_addr, ++ (const struct sockaddr *)&addr)) { ++ is_complete = true; ++ } ++ // delete duplicate ip, continuosly repeat, skip it ++ for (i = 0; i < ip_list->count; i++) { ++ duplicate_flag = false; ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &ip_list->address[i], ++ (const struct sockaddr *)&tmp_addr)) { ++ add_num++; ++ duplicate_flag = true; ++ break; ++ } ++ } ++ ++ if (duplicate_flag == false) { ++ pr_info("this ip not duplicate;"); ++ add_num = 1; ++ // if not repeat but omit limit return false ++ if ((type == LOCALADDR && ++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || ++ (type == REMOTEADDR && ++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { ++ ++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", ++ __func__, type, ip_list->count, ++ type == LOCALADDR ? ++ MAX_SUPPORTED_LOCAL_IP_COUNT : ++ MAX_SUPPORTED_REMOTE_IP_COUNT); ++ ip_list->count = 0; ++ return -ENOSPC; ++ } ++ ip_list->address[ip_list->count] = tmp_addr; ++ ++ ip_list->addrlen[ip_list->count] = ++ ip_list->addrlen[ip_list->count - 1]; ++ ++ ip_list->count += 1; ++ } ++ if (is_complete == true) ++ break; ++ } ++ return 0; ++} ++ ++int nfs_multipath_parse_ip_list_inter(struct nfs_ip_list *ip_list, ++ struct net *net_ns, ++ char *cursor, enum nfsmultipathoptions type) ++{ ++ int i = 0; ++ struct sockaddr_storage addr; ++ struct sockaddr_storage swap; ++ int len; ++ ++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", ++ cursor, type, __func__); ++ ++ len = rpc_pton(net_ns, cursor, ++ strlen(cursor), ++ (struct sockaddr *)&addr, sizeof(addr)); ++ if (!len) ++ return -EINVAL; ++ ++ // check repeated ip ++ for (i = 0; i < ip_list->count; i++) { ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &ip_list->address[i], ++ (const struct sockaddr *)&addr)) { ++ ++ pr_info("NFS: mount option '%s' type:%d index %d same as before index %d [%s]\n", ++ cursor, type, ip_list->count, i, __func__); ++ // prevent this ip is beginning ++ // if repeated take it to the end of list ++ swap = ip_list->address[i]; ++ ++ ip_list->address[i] = ++ ip_list->address[ip_list->count-1]; ++ ++ ip_list->address[ip_list->count-1] = swap; ++ return 0; ++ } ++ } ++ // if not repeated, check exceed limit ++ if ((type == LOCALADDR && ++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || ++ (type == REMOTEADDR && ++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { ++ ++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", ++ __func__, type, ip_list->count, ++ type == LOCALADDR ? ++ MAX_SUPPORTED_LOCAL_IP_COUNT : ++ MAX_SUPPORTED_REMOTE_IP_COUNT); ++ ++ ip_list->count = 0; ++ return -ENOSPC; ++ } ++ ip_list->address[ip_list->count] = addr; ++ ip_list->addrlen[ip_list->count] = len; ++ ip_list->count++; ++ ++ return 0; ++} ++ ++char *nfs_multipath_parse_ip_list_get_cursor(char **buf_to_parse, bool *single) ++{ ++ char *cursor = NULL; ++ const char *single_sep = strchr(*buf_to_parse, '~'); ++ const char *range_sep = strchr(*buf_to_parse, '-'); ++ ++ *single = true; ++ if (range_sep) { ++ if (range_sep > single_sep) { // A-B or A~B-C ++ if (single_sep == NULL) { // A-B ++ cursor = strsep(buf_to_parse, "-"); ++ if (cursor) ++ *single = false; ++ } else// A~B-C ++ cursor = strsep(buf_to_parse, "~"); ++ } else { // A-B~C ++ cursor = strsep(buf_to_parse, "-"); ++ if (cursor) ++ *single = false; ++ } ++ } else { // A~B~C ++ cursor = strsep(buf_to_parse, "~"); ++ } ++ return cursor; ++} ++ ++bool nfs_multipath_parse_param_check(enum nfsmultipathoptions type, ++ struct multipath_mount_options *options) ++{ ++ if (type == REMOUNTREMOTEADDR && options->remote_ip_list->count != 0) { ++ memset(options->remote_ip_list, 0, sizeof(struct nfs_ip_list)); ++ return true; ++ } ++ if (type == REMOUNTLOCALADDR && options->local_ip_list->count != 0) { ++ memset(options->local_ip_list, 0, sizeof(struct nfs_ip_list)); ++ return true; ++ } ++ if ((type == REMOTEADDR || type == REMOTEDNSNAME) && ++ options->pRemoteDnsInfo->dnsNameCount != 0) { ++ ++ pr_info("[MULTIPATH:%s] parse for %d ,already have dns\n", ++ __func__, type); ++ return false; ++ } else if ((type == REMOTEADDR || type == REMOTEDNSNAME) && ++ options->remote_ip_list->count != 0) { ++ ++ pr_info("[MULTIPATH:%s] parse for %d ,already have iplist\n", ++ __func__, type); ++ return false; ++ } ++ return true; ++} ++ ++int nfs_multipath_parse_ip_list(char *buffer, struct net *net_ns, ++ struct multipath_mount_options *options, ++ enum nfsmultipathoptions type) ++{ ++ char *buf_to_parse = NULL; ++ bool prev_range = false; ++ int ret = 0; ++ char *cursor = NULL; ++ bool single = true; ++ struct nfs_ip_list *ip_list_tmp = NULL; ++ ++ if (!nfs_multipath_parse_param_check(type, options)) ++ return -ENOTSUPP; ++ ++ if (type == REMOUNTREMOTEADDR) ++ type = REMOTEADDR; ++ ++ if (type == REMOUNTLOCALADDR) ++ type = LOCALADDR; ++ ++ if (type == LOCALADDR) ++ ip_list_tmp = options->local_ip_list; ++ else ++ ip_list_tmp = options->remote_ip_list; ++ ++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", ++ buffer, type, __func__); ++ ++ buf_to_parse = buffer; ++ while (buf_to_parse != NULL) { ++ cursor = ++ nfs_multipath_parse_ip_list_get_cursor(&buf_to_parse, &single); ++ if (!cursor) ++ break; ++ ++ if (single == false && prev_range == true) { ++ pr_info("NFS: mount option type: %d fail. Multiple Range.[%s]\n", ++ type, __func__); ++ ++ ret = -EINVAL; ++ goto out; ++ } ++ ++ if (prev_range == false) { ++ ret = nfs_multipath_parse_ip_list_inter(ip_list_tmp, ++ net_ns, cursor, type); ++ if (ret) ++ goto out; ++ if (single == false) ++ prev_range = true; ++ } else { ++ ret = nfs_multipath_parse_ip_range(net_ns, cursor, ++ ip_list_tmp, type); ++ if (ret != 0) ++ goto out; ++ prev_range = false; ++ } ++ } ++ ++out: ++ if (ret) ++ memset(ip_list_tmp, 0, sizeof(struct nfs_ip_list)); ++ ++ return ret; ++} ++ ++int nfs_multipath_parse_dns_list(char *buffer, struct net *net_ns, ++ struct multipath_mount_options *options) ++{ ++ struct NFS_ROUTE_DNS_INFO_S *dns_name_list_tmp = NULL; ++ char *cursor = NULL; ++ char *bufToParse; ++ ++ if (!nfs_multipath_parse_param_check(REMOTEDNSNAME, options)) ++ return -ENOTSUPP; ++ ++ pr_info("[MULTIPATH:%s] buffer %s\n", __func__, buffer); ++ // freed in nfs_free_parsed_mount_data ++ dns_name_list_tmp = kmalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), ++ GFP_KERNEL); ++ if (!dns_name_list_tmp) ++ return -ENOMEM; ++ ++ dns_name_list_tmp->dnsNameCount = 0; ++ bufToParse = buffer; ++ while (bufToParse) { ++ if (dns_name_list_tmp->dnsNameCount >= MAX_DNS_SUPPORTED) { ++ pr_err("%s: dnsname for %s reached %d,more than supported limit %d\n", ++ __func__, cursor, ++ dns_name_list_tmp->dnsNameCount, ++ MAX_DNS_SUPPORTED); ++ dns_name_list_tmp->dnsNameCount = 0; ++ return -ENOSPC; ++ } ++ cursor = strsep(&bufToParse, "~"); ++ if (!cursor) ++ break; ++ ++ strcpy(dns_name_list_tmp->routeRemoteDnsList ++ [dns_name_list_tmp->dnsNameCount].dnsname, ++ cursor); ++ dns_name_list_tmp->dnsNameCount++; ++ } ++ if (dns_name_list_tmp->dnsNameCount == 0) ++ return -EINVAL; ++ options->pRemoteDnsInfo = dns_name_list_tmp; ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check_ipv4_valid(struct sockaddr_in *addr) ++{ ++ if (addr->sin_addr.s_addr == 0 || addr->sin_addr.s_addr == 0xffffffff) ++ return -EINVAL; ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check_ipv6_valid(struct sockaddr_in6 *addr) ++{ ++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0 && ++ addr->sin6_addr.in6_u.u6_addr32[1] == 0 && ++ addr->sin6_addr.in6_u.u6_addr32[2] == 0 && ++ addr->sin6_addr.in6_u.u6_addr32[3] == 0) ++ return -EINVAL; ++ ++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0xffffffff && ++ addr->sin6_addr.in6_u.u6_addr32[1] == 0xffffffff && ++ addr->sin6_addr.in6_u.u6_addr32[2] == 0xffffffff && ++ addr->sin6_addr.in6_u.u6_addr32[3] == 0xffffffff) ++ return -EINVAL; ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check_ip_valid(struct sockaddr_storage *address) ++{ ++ int rc = 0; ++ ++ if (address->ss_family == AF_INET) ++ rc = nfs_multipath_parse_options_check_ipv4_valid( ++ (struct sockaddr_in *)address); ++ else if (address->ss_family == AF_INET6) ++ rc = nfs_multipath_parse_options_check_ipv6_valid( ++ (struct sockaddr_in6 *)address); ++ else ++ rc = -EINVAL; ++ ++ return rc; ++} ++ ++int nfs_multipath_parse_options_check_valid( ++ struct multipath_mount_options *options) ++{ ++ int rc; ++ int i; ++ ++ if (options == NULL) ++ return 0; ++ ++ for (i = 0; i < options->local_ip_list->count; i++) { ++ rc = nfs_multipath_parse_options_check_ip_valid( ++ &options->local_ip_list->address[i]); ++ if (rc != 0) ++ return rc; ++ } ++ ++ for (i = 0; i < options->remote_ip_list->count; i++) { ++ rc = nfs_multipath_parse_options_check_ip_valid( ++ &options->remote_ip_list->address[i]); ++ if (rc != 0) ++ return rc; ++ } ++ ++ return 0; ++} ++int nfs_multipath_parse_options_check_duplicate( ++ struct multipath_mount_options *options) ++{ ++ int i; ++ int j; ++ ++ if (options == NULL || ++ options->local_ip_list->count == 0 || ++ options->remote_ip_list->count == 0) ++ ++ return 0; ++ ++ for (i = 0; i < options->local_ip_list->count; i++) { ++ for (j = 0; j < options->remote_ip_list->count; j++) { ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &options->local_ip_list->address[i], ++ (const struct sockaddr *) ++ &options->remote_ip_list->address[j])) ++ return -ENOTSUPP; ++ } ++ } ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check(struct multipath_mount_options *options) ++{ ++ int rc = 0; ++ ++ rc = nfs_multipath_parse_options_check_valid(options); ++ ++ if (rc != 0) { ++ pr_err("has invaild ip.\n"); ++ return rc; ++ } ++ ++ rc = nfs_multipath_parse_options_check_duplicate(options); ++ if (rc != 0) ++ return rc; ++ return rc; ++} ++ ++int nfs_multipath_alloc_options(void **enfs_option) ++{ ++ struct multipath_mount_options *options = NULL; ++ ++ options = kzalloc(sizeof(struct multipath_mount_options), GFP_KERNEL); ++ ++ if (options == NULL) ++ return -ENOMEM; ++ ++ options->local_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ if (options->local_ip_list == NULL) { ++ kfree(options); ++ return -ENOMEM; ++ } ++ ++ options->remote_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ if (options->remote_ip_list == NULL) { ++ kfree(options->local_ip_list); ++ kfree(options); ++ return -ENOMEM; ++ } ++ ++ options->pRemoteDnsInfo = kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), ++ GFP_KERNEL); ++ if (options->pRemoteDnsInfo == NULL) { ++ kfree(options->remote_ip_list); ++ kfree(options->local_ip_list); ++ kfree(options); ++ return -ENOMEM; ++ } ++ ++ *enfs_option = options; ++ return 0; ++} ++ ++int nfs_multipath_parse_options(enum nfsmultipathoptions type, ++ char *str, void **enfs_option, struct net *net_ns) ++{ ++ int rc; ++ struct multipath_mount_options *options = NULL; ++ ++ if ((str == NULL) || (enfs_option == NULL) || (net_ns == NULL)) ++ return -EINVAL; ++ ++ if (*enfs_option == NULL) { ++ rc = nfs_multipath_alloc_options(enfs_option); ++ if (rc != 0) { ++ enfs_log_error( ++ "alloc enfs_options failed! errno:%d\n", rc); ++ return rc; ++ } ++ } ++ ++ options = (struct multipath_mount_options *)*enfs_option; ++ ++ if (type == LOCALADDR || type == REMOUNTLOCALADDR || ++ type == REMOTEADDR || type == REMOUNTREMOTEADDR) { ++ rc = nfs_multipath_parse_ip_list(str, net_ns, options, type); ++ } else if (type == REMOTEDNSNAME) { ++ /* alloc and release need to modify */ ++ rc = nfs_multipath_parse_dns_list(str, net_ns, options); ++ } else { ++ rc = -EOPNOTSUPP; ++ } ++ ++ // after parsing cmd, need checking local and remote ++ // IP is same. if not means illegal cmd ++ if (rc == 0) ++ rc = nfs_multipath_parse_options_check_duplicate(options); ++ ++ if (rc == 0) ++ rc = nfs_multipath_parse_options_check(options); ++ ++ return rc; ++} ++ ++void nfs_multipath_free_options(void **enfs_option) ++{ ++ struct multipath_mount_options *options; ++ ++ if (enfs_option == NULL || *enfs_option == NULL) ++ return; ++ ++ options = (struct multipath_mount_options *)*enfs_option; ++ ++ if (options->remote_ip_list != NULL) { ++ kfree(options->remote_ip_list); ++ options->remote_ip_list = NULL; ++ } ++ ++ if (options->local_ip_list != NULL) { ++ kfree(options->local_ip_list); ++ options->local_ip_list = NULL; ++ } ++ ++ if (options->pRemoteDnsInfo != NULL) { ++ kfree(options->pRemoteDnsInfo); ++ options->pRemoteDnsInfo = NULL; ++ } ++ ++ kfree(options); ++ *enfs_option = NULL; ++} +diff --git a/fs/nfs/enfs/enfs_multipath_parse.h b/fs/nfs/enfs/enfs_multipath_parse.h +new file mode 100644 +index 000000000000..6f3e8703e3e2 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_parse.h +@@ -0,0 +1,22 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _ENFS_MULTIPATH_PARSE_H_ ++#define _ENFS_MULTIPATH_PARSE_H_ ++ ++#include "enfs.h" ++ ++struct multipath_mount_options { ++ struct nfs_ip_list *remote_ip_list; ++ struct nfs_ip_list *local_ip_list; ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; ++}; ++ ++int nfs_multipath_parse_options(enum nfsmultipathoptions type, ++ char *str, void **enfs_option, struct net *net_ns); ++void nfs_multipath_free_options(void **enfs_option); ++ ++#endif diff --git a/0004-add_enfs_module_for_sunrpc_multipatch.patch b/0004-add_enfs_module_for_sunrpc_multipatch.patch new file mode 100644 index 0000000..2c0fcc7 --- /dev/null +++ b/0004-add_enfs_module_for_sunrpc_multipatch.patch @@ -0,0 +1,1581 @@ +diff --git a/fs/nfs/enfs/enfs_multipath.h b/fs/nfs/enfs/enfs_multipath.h +new file mode 100644 +index 000000000000..e064c2929ced +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath.h +@@ -0,0 +1,24 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: enfs multipath ++ * Author: ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef ENFS_MULTIPATH_H ++#define ENFS_MULTIPATH_H ++#include <linux/sunrpc/clnt.h> ++ ++#define MAX_XPRT_NUM_PER_CLIENT 32 ++ ++int enfs_multipath_init(void); ++void enfs_multipath_exit(void); ++void enfs_xprt_ippair_create(struct xprt_create *xprtargs, ++ struct rpc_clnt *clnt, void *data); ++int enfs_config_xprt_create_args(struct xprt_create *xprtargs, ++ struct rpc_create_args *args, ++ char *servername, size_t length); ++void print_enfs_multipath_addr(struct sockaddr *local, struct sockaddr *remote); ++ ++#endif // ENFS_MULTIPATH_H +diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c +new file mode 100644 +index 000000000000..63c02898a42c +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.c +@@ -0,0 +1,340 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/proc_fs.h> ++#include <linux/seq_file.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/addr.h> ++#include "enfs_multipath_client.h" ++#include "enfs_multipath_parse.h" ++ ++int ++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, ++ const struct nfs_client_initdata *client_init_data) ++{ ++ struct multipath_mount_options *mount_options = ++ (struct multipath_mount_options *)client_init_data->enfs_option; ++ ++ if (mount_options->local_ip_list) { ++ client_info->local_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->local_ip_list) ++ return -ENOMEM; ++ ++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->remote_ip_list) { ++ ++ client_info->remote_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->remote_ip_list) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->remote_ip_list, ++ mount_options->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->pRemoteDnsInfo) { ++ client_info->pRemoteDnsInfo = ++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); ++ ++ if (!client_info->pRemoteDnsInfo) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ kfree(client_info->remote_ip_list); ++ client_info->remote_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->pRemoteDnsInfo, ++ mount_options->pRemoteDnsInfo, ++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); ++ } ++ return 0; ++} ++ ++void nfs_multipath_client_info_free_work(struct work_struct *work) ++{ ++ ++ struct multipath_client_info *clp_info; ++ ++ if (work == NULL) ++ return; ++ ++ clp_info = container_of(work, struct multipath_client_info, work); ++ ++ if (clp_info->local_ip_list != NULL) { ++ kfree(clp_info->local_ip_list); ++ clp_info->local_ip_list = NULL; ++ } ++ if (clp_info->remote_ip_list != NULL) { ++ kfree(clp_info->remote_ip_list); ++ clp_info->remote_ip_list = NULL; ++ } ++ kfree(clp_info); ++} ++ ++void nfs_multipath_client_info_free(void *data) ++{ ++ struct multipath_client_info *clp_info = ++ (struct multipath_client_info *)data; ++ ++ if (clp_info == NULL) ++ return; ++ pr_info("free client info %p.\n", clp_info); ++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); ++ schedule_work(&clp_info->work); ++} ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init) ++{ ++ int rc; ++ struct multipath_client_info *info; ++ struct multipath_client_info **enfs_info; ++ /* no multi path info, no need do multipath init */ ++ if (cl_init->enfs_option == NULL) ++ return 0; ++ enfs_info = (struct multipath_client_info **)data; ++ if (enfs_info == NULL) ++ return -EINVAL; ++ ++ if (*enfs_info == NULL) ++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), ++ GFP_KERNEL); ++ ++ if (*enfs_info == NULL) ++ return -ENOMEM; ++ ++ info = (struct multipath_client_info *)*enfs_info; ++ pr_info("init client info %p.\n", info); ++ rc = nfs_multipath_client_mount_info_init(info, cl_init); ++ if (rc) { ++ nfs_multipath_client_info_free((void *)info); ++ return rc; ++ } ++ return rc; ++} ++ ++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, ++ const struct nfs_ip_list *ip_list_dst) ++{ ++ int i; ++ int j; ++ bool is_find; ++ /* if both are equal or NULL, then return true. */ ++ if (ip_list_src == ip_list_dst) ++ return true; ++ ++ if ((ip_list_src == NULL || ip_list_dst == NULL)) ++ return false; ++ ++ if (ip_list_src->count != ip_list_dst->count) ++ return false; ++ ++ for (i = 0; i < ip_list_src->count; i++) { ++ is_find = false; ++ for (j = 0; j < ip_list_src->count; j++) { ++ if (rpc_cmp_addr_port( ++ (const struct sockaddr *) ++ &ip_list_src->address[i], ++ (const struct sockaddr *) ++ &ip_list_dst->address[j]) ++ ) { ++ is_find = true; ++ break; ++ } ++ } ++ if (is_find == false) ++ return false; ++ } ++ return true; ++} ++ ++int ++nfs_multipath_dns_list_info_match( ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) ++{ ++ int i; ++ ++ /* if both are equal or NULL, then return true. */ ++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) ++ return true; ++ ++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) ++ return false; ++ ++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) ++ return false; ++ ++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { ++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, ++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) ++ return false; ++ } ++ return true; ++} ++ ++int nfs_multipath_client_info_match(void *src, void *dst) ++{ ++ int ret = true; ++ ++ struct multipath_client_info *src_info; ++ struct multipath_mount_options *dst_info; ++ ++ src_info = (struct multipath_client_info *)src; ++ dst_info = (struct multipath_mount_options *)dst; ++ pr_info("try match client .\n"); ++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, ++ dst_info->local_ip_list); ++ if (ret == false) { ++ pr_err("local_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, ++ dst_info->remote_ip_list); ++ if (ret == false) { ++ pr_err("remote_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, ++ dst_info->pRemoteDnsInfo); ++ if (ret == false) { ++ pr_err("dns not match.\n"); ++ return ret; ++ } ++ pr_info("try match client ret %d.\n", ret); ++ return ret; ++} ++ ++void nfs_multipath_print_ip_info(struct seq_file *mount_option, ++ struct nfs_ip_list *ip_list, ++ const char *type) ++{ ++ char buf[IP_ADDRESS_LEN_MAX + 1]; ++ int len = 0; ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < ip_list->count; i++) { ++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], ++ buf, IP_ADDRESS_LEN_MAX); ++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) ++ buf[len] = '\0'; ++ ++ if (i == 0) ++ seq_printf(mount_option, "%s", buf); ++ else ++ seq_printf(mount_option, "~%s", buf); ++ dfprintk(MOUNT, ++ "NFS: show nfs mount option type:%s %s [%s]\n", ++ type, buf, __func__); ++ } ++} ++ ++void nfs_multipath_print_dns_info(struct seq_file *mount_option, ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, ++ const char *type) ++{ ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { ++ if (i == 0) ++ seq_printf(mount_option, ++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) ++ seq_printf(mount_option, ",%s]", ++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else ++ seq_printf(mount_option, ++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ } ++} ++ ++ ++static void multipath_print_sockaddr(struct seq_file *seq, ++ struct sockaddr *addr) ++{ ++ switch (addr->sa_family) { ++ case AF_INET: { ++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; ++ ++ seq_printf(seq, "%pI4", &sin->sin_addr); ++ return; ++ } ++ case AF_INET6: { ++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; ++ ++ seq_printf(seq, "%pI6", &sin6->sin6_addr); ++ return; ++ } ++ default: ++ break; ++ } ++ pr_err("unsupport family:%d\n", addr->sa_family); ++} ++ ++static void multipath_print_enfs_info(struct seq_file *seq, ++ struct nfs_server *server) ++{ ++ struct sockaddr_storage peeraddr; ++ struct rpc_clnt *next = server->client; ++ ++ rpc_peeraddr(server->client, ++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); ++ seq_puts(seq, ",enfs_info="); ++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); ++ ++ while (next->cl_parent) { ++ if (next == next->cl_parent) ++ break; ++ next = next->cl_parent; ++ } ++ seq_printf(seq, "_%u", next->cl_clid); ++} ++ ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) ++{ ++ struct nfs_server *server = data; ++ struct multipath_client_info *client_info = ++ server->nfs_client->cl_multipath_data; ++ ++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); ++ if ((client_info->remote_ip_list) && ++ (client_info->remote_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->remote_ip_list, ++ "remoteaddrs"); ++ ++ if ((client_info->local_ip_list) && ++ (client_info->local_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->local_ip_list, ++ "localaddrs"); ++ ++ if ((client_info->pRemoteDnsInfo) && ++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) ++ nfs_multipath_print_dns_info(mount_option, ++ client_info->pRemoteDnsInfo, ++ "remotednsname"); ++ ++ multipath_print_enfs_info(mount_option, server); ++} +diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h +new file mode 100644 +index 000000000000..208f7260690d +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.h +@@ -0,0 +1,26 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _ENFS_MULTIPATH_CLIENT_H_ ++#define _ENFS_MULTIPATH_CLIENT_H_ ++ ++#include "enfs.h" ++ ++struct multipath_client_info { ++ struct work_struct work; ++ struct nfs_ip_list *remote_ip_list; ++ struct nfs_ip_list *local_ip_list; ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; ++ s64 client_id; ++}; ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init); ++void nfs_multipath_client_info_free(void *data); ++int nfs_multipath_client_info_match(void *src, void *dst); ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_path.c b/fs/nfs/enfs/enfs_path.c +new file mode 100644 +index 000000000000..7355f8c2f672 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_path.c +@@ -0,0 +1,47 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++ ++#include <linux/sunrpc/metrics.h> ++#include <linux/sunrpc/xprt.h> ++ ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_path.h" ++ ++// only create ctx in this function ++// alloc iostat memory in create_clnt ++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx; ++ ++ if (!xprt) { ++ enfs_log_error("invalid xprt pointer.\n"); ++ return -EINVAL; ++ } ++ ++ ctx = kzalloc(sizeof(struct enfs_xprt_context), GFP_KERNEL); ++ if (!ctx) { ++ enfs_log_error("add xprt test failed.\n"); ++ return -ENOMEM; ++ } ++ ++ xprt->multipath_context = (void *)ctx; ++ return 0; ++} ++ ++// free multi_context and iostat memory ++void enfs_free_xprt_ctx(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = xprt->multipath_context; ++ ++ if (ctx) { ++ if (ctx->stats) { ++ rpc_free_iostats(ctx->stats); ++ ctx->stats = NULL; ++ } ++ kfree(xprt->multipath_context); ++ xprt->multipath_context = NULL; ++ } ++} +diff --git a/fs/nfs/enfs/enfs_path.h b/fs/nfs/enfs/enfs_path.h +new file mode 100644 +index 000000000000..97b1ef3730b8 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_path.h +@@ -0,0 +1,12 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++ ++#ifndef ENFS_PATH_H ++#define ENFS_PATH_H ++ ++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt); ++void enfs_free_xprt_ctx(struct rpc_xprt *xprt); ++ ++#endif // ENFS_PATH_H +diff --git a/fs/nfs/enfs/enfs_proc.c b/fs/nfs/enfs/enfs_proc.c +new file mode 100644 +index 000000000000..53fa1a07642f +--- /dev/null ++++ b/fs/nfs/enfs/enfs_proc.c +@@ -0,0 +1,545 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#include <linux/module.h> ++#include <linux/proc_fs.h> ++#include <linux/seq_file.h> ++#include <linux/spinlock.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/metrics.h> ++#include <linux/sunrpc/xprtsock.h> ++#include <net/netns/generic.h> ++ ++#include "../../../net/sunrpc/netns.h" ++ ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_proc.h" ++#include "enfs_multipath.h" ++#include "pm_state.h" ++ ++#define ENFS_PROC_DIR "enfs" ++#define ENFS_PROC_PATH_STATUS_LEN 256 ++ ++static struct proc_dir_entry *enfs_proc_parent; ++ ++void ++enfs_iterate_each_rpc_clnt(int (*fn)(struct rpc_clnt *clnt, void *data), ++ void *data) ++{ ++ struct net *net; ++ struct sunrpc_net *sn; ++ struct rpc_clnt *clnt; ++ ++ rcu_read_lock(); ++ for_each_net_rcu(net) { ++ sn = net_generic(net, sunrpc_net_id); ++ if (sn == NULL) ++ continue; ++ spin_lock(&sn->rpc_client_lock); ++ list_for_each_entry(clnt, &sn->all_clients, cl_clients) { ++ fn(clnt, data); ++ } ++ spin_unlock(&sn->rpc_client_lock); ++ } ++ rcu_read_unlock(); ++} ++ ++struct proc_dir_entry *enfs_get_proc_parent(void) ++{ ++ return enfs_proc_parent; ++} ++ ++static int sockaddr_ip_to_str(struct sockaddr *addr, char *buf, int len) ++{ ++ switch (addr->sa_family) { ++ case AF_INET: { ++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; ++ ++ snprintf(buf, len, "%pI4", &sin->sin_addr); ++ return 0; ++ } ++ case AF_INET6: { ++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; ++ ++ snprintf(buf, len, "%pI6", &sin6->sin6_addr); ++ return 0; ++ } ++ default: ++ break; ++ } ++ return 1; ++} ++ ++static bool should_print(const char *name) ++{ ++ int i; ++ static const char * const proc_names[] = { ++ "READ", ++ "WRITE", ++ }; ++ ++ if (name == NULL) ++ return false; ++ ++ for (i = 0; i < ARRAY_SIZE(proc_names); i++) { ++ if (strcmp(name, proc_names[i]) == 0) ++ return true; ++ } ++ return false; ++} ++ ++struct enfs_xprt_iter { ++ unsigned int id; ++ struct seq_file *seq; ++ unsigned int max_addrs_length; ++}; ++ ++static int debug_show_xprt(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ ++ if (xprt->multipath_context) ++ ctx = xprt->multipath_context; ++ ++ pr_info(" xprt:%p ctx:%p main:%d queue_len:%lu.\n", xprt, ++ xprt->multipath_context, ++ ctx ? ctx->main : false, ++ atomic_long_read(&xprt->queuelen)); ++ return 0; ++} ++ ++static int debug_show_clnt(struct rpc_clnt *clnt, void *data) ++{ ++ pr_info(" clnt %d addr:%p enfs:%d\n", ++ clnt->cl_clid, clnt, ++ clnt->cl_enfs); ++ rpc_clnt_iterate_for_each_xprt(clnt, debug_show_xprt, NULL); ++ return 0; ++} ++ ++static void debug_print_all_xprt(void) ++{ ++ enfs_iterate_each_rpc_clnt(debug_show_clnt, NULL); ++} ++ ++static ++void enfs_proc_format_xprt_addr_display(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ char *local_name_buf, ++ int local_name_buf_len, ++ char *remote_name_buf, ++ int remote_name_buf_len) ++{ ++ int err; ++ struct sockaddr_storage srcaddr; ++ struct enfs_xprt_context *ctx; ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ sockaddr_ip_to_str((struct sockaddr *)&xprt->addr, ++ remote_name_buf, remote_name_buf_len); ++ ++ // get local address depend one main or not ++ if (enfs_is_main_xprt(xprt)) { ++ err = rpc_localaddr(clnt, (struct sockaddr *)&srcaddr, ++ sizeof(srcaddr)); ++ if (err != 0) ++ (void)snprintf(local_name_buf, ++ local_name_buf_len, "Unknown"); ++ else ++ sockaddr_ip_to_str((struct sockaddr *)&srcaddr, ++ local_name_buf, ++ local_name_buf_len); ++ } else { ++ sockaddr_ip_to_str((struct sockaddr *)&ctx->srcaddr, ++ local_name_buf, ++ local_name_buf_len); ++ } ++} ++ ++static int enfs_show_xprt_stats(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ unsigned int op; ++ unsigned int maxproc = clnt->cl_maxproc; ++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; ++ struct enfs_xprt_context *ctx; ++ char local_name[INET6_ADDRSTRLEN]; ++ char remote_name[INET6_ADDRSTRLEN]; ++ ++ if (!xprt->multipath_context) ++ return 0; ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ enfs_proc_format_xprt_addr_display(clnt, xprt, local_name, ++ sizeof(local_name), ++ remote_name, sizeof(remote_name)); ++ ++ seq_printf(iter->seq, "%-6u%-*s%-*s", iter->id, ++ iter->max_addrs_length + 4, ++ local_name, ++ iter->max_addrs_length + 4, ++ remote_name); ++ ++ iter->id++; ++ ++ for (op = 0; op < maxproc; op++) { ++ if (!should_print(clnt->cl_procinfo[op].p_name)) ++ continue; ++ ++ seq_printf(iter->seq, "%-22lu%-22Lu%-22Lu", ++ ctx->stats[op].om_ops, ++ ctx->stats[op].om_ops == 0 ? 0 : ++ ktime_to_ms(ctx->stats[op].om_rtt) / ++ ctx->stats[op].om_ops, ++ ctx->stats[op].om_ops == 0 ? 0 : ++ ktime_to_ms(ctx->stats[op].om_execute) / ++ ctx->stats[op].om_ops); ++ } ++ seq_puts(iter->seq, "\n"); ++ return 0; ++} ++ ++static int rpc_proc_show_path_status(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; ++ struct enfs_xprt_context *ctx = NULL; ++ char local_name[INET6_ADDRSTRLEN] = {0}; ++ char remote_name[INET6_ADDRSTRLEN] = {0}; ++ char multiapth_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; ++ char xprt_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; ++ ++ if (!xprt->multipath_context) { ++ enfs_log_debug("multipath_context is null.\n"); ++ return 0; ++ } ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ enfs_proc_format_xprt_addr_display(clnt, xprt, ++ local_name, ++ sizeof(local_name), ++ remote_name, sizeof(remote_name)); ++ ++ pm_get_path_state_desc(xprt, ++ multiapth_status, ++ ENFS_PROC_PATH_STATUS_LEN); ++ ++ pm_get_xprt_state_desc(xprt, ++ xprt_status, ++ ENFS_PROC_PATH_STATUS_LEN); ++ ++ seq_printf(iter->seq, "%-6u%-*s%-*s%-12s%-12s\n", ++ iter->id, iter->max_addrs_length + 4, ++ local_name, iter->max_addrs_length + 4, ++ remote_name, multiapth_status, ++ xprt_status); ++ iter->id++; ++ return 0; ++} ++ ++static int enfs_get_max_addrs_length(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; ++ char local_name[INET6_ADDRSTRLEN]; ++ char remote_name[INET6_ADDRSTRLEN]; ++ ++ enfs_proc_format_xprt_addr_display(clnt, xprt, ++ local_name, sizeof(local_name), ++ remote_name, sizeof(remote_name)); ++ ++ if (iter->max_addrs_length < strlen(local_name)) ++ iter->max_addrs_length = strlen(local_name); ++ ++ if (iter->max_addrs_length < strlen(remote_name)) ++ iter->max_addrs_length = strlen(remote_name); ++ ++ return 0; ++} ++ ++static int rpc_proc_clnt_showpath(struct seq_file *seq, void *v) ++{ ++ struct rpc_clnt *clnt = seq->private; ++ struct enfs_xprt_iter iter; ++ ++ iter.seq = seq; ++ iter.id = 0; ++ iter.max_addrs_length = 0; ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ enfs_get_max_addrs_length, ++ (void *)&iter); ++ ++ seq_printf(seq, "%-6s%-*s%-*s%-12s%-12s\n", "id", ++ iter.max_addrs_length + 4, ++ "local_addr", ++ iter.max_addrs_length + 4, ++ "remote_addr", ++ "path_state", ++ "xprt_state"); ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ rpc_proc_show_path_status, ++ (void *)&iter); ++ return 0; ++} ++ ++static int enfs_rpc_proc_show(struct seq_file *seq, void *v) ++{ ++ struct rpc_clnt *clnt = seq->private; ++ struct enfs_xprt_iter iter; ++ ++ iter.seq = seq; ++ iter.id = 0; ++ iter.max_addrs_length = 0; ++ ++ debug_print_all_xprt(); ++ pr_info("enfs proc clnt:%p\n", clnt); ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ enfs_get_max_addrs_length, ++ (void *)&iter); ++ ++ seq_printf(seq, "%-6s%-*s%-*s%-22s%-22s%-22s%-22s%-22s%-22s\n", "id", ++ iter.max_addrs_length + 4, "local_addr", ++ iter.max_addrs_length + 4, ++ "remote_addr", "r_count", ++ "r_rtt", "r_exec", "w_count", "w_rtt", "w_exec"); ++ ++ // rpc_clnt_show_stats(seq, clnt); ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ enfs_show_xprt_stats, ++ (void *)&iter); ++ return 0; ++} ++ ++static int rpc_proc_open(struct inode *inode, struct file *file) ++{ ++ struct rpc_clnt *clnt = PDE_DATA(inode); ++ ++ pr_info("%s %p\n", __func__, clnt); ++ return single_open(file, enfs_rpc_proc_show, clnt); ++} ++ ++static int enfs_reset_xprt_stats(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ unsigned int op; ++ struct enfs_xprt_context *ctx; ++ unsigned int maxproc = clnt->cl_maxproc; ++ struct rpc_iostats stats = {0}; ++ ++ if (!xprt->multipath_context) ++ return 0; ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ for (op = 0; op < maxproc; op++) { ++ spin_lock(&ctx->stats[op].om_lock); ++ ctx->stats[op] = stats; ++ spin_unlock(&ctx->stats[op].om_lock); ++ } ++ return 0; ++} ++ ++static void trim_newline_ch(char *str, int len) ++{ ++ int i; ++ ++ for (i = 0; str[i] != '\0' && i < len; i++) { ++ if (str[i] == '\n') ++ str[i] = '\0'; ++ } ++} ++ ++static ssize_t enfs_proc_write(struct file *file, ++ const char __user *user_buf, ++ size_t len, ++ loff_t *offset) ++{ ++ char buffer[128]; ++ struct rpc_clnt *clnt = ++ ((struct seq_file *)file->private_data)->private; ++ ++ if (len >= sizeof(buffer)) ++ return -E2BIG; ++ ++ if (copy_from_user(buffer, user_buf, len) != 0) ++ return -EFAULT; ++ ++ buffer[len] = '\0'; ++ trim_newline_ch(buffer, len); ++ if (strcmp(buffer, "reset") != 0) ++ return -EINVAL; ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, enfs_reset_xprt_stats, NULL); ++ return len; ++} ++ ++static int rpc_proc_show_path(struct inode *inode, struct file *file) ++{ ++ struct rpc_clnt *clnt = PDE_DATA(inode); ++ ++ return single_open(file, rpc_proc_clnt_showpath, clnt); ++} ++ ++static const struct file_operations rpc_proc_fops = { ++ .owner = THIS_MODULE, ++ .open = rpc_proc_open, ++ .read = seq_read, ++ .llseek = seq_lseek, ++ .release = single_release, ++ .write = enfs_proc_write, ++}; ++ ++static const struct file_operations rpc_show_path_fops = { ++ .owner = THIS_MODULE, ++ .open = rpc_proc_show_path, ++ .read = seq_read, ++ .llseek = seq_lseek, ++ .release = single_release, ++}; ++ ++static int clnt_proc_name(struct rpc_clnt *clnt, char *buf, int len) ++{ ++ int ret; ++ ++ ret = snprintf(buf, len, "%s_%u", ++ rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR), ++ clnt->cl_clid); ++ if (ret > len) ++ return -E2BIG; ++ return 0; ++} ++ ++static int enfs_proc_create_file(struct rpc_clnt *clnt) ++{ ++ int err; ++ char buf[128]; ++ ++ struct proc_dir_entry *clnt_entry; ++ struct proc_dir_entry *stat_entry; ++ ++ err = clnt_proc_name(clnt, buf, sizeof(buf)); ++ if (err) ++ return err; ++ ++ clnt_entry = proc_mkdir(buf, enfs_proc_parent); ++ if (clnt_entry == NULL) ++ return -EINVAL; ++ ++ stat_entry = proc_create_data("stat", ++ 0, clnt_entry, ++ &rpc_proc_fops, clnt); ++ ++ if (stat_entry == NULL) ++ return -EINVAL; ++ ++ stat_entry = proc_create_data("path", ++ 0, clnt_entry, ++ &rpc_show_path_fops, clnt); ++ ++ if (stat_entry == NULL) ++ return -EINVAL; ++ ++ return 0; ++} ++ ++void enfs_count_iostat(struct rpc_task *task) ++{ ++ struct enfs_xprt_context *ctx = task->tk_xprt->multipath_context; ++ ++ if (!ctx || !ctx->stats) ++ return; ++ rpc_count_iostats(task, ctx->stats); ++} ++ ++static void enfs_proc_delete_file(struct rpc_clnt *clnt) ++{ ++ int err; ++ char buf[128]; ++ ++ err = clnt_proc_name(clnt, buf, sizeof(buf)); ++ if (err) { ++ pr_err("gen clnt name failed.\n"); ++ return; ++ } ++ remove_proc_subtree(buf, enfs_proc_parent); ++} ++ ++// create proc file "/porc/enfs/[mount_ip]_[id]/stat" ++int enfs_proc_create_clnt(struct rpc_clnt *clnt) ++{ ++ int err; ++ ++ err = enfs_proc_create_file(clnt); ++ if (err) { ++ pr_err("create client %d\n", err); ++ return err; ++ } ++ ++ return 0; ++} ++ ++void enfs_proc_delete_clnt(struct rpc_clnt *clnt) ++{ ++ if (clnt->cl_enfs) ++ enfs_proc_delete_file(clnt); ++} ++ ++static int enfs_proc_create_parent(void) ++{ ++ enfs_proc_parent = proc_mkdir(ENFS_PROC_DIR, NULL); ++ ++ if (enfs_proc_parent == NULL) { ++ pr_err("Enfs create proc dir err\n"); ++ return -ENOMEM; ++ } ++ return 0; ++} ++ ++static void enfs_proc_delete_parent(void) ++{ ++ remove_proc_entry(ENFS_PROC_DIR, NULL); ++} ++ ++static int enfs_proc_init_create_clnt(struct rpc_clnt *clnt, void *data) ++{ ++ if (clnt->cl_enfs) ++ enfs_proc_create_file(clnt); ++ return 0; ++} ++ ++static int enfs_proc_destroy_clnt(struct rpc_clnt *clnt, void *data) ++{ ++ if (clnt->cl_enfs) ++ enfs_proc_delete_file(clnt); ++ return 0; ++} ++ ++int enfs_proc_init(void) ++{ ++ int err; ++ ++ err = enfs_proc_create_parent(); ++ if (err) ++ return err; ++ ++ enfs_iterate_each_rpc_clnt(enfs_proc_init_create_clnt, NULL); ++ return 0; ++} ++ ++void enfs_proc_exit(void) ++{ ++ enfs_iterate_each_rpc_clnt(enfs_proc_destroy_clnt, NULL); ++ enfs_proc_delete_parent(); ++} +diff --git a/fs/nfs/enfs/enfs_proc.h b/fs/nfs/enfs/enfs_proc.h +new file mode 100644 +index 000000000000..321951031c2e +--- /dev/null ++++ b/fs/nfs/enfs/enfs_proc.h +@@ -0,0 +1,21 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS PROC. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef ENFS_PROC_H ++#define ENFS_PROC_H ++ ++struct rpc_clnt; ++struct rpc_task; ++struct proc_dir_entry; ++ ++int enfs_proc_init(void); ++void enfs_proc_exit(void); ++struct proc_dir_entry *enfs_get_proc_parent(void); ++int enfs_proc_create_clnt(struct rpc_clnt *clnt); ++void enfs_proc_delete_clnt(struct rpc_clnt *clnt); ++void enfs_count_iostat(struct rpc_task *task); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_remount.c b/fs/nfs/enfs/enfs_remount.c +new file mode 100644 +index 000000000000..2c3fe125c735 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_remount.c +@@ -0,0 +1,221 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: remount ip source file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++#include "enfs_remount.h" ++ ++#include <linux/string.h> ++#include <linux/in.h> ++#include <linux/in6.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/spinlock.h> ++#include <linux/sunrpc/addr.h> ++#include <linux/sunrpc/metrics.h> ++#include <linux/sunrpc/xprtmultipath.h> ++#include <linux/sunrpc/xprtsock.h> ++#include <linux/sunrpc/xprt.h> ++#include <linux/smp.h> ++#include <linux/delay.h> ++ ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_multipath.h" ++#include "enfs_multipath_parse.h" ++#include "enfs_path.h" ++#include "enfs_proc.h" ++#include "enfs_multipath_client.h" ++ ++static bool enfs_rpc_xprt_switch_need_delete_addr( ++ struct multipath_mount_options *enfs_option, ++ struct sockaddr *dstaddr, struct sockaddr *srcaddr) ++{ ++ int i; ++ bool find_same_ip = false; ++ int32_t local_total; ++ int32_t remote_total; ++ ++ local_total = enfs_option->local_ip_list->count; ++ remote_total = enfs_option->remote_ip_list->count; ++ if (local_total == 0 || remote_total == 0) { ++ pr_err("no ip list is present.\n"); ++ return false; ++ } ++ ++ for (i = 0; i < local_total; i++) { ++ find_same_ip = ++ rpc_cmp_addr((struct sockaddr *) ++ &enfs_option->local_ip_list->address[i], ++ srcaddr); ++ if (find_same_ip) ++ break; ++ } ++ ++ if (find_same_ip == false) ++ return true; ++ ++ find_same_ip = false; ++ for (i = 0; i < remote_total; i++) { ++ find_same_ip = ++ rpc_cmp_addr((struct sockaddr *) ++ &enfs_option->remote_ip_list->address[i], ++ dstaddr); ++ if (find_same_ip) ++ break; ++ } ++ ++ if (find_same_ip == false) ++ return true; ++ ++ return false; ++} ++ ++// Used in rcu_lock ++static bool enfs_delete_xprt_from_switch(struct rpc_xprt *xprt, ++ void *enfs_option, ++ struct rpc_xprt_switch *xps) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ struct multipath_mount_options *mopt = ++ (struct multipath_mount_options *)enfs_option; ++ ++ if (enfs_is_main_xprt(xprt)) ++ return true; ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (enfs_rpc_xprt_switch_need_delete_addr(mopt, ++ (struct sockaddr *)&xprt->addr, ++ (struct sockaddr *)&ctx->srcaddr)) { ++ ++ print_enfs_multipath_addr((struct sockaddr *)&ctx->srcaddr, ++ (struct sockaddr *)&xprt->addr); ++ rpc_xprt_switch_remove_xprt(xps, xprt); ++ return true; ++ } ++ ++ return false; ++} ++ ++void enfs_clnt_delete_obsolete_xprts(struct nfs_client *nfs_client, ++ void *enfs_option) ++{ ++ int xprt_count = 0; ++ struct rpc_xprt *pos = NULL; ++ struct rpc_xprt_switch *xps = NULL; ++ ++ rcu_read_lock(); ++ xps = xprt_switch_get( ++ rcu_dereference( ++ nfs_client->cl_rpcclient->cl_xpi.xpi_xpswitch)); ++ if (xps == NULL) { ++ rcu_read_unlock(); ++ xprt_switch_put(xps); ++ return; ++ } ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (xprt_count < MAX_XPRT_NUM_PER_CLIENT) { ++ if (enfs_delete_xprt_from_switch( ++ pos, enfs_option, xps) == false) ++ xprt_count++; ++ } else ++ rpc_xprt_switch_remove_xprt(xps, pos); ++ } ++ rcu_read_unlock(); ++ xprt_switch_put(xps); ++} ++ ++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) ++{ ++ int errno = 0; ++ char servername[48]; ++ struct multipath_mount_options *remount_lists = ++ (struct multipath_mount_options *)enfs_option; ++ struct multipath_client_info *client_info = ++ (struct multipath_client_info *)nfs_client->cl_multipath_data; ++ struct xprt_create xprtargs; ++ struct rpc_create_args args = { ++ .protocol = nfs_client->cl_proto, ++ .net = nfs_client->cl_net, ++ .addrsize = nfs_client->cl_addrlen, ++ .servername = nfs_client->cl_hostname, ++ }; ++ ++ memset(&xprtargs, 0, sizeof(struct xprt_create)); ++ ++ //mount is not use multipath ++ if (client_info == NULL || enfs_option == NULL) { ++ enfs_log_error( ++ "mount information or remount information is empty.\n"); ++ return -EINVAL; ++ } ++ ++ //remount : localaddrs and remoteaddrs are empty ++ if (remount_lists->local_ip_list->count == 0 && ++ remount_lists->remote_ip_list->count == 0) { ++ enfs_log_info("remount local_ip_list and remote_ip_list are NULL\n"); ++ return 0; ++ } ++ ++ errno = enfs_config_xprt_create_args(&xprtargs, ++ &args, servername, sizeof(servername)); ++ ++ if (errno) { ++ enfs_log_error("config_xprt_create failed! errno:%d\n", errno); ++ return errno; ++ } ++ ++ if (remount_lists->local_ip_list->count == 0) { ++ if (client_info->local_ip_list->count == 0) { ++ errno = rpc_localaddr(nfs_client->cl_rpcclient, ++ (struct sockaddr *) ++ &remount_lists->local_ip_list->address[0], ++ sizeof(struct sockaddr_storage)); ++ if (errno) { ++ enfs_log_error("get clnt srcaddr errno:%d\n", ++ errno); ++ return errno; ++ } ++ remount_lists->local_ip_list->count = 1; ++ } else ++ memcpy(remount_lists->local_ip_list, ++ client_info->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (remount_lists->remote_ip_list->count == 0) { ++ if (client_info->remote_ip_list->count == 0) { ++ errno = rpc_peeraddr(nfs_client->cl_rpcclient, ++ (struct sockaddr *) ++ &remount_lists->remote_ip_list->address[0], ++ sizeof(struct sockaddr_storage)); ++ if (errno == 0) { ++ enfs_log_error("get clnt dstaddr errno:%d\n", ++ errno); ++ return errno; ++ } ++ remount_lists->remote_ip_list->count = 1; ++ } else ++ memcpy(remount_lists->remote_ip_list, ++ client_info->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ enfs_log_info("Remount creating new links...\n"); ++ enfs_xprt_ippair_create(&xprtargs, ++ nfs_client->cl_rpcclient, ++ remount_lists); ++ ++ enfs_log_info("Remount deleting obsolete links...\n"); ++ enfs_clnt_delete_obsolete_xprts(nfs_client, remount_lists); ++ ++ memcpy(client_info->local_ip_list, ++ remount_lists->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ memcpy(client_info->remote_ip_list, ++ remount_lists->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ ++ return 0; ++} +diff --git a/fs/nfs/enfs/enfs_remount.h b/fs/nfs/enfs/enfs_remount.h +new file mode 100644 +index 000000000000..a663ed257004 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_remount.h +@@ -0,0 +1,15 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: remount ip header file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++#ifndef _ENFS_REMOUNT_ ++#define _ENFS_REMOUNT_ ++#include <linux/string.h> ++#include "enfs.h" ++ ++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_roundrobin.c b/fs/nfs/enfs/enfs_roundrobin.c +new file mode 100644 +index 000000000000..4e4eda784a3e +--- /dev/null ++++ b/fs/nfs/enfs/enfs_roundrobin.c +@@ -0,0 +1,255 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#include <linux/spinlock.h> ++#include <linux/module.h> ++#include <linux/printk.h> ++#include <linux/kref.h> ++#include <linux/rculist.h> ++#include <linux/types.h> ++#include <linux/sunrpc/xprt.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/xprtmultipath.h> ++#include "enfs_roundrobin.h" ++ ++#include "enfs.h" ++#include "enfs_config.h" ++#include "pm_state.h" ++ ++typedef struct rpc_xprt *(*enfs_xprt_switch_find_xprt_t)( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur); ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin; ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular; ++ ++static bool enfs_xprt_is_active(struct rpc_xprt *xprt) ++{ ++ enum pm_path_state state; ++ ++ if (kref_read(&xprt->kref) <= 0) ++ return false; ++ ++ state = pm_get_path_state(xprt); ++ if (state == PM_STATE_NORMAL) ++ return true; ++ ++ return false; ++} ++ ++static struct rpc_xprt *enfs_lb_set_cursor_xprt( ++ struct rpc_xprt_switch *xps, struct rpc_xprt **cursor, ++ enfs_xprt_switch_find_xprt_t find_next) ++{ ++ struct rpc_xprt *pos; ++ struct rpc_xprt *old; ++ ++ old = smp_load_acquire(cursor); /* read latest cursor */ ++ pos = find_next(xps, old); ++ smp_store_release(cursor, pos); /* let cursor point to pos */ ++ return pos; ++} ++ ++static ++struct rpc_xprt *enfs_lb_find_next_entry_roundrobin( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *pos; ++ struct rpc_xprt *prev = NULL; ++ bool found = false; ++ struct rpc_xprt *min_queuelen_xprt = NULL; ++ unsigned long pos_xprt_queuelen; ++ unsigned long min_xprt_queuelen = 0; ++ ++ unsigned long xps_queuelen = atomic_long_read(&xps->xps_queuelen); ++ // delete origin xprt ++ unsigned int multipath_nactive = READ_ONCE(xps->xps_nactive) - 1; ++ ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (enfs_is_main_xprt(pos) || !enfs_xprt_is_active(pos)) { ++ prev = pos; ++ continue; ++ } ++ ++ pos_xprt_queuelen = atomic_long_read(&pos->queuelen); ++ if (min_queuelen_xprt == NULL || ++ pos_xprt_queuelen < min_xprt_queuelen) { ++ ++ min_queuelen_xprt = pos; ++ min_xprt_queuelen = pos_xprt_queuelen; ++ } ++ ++ if (cur == prev) ++ found = true; ++ ++ if (found && pos_xprt_queuelen * ++ multipath_nactive <= xps_queuelen) ++ return pos; ++ prev = pos; ++ }; ++ ++ return min_queuelen_xprt; ++} ++ ++struct rpc_xprt *enfs_lb_switch_find_first_active_xprt( ++ struct rpc_xprt_switch *xps) ++{ ++ struct rpc_xprt *pos; ++ ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (enfs_xprt_is_active(pos)) ++ return pos; ++ }; ++ return NULL; ++} ++ ++struct rpc_xprt *enfs_lb_switch_get_main_xprt(struct rpc_xprt_switch *xps) ++{ ++ return list_first_or_null_rcu(&xps->xps_xprt_list, ++ struct rpc_xprt, xprt_switch); ++} ++ ++static struct rpc_xprt *enfs_lb_switch_get_next_xprt_roundrobin( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *xprt; ++ ++ // disable multipath ++ if (enfs_get_config_multipath_state()) ++ return enfs_lb_switch_get_main_xprt(xps); ++ ++ xprt = enfs_lb_find_next_entry_roundrobin(xps, cur); ++ if (xprt != NULL) ++ return xprt; ++ ++ return enfs_lb_switch_get_main_xprt(xps); ++} ++ ++static ++struct rpc_xprt *enfs_lb_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi) ++{ ++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); ++ ++ if (xps == NULL) ++ return NULL; ++ ++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, ++ enfs_lb_switch_get_next_xprt_roundrobin); ++} ++ ++static ++struct rpc_xprt *enfs_lb_switch_find_singular_entry( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *pos; ++ bool found = false; ++ ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (cur == pos) ++ found = true; ++ ++ if (found && enfs_xprt_is_active(pos)) ++ return pos; ++ } ++ return NULL; ++} ++ ++struct rpc_xprt *enfs_lb_get_singular_xprt( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *xprt; ++ ++ if (xps == NULL) ++ return NULL; ++ ++ // disable multipath ++ if (enfs_get_config_multipath_state()) ++ return enfs_lb_switch_get_main_xprt(xps); ++ ++ if (cur == NULL || xps->xps_nxprts < 2) ++ return enfs_lb_switch_find_first_active_xprt(xps); ++ ++ xprt = enfs_lb_switch_find_singular_entry(xps, cur); ++ if (!xprt) ++ return enfs_lb_switch_get_main_xprt(xps); ++ ++ return xprt; ++} ++ ++static ++struct rpc_xprt *enfs_lb_iter_next_entry_sigular(struct rpc_xprt_iter *xpi) ++{ ++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); ++ ++ if (xps == NULL) ++ return NULL; ++ ++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, ++ enfs_lb_get_singular_xprt); ++} ++ ++static void enfs_lb_iter_default_rewind(struct rpc_xprt_iter *xpi) ++{ ++ WRITE_ONCE(xpi->xpi_cursor, NULL); ++} ++ ++static void enfs_lb_switch_set_roundrobin(struct rpc_clnt *clnt) ++{ ++ struct rpc_xprt_switch *xps; ++ ++ rcu_read_lock(); ++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ++ rcu_read_unlock(); ++ if (clnt->cl_vers == 3) { ++ ++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_roundrobin) ++ WRITE_ONCE(xps->xps_iter_ops, ++ &enfs_xprt_iter_roundrobin); ++ ++ return; ++ } ++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_singular) ++ WRITE_ONCE(xps->xps_iter_ops, &enfs_xprt_iter_singular); ++} ++ ++static ++struct rpc_xprt *enfs_lb_switch_find_current(struct list_head *head, ++ const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *pos; ++ ++ list_for_each_entry_rcu(pos, head, xprt_switch) { ++ if (cur == pos) ++ return pos; ++ } ++ return NULL; ++} ++ ++static struct rpc_xprt *enfs_lb_iter_current_entry(struct rpc_xprt_iter *xpi) ++{ ++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); ++ struct list_head *head; ++ ++ if (xps == NULL) ++ return NULL; ++ head = &xps->xps_xprt_list; ++ if (xpi->xpi_cursor == NULL || xps->xps_nxprts < 2) ++ return enfs_lb_switch_get_main_xprt(xps); ++ return enfs_lb_switch_find_current(head, xpi->xpi_cursor); ++} ++ ++void enfs_lb_set_policy(struct rpc_clnt *clnt) ++{ ++ enfs_lb_switch_set_roundrobin(clnt); ++} ++ ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin = { ++ .xpi_rewind = enfs_lb_iter_default_rewind, ++ .xpi_xprt = enfs_lb_iter_current_entry, ++ .xpi_next = enfs_lb_iter_next_entry_roundrobin, ++}; ++ ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular = { ++ .xpi_rewind = enfs_lb_iter_default_rewind, ++ .xpi_xprt = enfs_lb_iter_current_entry, ++ .xpi_next = enfs_lb_iter_next_entry_sigular, ++}; +diff --git a/fs/nfs/enfs/enfs_roundrobin.h b/fs/nfs/enfs/enfs_roundrobin.h +new file mode 100644 +index 000000000000..b72b088a6258 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_roundrobin.h +@@ -0,0 +1,9 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#ifndef ENFS_ROUNDROBIN_H ++#define ENFS_ROUNDROBIN_H ++ ++void enfs_lb_set_policy(struct rpc_clnt *clnt); ++#endif diff --git a/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch new file mode 100644 index 0000000..cc6b677 --- /dev/null +++ b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch @@ -0,0 +1,1607 @@ +diff --git a/fs/nfs/enfs/enfs_config.c b/fs/nfs/enfs/enfs_config.c +new file mode 100644 +index 000000000000..11aa7a00385b +--- /dev/null ++++ b/fs/nfs/enfs/enfs_config.c +@@ -0,0 +1,378 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#include <linux/cdev.h> ++#include <linux/errno.h> ++#include <linux/fcntl.h> ++#include <linux/fs.h> ++#include <linux/kernel.h> ++#include <linux/kthread.h> ++#include <linux/slab.h> ++#include <linux/string.h> ++#include <linux/uaccess.h> ++#include <linux/delay.h> ++ ++#include "enfs_errcode.h" ++#include "enfs_log.h" ++#include "enfs_config.h" ++ ++#define MAX_FILE_SIZE 8192 ++#define STRING_BUF_SIZE 128 ++#define CONFIG_FILE_PATH "/etc/enfs/config.ini" ++#define ENFS_NOTIFY_FILE_PERIOD 1000UL ++ ++#define MAX_PATH_DETECT_INTERVAL 300 ++#define MIN_PATH_DETECT_INTERVAL 5 ++#define MAX_PATH_DETECT_TIMEOUT 60 ++#define MIN_PATH_DETECT_TIMEOUT 1 ++#define MAX_MULTIPATH_TIMEOUT 60 ++#define MIN_MULTIPATH_TIMEOUT 0 ++#define MAX_MULTIPATH_STATE ENFS_MULTIPATH_DISABLE ++#define MIN_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE ++ ++#define DEFAULT_PATH_DETECT_INTERVAL 10 ++#define DEFAULT_PATH_DETECT_TIMEOUT 5 ++#define DEFAULT_MULTIPATH_TIMEOUT 0 ++#define DEFAULT_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE ++#define DEFAULT_LOADBALANCE_MODE ENFS_LOADBALANCE_RR ++ ++typedef int (*check_and_assign_func)(char *, char *, int, int); ++ ++struct enfs_config_info { ++ int32_t path_detect_interval; ++ int32_t path_detect_timeout; ++ int32_t multipath_timeout; ++ int32_t loadbalance_mode; ++ int32_t multipath_state; ++}; ++ ++struct check_and_assign_value { ++ char *field_name; ++ check_and_assign_func func; ++ int min_value; ++ int max_value; ++}; ++ ++static struct enfs_config_info g_enfs_config_info; ++static struct timespec64 modify_time; ++static struct task_struct *thread; ++ ++static int enfs_check_config_value(char *value, int min_value, int max_value) ++{ ++ unsigned long num_value; ++ int ret; ++ ++ ret = kstrtol(value, 10, &num_value); ++ if (ret != 0) { ++ enfs_log_error("Failed to convert string to int\n"); ++ return -EINVAL; ++ } ++ ++ if (num_value < min_value || num_value > max_value) ++ return -EINVAL; ++ ++ return num_value; ++} ++ ++static int32_t enfs_check_and_assign_int_value(char *field_name, char *value, ++ int min_value, int max_value) ++{ ++ int int_value = enfs_check_config_value(value, min_value, max_value); ++ ++ if (int_value < 0) ++ return -EINVAL; ++ ++ if (strcmp(field_name, "path_detect_interval") == 0) { ++ g_enfs_config_info.path_detect_interval = int_value; ++ return ENFS_RET_OK; ++ } ++ if (strcmp(field_name, "path_detect_timeout") == 0) { ++ g_enfs_config_info.path_detect_timeout = int_value; ++ return ENFS_RET_OK; ++ } ++ if (strcmp(field_name, "multipath_timeout") == 0) { ++ g_enfs_config_info.multipath_timeout = int_value; ++ return ENFS_RET_OK; ++ } ++ if (strcmp(field_name, "multipath_disable") == 0) { ++ g_enfs_config_info.multipath_state = int_value; ++ return ENFS_RET_OK; ++ } ++ return -EINVAL; ++} ++ ++static int32_t enfs_check_and_assign_loadbalance_mode(char *field_name, ++ char *value, ++ int min_value, ++ int max_value) ++{ ++ if (value == NULL) ++ return -EINVAL; ++ ++ if (strcmp(field_name, "multipath_select_policy") == 0) { ++ if (strcmp(value, "roundrobin") == 0) { ++ g_enfs_config_info.loadbalance_mode ++ = ENFS_LOADBALANCE_RR; ++ return ENFS_RET_OK; ++ } ++ } ++ return -EINVAL; ++} ++ ++static const struct check_and_assign_value g_check_and_assign_value[] = { ++ {"path_detect_interval", enfs_check_and_assign_int_value, ++ MIN_PATH_DETECT_INTERVAL, MAX_PATH_DETECT_INTERVAL}, ++ {"path_detect_timeout", enfs_check_and_assign_int_value, ++ MIN_PATH_DETECT_TIMEOUT, MAX_PATH_DETECT_TIMEOUT}, ++ {"multipath_timeout", enfs_check_and_assign_int_value, ++ MIN_MULTIPATH_TIMEOUT, MAX_MULTIPATH_TIMEOUT}, ++ {"multipath_disable", enfs_check_and_assign_int_value, ++ MIN_MULTIPATH_STATE, MAX_MULTIPATH_STATE}, ++ {"multipath_select_policy", enfs_check_and_assign_loadbalance_mode, ++ 0, 0}, ++}; ++ ++static int32_t enfs_read_config_file(char *buffer, char *file_path) ++{ ++ int ret; ++ struct file *filp = NULL; ++ loff_t f_pos = 0; ++ mm_segment_t fs; ++ ++ ++ filp = filp_open(file_path, O_RDONLY, 0); ++ ++ if (IS_ERR(filp)) { ++ enfs_log_error("Failed to open file %s\n", CONFIG_FILE_PATH); ++ ret = -ENOENT; ++ return ret; ++ } ++ ++ fs = get_fs(); ++ set_fs(get_ds()); ++ kernel_read(filp, buffer, MAX_FILE_SIZE, &f_pos); ++ set_fs(fs); ++ ++ ret = filp_close(filp, NULL); ++ if (ret) { ++ enfs_log_error("Close File:%s failed:%d.\n", ++ CONFIG_FILE_PATH, ret); ++ return -EINVAL; ++ } ++ return ENFS_RET_OK; ++} ++ ++static int32_t enfs_deal_with_comment_line(char *buffer) ++{ ++ int ret; ++ char *pos = strchr(buffer, '\n'); ++ ++ if (pos != NULL) ++ ret = strlen(buffer) - strlen(pos); ++ else ++ ret = strlen(buffer); ++ ++ return ret; ++} ++ ++static int32_t enfs_parse_key_value_from_config(char *buffer, char *key, ++ char *value, int keyLen, ++ int valueLen) ++{ ++ char *line; ++ char *tokenPtr; ++ int len; ++ char *tem; ++ char *pos = strchr(buffer, '\n'); ++ ++ if (pos != NULL) ++ len = strlen(buffer) - strlen(pos); ++ else ++ len = strlen(buffer); ++ ++ line = kmalloc(len + 1, GFP_KERNEL); ++ if (!line) { ++ enfs_log_error("Failed to allocate memory.\n"); ++ return -ENOMEM; ++ } ++ line[len] = '\0'; ++ strncpy(line, buffer, len); ++ ++ tem = line; ++ tokenPtr = strsep(&tem, "="); ++ if (tokenPtr == NULL || tem == NULL) { ++ kfree(line); ++ return len; ++ } ++ strncpy(key, strim(tokenPtr), keyLen); ++ strncpy(value, strim(tem), valueLen); ++ ++ kfree(line); ++ return len; ++} ++ ++static int32_t enfs_get_value_from_config_file(char *buffer, char *field_name, ++ char *value, int valueLen) ++{ ++ int ret; ++ char key[STRING_BUF_SIZE + 1] = {0}; ++ char val[STRING_BUF_SIZE + 1] = {0}; ++ ++ while (buffer[0] != '\0') { ++ if (buffer[0] == '\n') { ++ buffer++; ++ } else if (buffer[0] == '#') { ++ ret = enfs_deal_with_comment_line(buffer); ++ if (ret > 0) ++ buffer += ret; ++ } else { ++ ret = enfs_parse_key_value_from_config(buffer, key, val, ++ STRING_BUF_SIZE, ++ STRING_BUF_SIZE); ++ if (ret < 0) { ++ enfs_log_error("failed parse key value, %d\n" ++ , ret); ++ return ret; ++ } ++ key[STRING_BUF_SIZE] = '\0'; ++ val[STRING_BUF_SIZE] = '\0'; ++ ++ buffer += ret; ++ ++ if (strcmp(field_name, key) == 0) { ++ strncpy(value, val, valueLen); ++ return ENFS_RET_OK; ++ } ++ } ++ } ++ enfs_log_error("can not find value which matched field_name: %s.\n", ++ field_name); ++ return -EINVAL; ++} ++ ++int32_t enfs_config_load(void) ++{ ++ char value[STRING_BUF_SIZE + 1]; ++ int ret; ++ int table_len; ++ int min; ++ int max; ++ int i; ++ char *buffer; ++ ++ buffer = kmalloc(MAX_FILE_SIZE, GFP_KERNEL); ++ if (!buffer) { ++ enfs_log_error("Failed to allocate memory.\n"); ++ return -ENOMEM; ++ } ++ memset(buffer, 0, MAX_FILE_SIZE); ++ ++ g_enfs_config_info.path_detect_interval = DEFAULT_PATH_DETECT_INTERVAL; ++ g_enfs_config_info.path_detect_timeout = DEFAULT_PATH_DETECT_TIMEOUT; ++ g_enfs_config_info.multipath_timeout = DEFAULT_MULTIPATH_TIMEOUT; ++ g_enfs_config_info.multipath_state = DEFAULT_MULTIPATH_STATE; ++ g_enfs_config_info.loadbalance_mode = DEFAULT_LOADBALANCE_MODE; ++ ++ table_len = sizeof(g_check_and_assign_value) / ++ sizeof(g_check_and_assign_value[0]); ++ ++ ret = enfs_read_config_file(buffer, CONFIG_FILE_PATH); ++ if (ret != 0) { ++ kfree(buffer); ++ return ret; ++ } ++ ++ for (i = 0; i < table_len; i++) { ++ ret = enfs_get_value_from_config_file(buffer, ++ g_check_and_assign_value[i].field_name, ++ value, STRING_BUF_SIZE); ++ if (ret < 0) ++ continue; ++ ++ value[STRING_BUF_SIZE] = '\0'; ++ min = g_check_and_assign_value[i].min_value; ++ max = g_check_and_assign_value[i].max_value; ++ if (g_check_and_assign_value[i].func != NULL) ++ (*g_check_and_assign_value[i].func)( ++ g_check_and_assign_value[i].field_name, ++ value, min, max); ++ } ++ ++ kfree(buffer); ++ return ENFS_RET_OK; ++} ++ ++int32_t enfs_get_config_path_detect_interval(void) ++{ ++ return g_enfs_config_info.path_detect_interval; ++} ++ ++int32_t enfs_get_config_path_detect_timeout(void) ++{ ++ return g_enfs_config_info.path_detect_timeout; ++} ++ ++int32_t enfs_get_config_multipath_timeout(void) ++{ ++ return g_enfs_config_info.multipath_timeout; ++} ++ ++int32_t enfs_get_config_multipath_state(void) ++{ ++ return g_enfs_config_info.multipath_state; ++} ++ ++int32_t enfs_get_config_loadbalance_mode(void) ++{ ++ return g_enfs_config_info.loadbalance_mode; ++} ++ ++static bool enfs_file_changed(const char *filename) ++{ ++ int err; ++ struct kstat file_stat; ++ ++ err = vfs_stat(filename, &file_stat); ++ if (err) { ++ pr_err("failed to open file:%s err:%d\n", filename, err); ++ return false; ++ } ++ ++ if (timespec64_compare(&modify_time, &file_stat.mtime) == -1) { ++ modify_time = file_stat.mtime; ++ pr_info("file change: %lld %lld\n", modify_time.tv_sec, ++ file_stat.mtime.tv_sec); ++ return true; ++ } ++ ++ return false; ++} ++ ++static int enfs_thread_func(void *data) ++{ ++ while (!kthread_should_stop()) { ++ if (enfs_file_changed(CONFIG_FILE_PATH)) ++ enfs_config_load(); ++ ++ msleep(ENFS_NOTIFY_FILE_PERIOD); ++ } ++ return 0; ++} ++ ++int enfs_config_timer_init(void) ++{ ++ thread = kthread_run(enfs_thread_func, NULL, "enfs_notiy_file_thread"); ++ if (IS_ERR(thread)) { ++ pr_err("Failed to create kernel thread\n"); ++ return PTR_ERR(thread); ++ } ++ return 0; ++} ++ ++void enfs_config_timer_exit(void) ++{ ++ pr_info("enfs_notify_file_exit\n"); ++ if (thread) ++ kthread_stop(thread); ++} +diff --git a/fs/nfs/enfs/enfs_config.h b/fs/nfs/enfs/enfs_config.h +new file mode 100644 +index 000000000000..752710129170 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_config.h +@@ -0,0 +1,32 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs configuration ++ * Author: y00583252 ++ * Create: 2023-07-27 ++ */ ++ ++#ifndef ENFS_CONFIG_H ++#define ENFS_CONFIG_H ++ ++#include <linux/types.h> ++ ++enum enfs_multipath_state { ++ ENFS_MULTIPATH_ENABLE = 0, ++ ENFS_MULTIPATH_DISABLE = 1, ++}; ++ ++enum enfs_loadbalance_mode { ++ ENFS_LOADBALANCE_RR, ++}; ++ ++ ++int32_t enfs_get_config_path_detect_interval(void); ++int32_t enfs_get_config_path_detect_timeout(void); ++int32_t enfs_get_config_multipath_timeout(void); ++int32_t enfs_get_config_multipath_state(void); ++int32_t enfs_get_config_loadbalance_mode(void); ++int32_t enfs_config_load(void); ++int32_t enfs_config_timer_init(void); ++void enfs_config_timer_exit(void); ++#endif // ENFS_CONFIG_H +diff --git a/fs/nfs/enfs/enfs_errcode.h b/fs/nfs/enfs/enfs_errcode.h +new file mode 100644 +index 000000000000..cca47ab9a191 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_errcode.h +@@ -0,0 +1,17 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs errocode ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef ENFS_ERRCODE_H ++#define ENFS_ERRCODE_H ++ ++enum { ++ ENFS_RET_OK = 0, ++ ENFS_RET_FAIL ++}; ++ ++#endif // ENFS_ERRCODE_H +diff --git a/fs/nfs/enfs/enfs_log.h b/fs/nfs/enfs/enfs_log.h +new file mode 100644 +index 000000000000..177b404f05df +--- /dev/null ++++ b/fs/nfs/enfs/enfs_log.h +@@ -0,0 +1,25 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: enfs log ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++#ifndef ENFS_LOG_H ++#define ENFS_LOG_H ++ ++#include <linux/printk.h> ++ ++#define enfs_log_info(fmt, ...) \ ++ pr_info("enfs:[%s]" pr_fmt(fmt), \ ++ __func__, ##__VA_ARGS__) ++ ++#define enfs_log_error(fmt, ...) \ ++ pr_err("enfs:[%s]" pr_fmt(fmt), \ ++ __func__, ##__VA_ARGS__) ++ ++#define enfs_log_debug(fmt, ...) \ ++ pr_debug("enfs:[%s]" pr_fmt(fmt), \ ++ __func__, ##__VA_ARGS__) ++ ++#endif // ENFS_ERRCODE_H +diff --git a/fs/nfs/enfs/failover_com.h b/fs/nfs/enfs/failover_com.h +new file mode 100644 +index 000000000000..c52940da232e +--- /dev/null ++++ b/fs/nfs/enfs/failover_com.h +@@ -0,0 +1,23 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: failover time commont header file ++ * Create: 2023-08-02 ++ */ ++#ifndef FAILOVER_COMMON_H ++#define FAILOVER_COMMON_H ++ ++static inline bool failover_is_enfs_clnt(struct rpc_clnt *clnt) ++{ ++ struct rpc_clnt *next = clnt->cl_parent; ++ ++ while (next) { ++ if (next == next->cl_parent) ++ break; ++ next = next->cl_parent; ++ } ++ ++ return next != NULL ? next->cl_enfs : clnt->cl_enfs; ++} ++ ++#endif // FAILOVER_COMMON_H +diff --git a/fs/nfs/enfs/failover_path.c b/fs/nfs/enfs/failover_path.c +new file mode 100644 +index 000000000000..93b454de29d1 +--- /dev/null ++++ b/fs/nfs/enfs/failover_path.c +@@ -0,0 +1,207 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs path failover file ++ * Author: y00583252 ++ * Create: 2023-08-02 ++ */ ++ ++#include "failover_path.h" ++#include <linux/nfs.h> ++#include <linux/nfs3.h> ++#include <linux/nfs4.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/sched.h> ++#include <linux/sunrpc/xprt.h> ++#include "enfs_config.h" ++#include "enfs_log.h" ++#include "failover_com.h" ++#include "pm_state.h" ++#include "pm_ping.h" ++ ++enum failover_policy_t { ++ FAILOVER_NOACTION = 1, ++ FAILOVER_RETRY, ++ FAILOVER_RETRY_DELAY, ++}; ++ ++static void failover_retry_path(struct rpc_task *task) ++{ ++ xprt_release(task); ++ rpc_init_task_retry_counters(task); ++ rpc_task_release_transport(task); ++ rpc_restart_call(task); ++} ++ ++static void failover_retry_path_delay(struct rpc_task *task, int32_t delay) ++{ ++ failover_retry_path(task); ++ rpc_delay(task, delay); ++} ++ ++static void failover_retry_path_by_policy(struct rpc_task *task, ++ enum failover_policy_t policy) ++{ ++ if (policy == FAILOVER_RETRY) ++ failover_retry_path(task); ++ else if (policy == FAILOVER_RETRY_DELAY) ++ failover_retry_path_delay(task, 3 * HZ); // delay 3s ++} ++ ++static ++enum failover_policy_t failover_get_nfs3_retry_policy(struct rpc_task *task) ++{ ++ enum failover_policy_t policy = FAILOVER_NOACTION; ++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; ++ u32 proc; ++ ++ if (unlikely(procinfo == NULL)) { ++ enfs_log_error("the task contains no valid proc.\n"); ++ return FAILOVER_NOACTION; ++ } ++ ++ proc = procinfo->p_proc; ++ ++ switch (proc) { ++ case NFS3PROC_CREATE: ++ case NFS3PROC_MKDIR: ++ case NFS3PROC_REMOVE: ++ case NFS3PROC_RMDIR: ++ case NFS3PROC_SYMLINK: ++ case NFS3PROC_LINK: ++ case NFS3PROC_SETATTR: ++ case NFS3PROC_WRITE: ++ policy = FAILOVER_RETRY_DELAY; ++ default: ++ policy = FAILOVER_RETRY; ++ } ++ return policy; ++} ++ ++static ++enum failover_policy_t failover_get_nfs4_retry_policy(struct rpc_task *task) ++{ ++ enum failover_policy_t policy = FAILOVER_NOACTION; ++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; ++ u32 proc_idx; ++ ++ if (unlikely(procinfo == NULL)) { ++ enfs_log_error("the task contains no valid proc.\n"); ++ return FAILOVER_NOACTION; ++ } ++ ++ proc_idx = procinfo->p_statidx; ++ ++ switch (proc_idx) { ++ case NFSPROC4_CLNT_CREATE: ++ case NFSPROC4_CLNT_REMOVE: ++ case NFSPROC4_CLNT_LINK: ++ case NFSPROC4_CLNT_SYMLINK: ++ case NFSPROC4_CLNT_SETATTR: ++ case NFSPROC4_CLNT_WRITE: ++ case NFSPROC4_CLNT_RENAME: ++ case NFSPROC4_CLNT_SETACL: ++ policy = FAILOVER_RETRY_DELAY; ++ default: ++ policy = FAILOVER_RETRY; ++ } ++ return policy; ++} ++ ++static enum failover_policy_t failover_get_retry_policy(struct rpc_task *task) ++{ ++ struct rpc_clnt *clnt = task->tk_client; ++ u32 version = clnt->cl_vers; ++ enum failover_policy_t policy = FAILOVER_NOACTION; ++ ++ // 1. if the task meant to send to certain xprt, take no action ++ if (task->tk_flags & RPC_TASK_FIXED) ++ return FAILOVER_NOACTION; ++ ++ // 2. get policy by different version of nfs protocal ++ if (version == 3) // nfs v3 ++ policy = failover_get_nfs3_retry_policy(task); ++ else if (version == 4) // nfs v4 ++ policy = failover_get_nfs4_retry_policy(task); ++ else ++ return FAILOVER_NOACTION; ++ ++ // 3. if the task is not send to target, retry immediately ++ if (!RPC_WAS_SENT(task)) ++ policy = FAILOVER_RETRY; ++ ++ return policy; ++} ++ ++static int failover_check_task(struct rpc_task *task) ++{ ++ struct rpc_clnt *clnt = NULL; ++ int disable_mpath = enfs_get_config_multipath_state(); ++ ++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return -EINVAL; ++ } ++ ++ if (unlikely((task == NULL) || (task->tk_client == NULL))) { ++ enfs_log_error("The task is not valid.\n"); ++ return -EINVAL; ++ } ++ ++ clnt = task->tk_client; ++ ++ if (clnt->cl_prog != NFS_PROGRAM) { ++ enfs_log_debug("The clnt is not prog{%u} type.\n", ++ clnt->cl_prog); ++ return -EINVAL; ++ } ++ ++ if (!failover_is_enfs_clnt(clnt)) { ++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); ++ return -EINVAL; ++ } ++ return 0; ++} ++ ++void failover_handle(struct rpc_task *task) ++{ ++ enum failover_policy_t policy; ++ int ret; ++ ++ ret = failover_check_task(task); ++ if (ret != 0) ++ return; ++ ++ pm_set_path_state(task->tk_xprt, PM_STATE_FAULT); ++ ++ policy = failover_get_retry_policy(task); ++ ++ failover_retry_path_by_policy(task, policy); ++} ++ ++bool failover_task_need_call_start_again(struct rpc_task *task) ++{ ++ int ret; ++ ++ ret = failover_check_task(task); ++ if (ret != 0) ++ return false; ++ ++ return true; ++} ++ ++bool failover_prepare_transmit(struct rpc_task *task) ++{ ++ if (task->tk_flags & RPC_TASK_FIXED) ++ return true; ++ ++ if (pm_ping_is_test_xprt_task(task)) ++ return true; ++ ++ if (pm_get_path_state(task->tk_xprt) == PM_STATE_FAULT) { ++ task->tk_status = -ETIMEDOUT; ++ return false; ++ } ++ ++ return true; ++} +diff --git a/fs/nfs/enfs/failover_path.h b/fs/nfs/enfs/failover_path.h +new file mode 100644 +index 000000000000..6f1294829a6e +--- /dev/null ++++ b/fs/nfs/enfs/failover_path.h +@@ -0,0 +1,17 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs path failover header file ++ * Author: y00583252 ++ * Create: 2023-08-02 ++ */ ++ ++#ifndef FAILOVER_PATH_H ++#define FAILOVER_PATH_H ++ ++#include <linux/sunrpc/sched.h> ++ ++void failover_handle(struct rpc_task *task); ++bool failover_prepare_transmit(struct rpc_task *task); ++ ++#endif // FAILOVER_PATH_H +diff --git a/fs/nfs/enfs/failover_time.c b/fs/nfs/enfs/failover_time.c +new file mode 100644 +index 000000000000..866ea82d13fc +--- /dev/null ++++ b/fs/nfs/enfs/failover_time.c +@@ -0,0 +1,99 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: failover time file ++ * Create: 2023-08-02 ++ */ ++ ++#include "failover_time.h" ++#include <linux/jiffies.h> ++#include <linux/sunrpc/clnt.h> ++#include "enfs_config.h" ++#include "enfs_log.h" ++#include "failover_com.h" ++#include "pm_ping.h" ++ ++static unsigned long failover_get_mulitipath_timeout(struct rpc_clnt *clnt) ++{ ++ unsigned long config_tmo = enfs_get_config_multipath_timeout() * HZ; ++ unsigned long clnt_tmo = clnt->cl_timeout->to_initval; ++ ++ if (config_tmo == 0) ++ return clnt_tmo; ++ ++ return config_tmo > clnt_tmo ? clnt_tmo : config_tmo; ++} ++ ++void failover_adjust_task_timeout(struct rpc_task *task, void *condition) ++{ ++ struct rpc_clnt *clnt = NULL; ++ unsigned long tmo; ++ int disable_mpath = enfs_get_config_multipath_state(); ++ ++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return; ++ } ++ ++ clnt = task->tk_client; ++ if (unlikely(clnt == NULL)) { ++ enfs_log_error("task associate client is NULL.\n"); ++ return; ++ } ++ ++ if (!failover_is_enfs_clnt(clnt)) { ++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); ++ return; ++ } ++ ++ tmo = failover_get_mulitipath_timeout(clnt); ++ if (tmo == 0) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return; ++ } ++ ++ if (task->tk_timeout != 0) ++ task->tk_timeout = ++ task->tk_timeout < tmo ? task->tk_timeout : tmo; ++ else ++ task->tk_timeout = tmo; ++} ++ ++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req) ++{ ++ struct rpc_clnt *clnt = NULL; ++ int disable_mpath = enfs_get_config_multipath_state(); ++ ++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return; ++ } ++ ++ clnt = task->tk_client; ++ if (unlikely(clnt == NULL)) { ++ enfs_log_error("task associate client is NULL.\n"); ++ return; ++ } ++ ++ if (!failover_is_enfs_clnt(clnt)) { ++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); ++ return; ++ } ++ ++ if (!pm_ping_is_test_xprt_task(task)) ++ req->rq_timeout = failover_get_mulitipath_timeout(clnt); ++ else { ++ req->rq_timeout = enfs_get_config_path_detect_timeout() * HZ; ++ req->rq_majortimeo = req->rq_timeout + jiffies; ++ } ++ ++ /* ++ * when task is retried, the req is new, we lost major-timeout times, ++ * so we have to restore req major ++ * timeouts from the task, if it is stored. ++ */ ++ if (task->tk_major_timeo != 0) ++ req->rq_majortimeo = task->tk_major_timeo; ++ else ++ task->tk_major_timeo = req->rq_majortimeo; ++} +diff --git a/fs/nfs/enfs/failover_time.h b/fs/nfs/enfs/failover_time.h +new file mode 100644 +index 000000000000..ede25b577a2a +--- /dev/null ++++ b/fs/nfs/enfs/failover_time.h +@@ -0,0 +1,16 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: failover time header file ++ * Create: 2023-08-02 ++ */ ++ ++#ifndef FAILOVER_TIME_H ++#define FAILOVER_TIME_H ++ ++#include <linux/sunrpc/sched.h> ++ ++void failover_adjust_task_timeout(struct rpc_task *task, void *condition); ++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req); ++ ++#endif // FAILOVER_TIME_H +diff --git a/fs/nfs/enfs/init.h b/fs/nfs/enfs/init.h +new file mode 100644 +index 000000000000..fdabb9084e19 +--- /dev/null ++++ b/fs/nfs/enfs/init.h +@@ -0,0 +1,17 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs client init ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef ENFS_INIT_H ++#define ENFS_INIT_H ++ ++#include <linux/types.h> ++ ++int32_t enfs_init(void); ++void enfs_fini(void); ++ ++#endif +diff --git a/fs/nfs/enfs/mgmt_init.c b/fs/nfs/enfs/mgmt_init.c +new file mode 100644 +index 000000000000..75a40c5e0f6c +--- /dev/null ++++ b/fs/nfs/enfs/mgmt_init.c +@@ -0,0 +1,22 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: mgmt component init ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#include "mgmt_init.h" ++#include <linux/printk.h> ++#include "enfs_errcode.h" ++#include "enfs_config.h" ++ ++int32_t mgmt_init(void) ++{ ++ return enfs_config_timer_init(); ++} ++ ++void mgmt_fini(void) ++{ ++ enfs_config_timer_exit(); ++} +diff --git a/fs/nfs/enfs/mgmt_init.h b/fs/nfs/enfs/mgmt_init.h +new file mode 100644 +index 000000000000..aa78303b9f01 +--- /dev/null ++++ b/fs/nfs/enfs/mgmt_init.h +@@ -0,0 +1,18 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: mgmt component init ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef MGMT_INIT_H ++#define MGMT_INIT_H ++ ++#include <linux/types.h> ++ ++int32_t mgmt_init(void); ++void mgmt_fini(void); ++ ++ ++#endif // MGMT_INIT_H +diff --git a/fs/nfs/enfs/pm_ping.c b/fs/nfs/enfs/pm_ping.c +new file mode 100644 +index 000000000000..24153cd4c7f3 +--- /dev/null ++++ b/fs/nfs/enfs/pm_ping.c +@@ -0,0 +1,421 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: path state header file ++ * Author: x00833432 ++ * Create: 2023-08-21 ++ */ ++ ++#include "pm_ping.h" ++#include <linux/err.h> ++#include <linux/spinlock.h> ++#include <linux/slab.h> ++#include <linux/module.h> ++#include <linux/printk.h> ++#include <linux/kthread.h> ++#include <linux/nfs.h> ++#include <linux/errno.h> ++#include <linux/rcupdate.h> ++#include <linux/workqueue.h> ++#include <net/netns/generic.h> ++#include <linux/atomic.h> ++#include <linux/sunrpc/clnt.h> ++ ++#include "../../../net/sunrpc/netns.h" ++#include "pm_state.h" ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_config.h" ++ ++#define SLEEP_INTERVAL 2 ++extern unsigned int sunrpc_net_id; ++ ++static struct task_struct *pm_ping_timer_thread; ++//protect pint_execute_workq ++static spinlock_t ping_execute_workq_lock; ++// timer for test xprt workqueue ++static struct workqueue_struct *ping_execute_workq; ++// count the ping xprt work on flight ++static atomic_t check_xprt_count; ++ ++struct ping_xprt_work { ++ struct rpc_xprt *xprt; // use this specific xprt ++ struct rpc_clnt *clnt; // use this specific rpc_client ++ struct work_struct ping_work; ++}; ++ ++struct pm_ping_async_callback { ++ void *data; ++ void (*func)(void *data); ++}; ++ ++// set xprt's enum pm_check_state ++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, ++ enum pm_check_state state) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ ++ if (IS_ERR(xprt)) { ++ enfs_log_error("The xprt ptr is not exist.\n"); ++ return; ++ } ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ xprt_get(xprt); ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ xprt_put(xprt); ++ return; ++ } ++ ++ atomic_set(&ctx->path_check_state, state); ++ xprt_put(xprt); ++} ++ ++// get xprt's enum pm_check_state ++static enum pm_check_state pm_ping_get_path_check_state(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ enum pm_check_state state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return PM_CHECK_UNDEFINE; ++ } ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ return PM_CHECK_UNDEFINE; ++ } ++ ++ state = atomic_read(&ctx->path_check_state); ++ ++ return state; ++} ++ ++static void pm_ping_call_done_callback(void *data) ++{ ++ struct pm_ping_async_callback *callback_data = ++ (struct pm_ping_async_callback *)data; ++ ++ if (callback_data == NULL) ++ return; ++ ++ callback_data->func(callback_data->data); ++ ++ kfree(callback_data); ++} ++ ++// Default callback for async RPC calls ++static void pm_ping_call_done(struct rpc_task *task, void *data) ++{ ++ struct rpc_xprt *xprt = task->tk_xprt; ++ ++ atomic_dec(&check_xprt_count); ++ if (task->tk_status >= 0) ++ pm_set_path_state(xprt, PM_STATE_NORMAL); ++ else ++ pm_set_path_state(xprt, PM_STATE_FAULT); ++ ++ pm_ping_set_path_check_state(xprt, PM_CHECK_FINISH); ++ ++ pm_ping_call_done_callback(data); ++} ++ ++// register func to rpc_call_done ++static const struct rpc_call_ops pm_ping_set_status_ops = { ++ .rpc_call_done = pm_ping_call_done, ++}; ++ ++// execute work which in work_queue ++static void pm_ping_execute_work(struct work_struct *work) ++{ ++ int ret = 0; ++ ++ // get the work information ++ struct ping_xprt_work *work_info = ++ container_of(work, struct ping_xprt_work, ping_work); ++ ++ // if check state is pending ++ if (pm_ping_get_path_check_state(work_info->xprt) == PM_CHECK_WAITING) { ++ ++ pm_ping_set_path_check_state(work_info->xprt, ++ PM_CHECK_CHECKING); ++ ++ ret = rpc_clnt_test_xprt(work_info->clnt, ++ work_info->xprt, ++ &pm_ping_set_status_ops, ++ NULL, ++ RPC_TASK_ASYNC | RPC_TASK_FIXED); ++ ++ if (ret < 0) { ++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); ++ ++ pm_ping_set_path_check_state(work_info->xprt, ++ PM_CHECK_FINISH); ++ ++ } else ++ atomic_inc(&check_xprt_count); ++ ++ } ++ ++ atomic_dec(&work_info->clnt->cl_count); ++ xprt_put(work_info->xprt); ++ kfree(work_info); ++ work_info = NULL; ++} ++ ++static bool pm_ping_workqueue_queue_work(struct work_struct *work) ++{ ++ bool ret = false; ++ ++ spin_lock(&ping_execute_workq_lock); ++ ++ if (ping_execute_workq != NULL) ++ ret = queue_work(ping_execute_workq, work); ++ ++ spin_unlock(&ping_execute_workq_lock); ++ return ret; ++} ++ ++// init test work and add this work to workqueue ++static int pm_ping_add_work(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, void *data) ++{ ++ struct ping_xprt_work *work_info; ++ bool ret = false; ++ ++ if (IS_ERR(xprt) || xprt == NULL) { ++ enfs_log_error("The xprt ptr is not exist.\n"); ++ return -EINVAL; ++ } ++ ++ if (IS_ERR(clnt) || clnt == NULL) { ++ enfs_log_error("The clnt ptr is not exist.\n"); ++ return -EINVAL; ++ } ++ ++ if (!xprt->multipath_context) { ++ enfs_log_error("multipath_context is null.\n"); ++ return -EINVAL; ++ } ++ ++ // check xprt pending status, if pending status equals Finish ++ // means this xprt can inster to work queue ++ if (pm_ping_get_path_check_state(xprt) == ++ PM_CHECK_FINISH || ++ pm_ping_get_path_check_state(xprt) == ++ PM_CHECK_INIT) { ++ ++ enfs_log_debug("find xprt pointer. %p\n", xprt); ++ work_info = kzalloc(sizeof(struct ping_xprt_work), GFP_ATOMIC); ++ if (work_info == NULL) ++ return -ENOMEM; ++ work_info->clnt = clnt; ++ atomic_inc(&clnt->cl_count); ++ work_info->xprt = xprt; ++ xprt_get(xprt); ++ INIT_WORK(&work_info->ping_work, pm_ping_execute_work); ++ pm_ping_set_path_check_state(xprt, PM_CHECK_WAITING); ++ ++ ret = pm_ping_workqueue_queue_work(&work_info->ping_work); ++ if (!ret) { ++ atomic_dec(&work_info->clnt->cl_count); ++ xprt_put(work_info->xprt); ++ kfree(work_info); ++ return -EINVAL; ++ } ++ } ++ return 0; ++} ++ ++// encapsulate pm_ping_add_work() ++static int pm_ping_execute_xprt_test(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, void *data) ++{ ++ pm_ping_add_work(clnt, xprt, NULL); ++ // return 0 for rpc_clnt_iterate_for_each_xprt(); ++ // because negative value will stop iterate all xprt ++ // and we need return negative value for debug ++ // Therefore, we need this function to iterate all xprt ++ return 0; ++} ++ ++// export to other module add ping work to workqueue ++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) ++{ ++ int ret; ++ ++ ret = pm_ping_add_work(clnt, xprt, NULL); ++ return ret; ++} ++ ++// iterate xprt in the client ++static void pm_ping_loop_rpclnt(struct sunrpc_net *sn) ++{ ++ struct rpc_clnt *clnt; ++ ++ spin_lock(&sn->rpc_client_lock); ++ list_for_each_entry_rcu(clnt, &sn->all_clients, cl_clients) { ++ if (clnt->cl_enfs) { ++ enfs_log_debug("find rpc_clnt. %p\n", clnt); ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ pm_ping_execute_xprt_test, NULL); ++ } ++ } ++ spin_unlock(&sn->rpc_client_lock); ++} ++ ++// iterate each clnt in the sunrpc_net ++static void pm_ping_loop_sunrpc_net(void) ++{ ++ struct net *net; ++ struct sunrpc_net *sn; ++ ++ rcu_read_lock(); ++ for_each_net_rcu(net) { ++ sn = net_generic(net, sunrpc_net_id); ++ if (sn == NULL) ++ continue; ++ pm_ping_loop_rpclnt(sn); ++ } ++ rcu_read_unlock(); ++} ++ ++static int pm_ping_routine(void *data) ++{ ++ while (!kthread_should_stop()) { ++ // equale 0 means open multipath ++ if (enfs_get_config_multipath_state() == ++ ENFS_MULTIPATH_ENABLE) ++ pm_ping_loop_sunrpc_net(); ++ ++ msleep((unsigned int) ++ enfs_get_config_path_detect_interval() * 1000); ++ } ++ return 0; ++} ++ ++// start thread to cycly ping ++static int pm_ping_start(void) ++{ ++ pm_ping_timer_thread = ++ kthread_run(pm_ping_routine, NULL, "pm_ping_routine"); ++ if (IS_ERR(pm_ping_timer_thread)) { ++ enfs_log_error("Failed to create kernel thread\n"); ++ return PTR_ERR(pm_ping_timer_thread); ++ } ++ return 0; ++} ++ ++// initialize workqueue ++static int pm_ping_workqueue_init(void) ++{ ++ struct workqueue_struct *queue = NULL; ++ ++ queue = create_workqueue("pm_ping_workqueue"); ++ ++ if (queue == NULL) { ++ enfs_log_error("create workqueue failed.\n"); ++ return -ENOMEM; ++ } ++ ++ spin_lock(&ping_execute_workq_lock); ++ ping_execute_workq = queue; ++ spin_unlock(&ping_execute_workq_lock); ++ enfs_log_info("create workqueue succeeeded.\n"); ++ return 0; ++} ++ ++static void pm_ping_workqueue_fini(void) ++{ ++ struct workqueue_struct *queue = NULL; ++ ++ spin_lock(&ping_execute_workq_lock); ++ queue = ping_execute_workq; ++ ping_execute_workq = NULL; ++ spin_unlock(&ping_execute_workq_lock); ++ ++ enfs_log_info("delete work queue\n"); ++ ++ if (queue != NULL) { ++ flush_workqueue(queue); ++ destroy_workqueue(queue); ++ } ++} ++ ++// module exit func ++void pm_ping_fini(void) ++{ ++ if (pm_ping_timer_thread) ++ kthread_stop(pm_ping_timer_thread); ++ ++ pm_ping_workqueue_fini(); ++ ++ while (atomic_read(&check_xprt_count) != 0) ++ msleep(SLEEP_INTERVAL); ++} ++ ++// module init func ++int pm_ping_init(void) ++{ ++ int ret; ++ ++ atomic_set(&check_xprt_count, 0); ++ ret = pm_ping_workqueue_init(); ++ if (ret != 0) { ++ enfs_log_error("PM_PING Module loading failed.\n"); ++ return ret; ++ } ++ ret = pm_ping_start(); ++ if (ret != 0) { ++ enfs_log_error("PM_PING Module loading failed.\n"); ++ pm_ping_workqueue_fini(); ++ return ret; ++ } ++ ++ return ret; ++} ++ ++bool pm_ping_is_test_xprt_task(struct rpc_task *task) ++{ ++ return task->tk_ops == &pm_ping_set_status_ops ? true : false; ++} ++ ++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void (*func)(void *data), ++ void *data) ++{ ++ int ret; ++ ++ struct pm_ping_async_callback *callback_data = ++ kzalloc(sizeof(struct pm_ping_async_callback), GFP_KERNEL); ++ ++ if (callback_data == NULL) { ++ enfs_log_error("failed to mzalloc mem\n"); ++ return -ENOMEM; ++ } ++ ++ callback_data->data = data; ++ callback_data->func = func; ++ atomic_inc(&check_xprt_count); ++ ret = rpc_clnt_test_xprt(clnt, xprt, ++ &pm_ping_set_status_ops, ++ callback_data, ++ RPC_TASK_ASYNC | RPC_TASK_FIXED); ++ ++ if (ret < 0) { ++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); ++ atomic_dec(&check_xprt_count); ++ } ++ ++ return ret; ++} +diff --git a/fs/nfs/enfs/pm_ping.h b/fs/nfs/enfs/pm_ping.h +new file mode 100644 +index 000000000000..6bcb94bfc836 +--- /dev/null ++++ b/fs/nfs/enfs/pm_ping.h +@@ -0,0 +1,33 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs configuration ++ * Author: x00833432 ++ * Create: 2023-07-27 ++ */ ++ ++#ifndef PM_PING_H ++#define PM_PING_H ++ ++#include <linux/sunrpc/clnt.h> ++ ++enum pm_check_state { ++ PM_CHECK_INIT, // this xprt never been queued ++ PM_CHECK_WAITING, // this xprt waiting in the queue ++ PM_CHECK_CHECKING, // this xprt is testing ++ PM_CHECK_FINISH, // this xprt has been finished ++ PM_CHECK_UNDEFINE, // undefine multipath struct ++}; ++ ++int pm_ping_init(void); ++void pm_ping_fini(void); ++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); ++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, ++ enum pm_check_state state); ++bool pm_ping_is_test_xprt_task(struct rpc_task *task); ++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void (*func)(void *data), ++ void *data); ++ ++#endif // PM_PING_H +diff --git a/fs/nfs/enfs/pm_state.c b/fs/nfs/enfs/pm_state.c +new file mode 100644 +index 000000000000..220621a207a2 +--- /dev/null ++++ b/fs/nfs/enfs/pm_state.c +@@ -0,0 +1,158 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: path state file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++#include "pm_state.h" ++#include <linux/sunrpc/xprt.h> ++ ++#include "enfs.h" ++#include "enfs_log.h" ++ ++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ enum pm_path_state state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return PM_STATE_UNDEFINED; ++ } ++ ++ xprt_get(xprt); ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ xprt_put(xprt); ++ return PM_STATE_UNDEFINED; ++ } ++ ++ state = atomic_read(&ctx->path_state); ++ ++ xprt_put(xprt); ++ ++ return state; ++} ++ ++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ enum pm_path_state cur_state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ xprt_get(xprt); ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ xprt_put(xprt); ++ return; ++ } ++ ++ cur_state = atomic_read(&ctx->path_state); ++ if (cur_state == state) { ++ enfs_log_debug("The xprt is already {%d}.\n", state); ++ xprt_put(xprt); ++ return; ++ } ++ ++ atomic_set(&ctx->path_state, state); ++ enfs_log_info("The xprt {%p} path state change from {%d} to {%d}.\n", ++ xprt, cur_state, state); ++ ++ xprt_put(xprt); ++} ++ ++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len) ++{ ++ enum pm_path_state state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ if ((buf == NULL) || (len <= 0)) { ++ enfs_log_error("Buffer is not valid, len=%d.\n", len); ++ return; ++ } ++ ++ state = pm_get_path_state(xprt); ++ ++ switch (state) { ++ case PM_STATE_INIT: ++ (void)snprintf(buf, len, "Init"); ++ break; ++ case PM_STATE_NORMAL: ++ (void)snprintf(buf, len, "Normal"); ++ break; ++ case PM_STATE_FAULT: ++ (void)snprintf(buf, len, "Fault"); ++ break; ++ default: ++ (void)snprintf(buf, len, "Unknown"); ++ break; ++ } ++} ++ ++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len) ++{ ++ int i; ++ unsigned long state; ++ static unsigned long xprt_mask[] = { ++ XPRT_LOCKED, XPRT_CONNECTED, ++ XPRT_CONNECTING, XPRT_CLOSE_WAIT, ++ XPRT_BOUND, XPRT_BINDING, XPRT_CLOSING, ++ XPRT_CONGESTED}; ++ ++ static const char *const xprt_state_desc[] = { ++ "LOCKED", "CONNECTED", "CONNECTING", ++ "CLOSE_WAIT", "BOUND", "BINDING", ++ "CLOSING", "CONGESTED"}; ++ int pos = 0; ++ int ret = 0; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ if ((buf == NULL) || (len <= 0)) { ++ enfs_log_error( ++ "Xprt state buffer is not valid, len=%d.\n", ++ len); ++ return; ++ } ++ ++ xprt_get(xprt); ++ state = READ_ONCE(xprt->state); ++ xprt_put(xprt); ++ ++ for (i = 0; i < ARRAY_SIZE(xprt_mask); ++i) { ++ if (pos >= len) ++ break; ++ ++ if (!test_bit(xprt_mask[i], &state)) ++ continue; ++ ++ if (pos == 0) ++ ret = snprintf(buf, len, "%s", xprt_state_desc[i]); ++ else ++ ret = snprintf(buf + pos, len - pos, "|%s", ++ xprt_state_desc[i]); ++ ++ if (ret < 0) { ++ enfs_log_error("format state failed, ret %d.\n", ret); ++ break; ++ } ++ ++ pos += ret; ++ } ++} +diff --git a/fs/nfs/enfs/pm_state.h b/fs/nfs/enfs/pm_state.h +new file mode 100644 +index 000000000000..f5f52e5ab91d +--- /dev/null ++++ b/fs/nfs/enfs/pm_state.h +@@ -0,0 +1,28 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: path state header file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++ ++#ifndef PM_STATE_H ++#define PM_STATE_H ++ ++#include <linux/types.h> ++#include <linux/sunrpc/xprt.h> ++ ++enum pm_path_state { ++ PM_STATE_INIT, ++ PM_STATE_NORMAL, ++ PM_STATE_FAULT, ++ PM_STATE_UNDEFINED // xprt is not multipath xprt ++}; ++ ++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state); ++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt); ++ ++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len); ++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len); ++ ++#endif // PM_STATE_H diff --git a/0006-add_enfs_compile_option.patch b/0006-add_enfs_compile_option.patch new file mode 100644 index 0000000..ff3bc0e --- /dev/null +++ b/0006-add_enfs_compile_option.patch @@ -0,0 +1,70 @@ +diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig +index b04256636d4b..ae53510c0627 100644 +--- a/arch/arm64/configs/openeuler_defconfig ++++ b/arch/arm64/configs/openeuler_defconfig +@@ -5344,6 +5344,7 @@ CONFIG_LOCKD=m + CONFIG_LOCKD_V4=y + CONFIG_NFS_ACL_SUPPORT=m + CONFIG_NFS_COMMON=y ++# CONFIG_ENFS is not set + CONFIG_SUNRPC=m + CONFIG_SUNRPC_GSS=m + CONFIG_SUNRPC_BACKCHANNEL=y +diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig +index 59baeb2973af..ccc317f7fdb2 100644 +--- a/arch/x86/configs/openeuler_defconfig ++++ b/arch/x86/configs/openeuler_defconfig +@@ -6825,6 +6825,7 @@ CONFIG_LOCKD=m + CONFIG_LOCKD_V4=y + CONFIG_NFS_ACL_SUPPORT=m + CONFIG_NFS_COMMON=y ++CONFIG_ENFS=y + CONFIG_SUNRPC=m + CONFIG_SUNRPC_GSS=m + CONFIG_SUNRPC_BACKCHANNEL=y +diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig +index e55f86713948..872c9b7671b1 100644 +--- a/fs/nfs/Kconfig ++++ b/fs/nfs/Kconfig +@@ -196,3 +196,14 @@ config NFS_DEBUG + depends on NFS_FS && SUNRPC_DEBUG + select CRC32 + default y ++ ++config ENFS ++ tristate "NFS client support for ENFS" ++ depends on NFS_FS ++ default n ++ help ++ This option enables support multipath of the NFS protocol ++ in the kernel's NFS client. ++ This feature will improve performance and reliability. ++ ++ If sure, say Y. +diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile +index c587e3c4c6a6..19d0ac2ba3b8 100644 +--- a/fs/nfs/Makefile ++++ b/fs/nfs/Makefile +@@ -12,6 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ + nfs-$(CONFIG_ROOT_NFS) += nfsroot.o + nfs-$(CONFIG_SYSCTL) += sysctl.o + nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o ++nfs-$(CONFIG_ENFS) += enfs_adapter.o + + obj-$(CONFIG_NFS_V2) += nfsv2.o + nfsv2-y := nfs2super.o proc.o nfs2xdr.o +@@ -34,3 +35,5 @@ nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o + obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ + obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ + obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ ++ ++obj-$(CONFIG_ENFS) += enfs/ +diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile +index 090658c3da12..fe4e3b28c5d1 100644 +--- a/net/sunrpc/Makefile ++++ b/net/sunrpc/Makefile +@@ -19,3 +19,4 @@ sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o + sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o + sunrpc-$(CONFIG_PROC_FS) += stats.o + sunrpc-$(CONFIG_SYSCTL) += sysctl.o ++sunrpc-$(CONFIG_ENFS) += sunrpc_enfs_adapter.o -- 2.25.0.windows.1

1 0

[PATCH openEuler-1.0-LTS] [just for review!!!!]Add feature: eNFS - nfs multipath to improve performance and reliability
by mingqian218472 25 Sep '23

25 Sep '23

From: 闫海涛 <yanhaitao2(a)huawei.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7SVH7 --------------------------------- Currently, the NFS client can use only one server IP address at a single mount point. As a result, the hardware capability of multiple storage nodes and NICs cannot be fully utilized. In multiple financial sites, the performance cannot meet service requirements. In addition, when a single link is faulty, services are suspended. The reliability problem needs to be solved. OpenEuler-based commercial OS vendors hope that the eNFS feature will be integrated into 20.03 SP4 to resolve performance and reliability problems. When user mount one NFS share, can input localaddrs/remoteaddrs these two optional Parameters to use eNFS multipath. If these optional parameters are not used, NFS will behave as before. For example, mount -t nfs -o [localaddrs=127.17.0.1-127.17.0.4],[remoteaddrs=127.17.1.1-127.17.1.4] xx.xx.xx.xx:/test /mnt/test Changes in eNFS are as follows: 1. patch 0001: At the NFS layer, the eNFS registration function is called back when the mount command parses parameters. The eNFS parses and saves the IP address list entered by users. 2. patch 0002: At the sunrpc layer, the eNFS registration function is called back When the NFS uses sunrpc to create rpc_clnt, the eNFS combines the IP address list entered for mount to generate multiple xprts. When the I/O times out, the callback function of the eNFS is called back so that the eNFS switches to an available link for retry. 3. patch 0003: The eNFS module registers the interface for parsing the mount command. During the mount process, the NFS invokes the eNFS interface to enable the eNFS to parse the mounting parameters of UltraPath. The eNFS module saves the mounting parameters to the context of nfs_client. 4. patch 0004: When the NFS invokes the SunRPC to create rpc_clnt, the eNFS interface is called back. The eNFS creates multiple xprts based on the output IP address list. When NFS V3 I/Os are delivered, eNFS distributes I/Os to available links based on the link status, improving performance through load balancing. 5. patch 0005: When sending I/Os from the SunRPC module to the NFS server times out, the SunRPC module calls back the eNFS module to reselect a link. The eNFS module distributes I/Os to other available links, preventing service interruption caused by a single link failure. 6. patch 0006: The eNFS compilation option and makefile are added. By default, the eNFS compilation is not performed. Signed-off-by: mingqian218472 <zhangmingqian.zhang(a)huawei.com> --- ...-nfs-multipath-to-improve-performanc.patch | 6148 +++++++++++++++++ ...enfs_registe_and_handle_mount_option.patch | 757 ++ ...nd_create_multipath_then_dispatch_IO.patch | 805 +++ ...add_enfs_module_for_nfs_mount_option.patch | 1209 ++++ ...dd_enfs_module_for_sunrpc_multipatch.patch | 1581 +++++ ...le_for_sunrpc_failover_and_configure.patch | 1607 +++++ 0006-add_enfs_compile_option.patch | 70 + 7 files changed, 12177 insertions(+) create mode 100644 0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch create mode 100644 0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch create mode 100644 0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch create mode 100644 0003-add_enfs_module_for_nfs_mount_option.patch create mode 100644 0004-add_enfs_module_for_sunrpc_multipatch.patch create mode 100644 0005-add_enfs_module_for_sunrpc_failover_and_configure.patch create mode 100644 0006-add_enfs_compile_option.patch diff --git a/0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch b/0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch new file mode 100644 index 0000000..2974c5f --- /dev/null +++ b/0001-Add-feature-eNFS-nfs-multipath-to-improve-performanc.patch @@ -0,0 +1,6148 @@ +From 53f616b0a649494e33d30b250d06c4049ccb88be Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?=E9=97=AB=E6=B5=B7=E6=B6=9B?= <yanhaitao2(a)huawei.com> +Date: Mon, 25 Sep 2023 19:19:15 +0800 +Subject: [PATCH openEuler-20.03-LTS-SP3] Add feature: eNFS - nfs multipath to + improve performance and reliability + +driver inclusion +category: feature +bugzilla: https://gitee.com/openeuler/release-management/issues/I7U0W0 + +--------------------------------- + +Currently, the NFS client can use only one server IP address at a single mount point. As a result, the hardware capability of multiple storage nodes and NICs cannot be fully utilized. In multiple financial sites, the performance cannot meet service requirements. In addition, when a single link is faulty, services are suspended. The reliability problem needs to be solved. +OpenEuler-based commercial OS vendors hope that the eNFS feature will be integrated into 20.03 SP4 to resolve performance and reliability problems. + +When user mount one NFS share, can input localaddrs/remoteaddrs these two optional Parameters to use eNFS multipath. If these optional parameters are not used, NFS will behave as before. For example, +mount -t nfs -o [localaddrs=127.17.0.1-127.17.0.4],[remoteaddrs=127.17.1.1-127.17.1.4] xx.xx.xx.xx:/test /mnt/test + +Changes in eNFS are as follows: +1. patch 0001: +At the NFS layer, the eNFS registration function is called back when the mount command parses parameters. The eNFS parses and saves the IP address list entered by users. +2. patch 0002: +At the sunrpc layer, the eNFS registration function is called back When the NFS uses sunrpc to create rpc_clnt, the eNFS combines the IP address list entered for mount to generate multiple xprts. When the I/O times out, the callback function of the eNFS is called back so that the eNFS switches to an available link for retry. +3. patch 0003: +The eNFS module registers the interface for parsing the mount command. During the mount process, the NFS invokes the eNFS interface to enable the eNFS to parse the mounting parameters of UltraPath. The eNFS module saves the mounting parameters to the context of nfs_client. +4. patch 0004: +When the NFS invokes the SunRPC to create rpc_clnt, the eNFS interface is called back. The eNFS creates multiple xprts based on the output IP address list. When NFS V3 I/Os are delivered, eNFS distributes I/Os to available links based on the link status, improving performance through load balancing. +5. patch 0005: +When sending I/Os from the SunRPC module to the NFS server times out, the SunRPC module calls back the eNFS module to reselect a link. The eNFS module distributes I/Os to other available links, preventing service interruption caused by a single link failure. +6. patch 0006: +The eNFS compilation option and makefile are added. By default, the eNFS compilation is not performed. + +Signed-off-by: mingqian218472 <zhangmingqian.zhang(a)huawei.com> +--- + ...enfs_registe_and_handle_mount_option.patch | 757 ++++++++ + ...nd_create_multipath_then_dispatch_IO.patch | 805 +++++++++ + ...add_enfs_module_for_nfs_mount_option.patch | 1209 +++++++++++++ + ...dd_enfs_module_for_sunrpc_multipatch.patch | 1581 ++++++++++++++++ + ...le_for_sunrpc_failover_and_configure.patch | 1607 +++++++++++++++++ + 0006-add_enfs_compile_option.patch | 70 + + kernel.spec | 13 + + 7 files changed, 6042 insertions(+) + create mode 100644 0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch + create mode 100644 0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch + create mode 100644 0003-add_enfs_module_for_nfs_mount_option.patch + create mode 100644 0004-add_enfs_module_for_sunrpc_multipatch.patch + create mode 100644 0005-add_enfs_module_for_sunrpc_failover_and_configure.patch + create mode 100644 0006-add_enfs_compile_option.patch + +diff --git a/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch +new file mode 100644 +index 0000000..38e57a9 +--- /dev/null ++++ b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch +@@ -0,0 +1,757 @@ ++diff --git a/fs/nfs/client.c b/fs/nfs/client.c ++index 7d02dc52209d..50820a8a684a 100644 ++--- a/fs/nfs/client.c +++++ b/fs/nfs/client.c ++@@ -48,7 +48,7 @@ ++ #include "callback.h" ++ #include "delegation.h" ++ #include "iostat.h" ++-#include "internal.h" +++#include "enfs_adapter.h" ++ #include "fscache.h" ++ #include "pnfs.h" ++ #include "nfs.h" ++@@ -255,6 +255,7 @@ void nfs_free_client(struct nfs_client *clp) ++ put_nfs_version(clp->cl_nfs_mod); ++ kfree(clp->cl_hostname); ++ kfree(clp->cl_acceptor); +++ nfs_free_multi_path_client(clp); ++ kfree(clp); ++ } ++ EXPORT_SYMBOL_GPL(nfs_free_client); ++@@ -330,6 +331,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat ++ sap)) ++ continue; ++ +++ if (!nfs_multipath_client_match(clp, data)) +++ continue; +++ ++ refcount_inc(&clp->cl_count); ++ return clp; ++ } ++@@ -512,6 +516,9 @@ int nfs_create_rpc_client(struct nfs_client *clp, ++ .program = &nfs_program, ++ .version = clp->rpc_ops->version, ++ .authflavor = flavor, +++#if IS_ENABLED(CONFIG_ENFS) +++ .multipath_option = cl_init->enfs_option, +++#endif ++ }; ++ ++ if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) ++@@ -634,6 +641,13 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp, ++ /* the client is already initialised */ ++ if (clp->cl_cons_state == NFS_CS_READY) ++ return clp; +++ error = nfs_create_multi_path_client(clp, cl_init); +++ if (error < 0) { +++ dprintk("%s: create failed.%d!\n", __func__, error); +++ nfs_put_client(clp); +++ clp = ERR_PTR(error); +++ return clp; +++ } ++ ++ /* ++ * Create a client RPC handle for doing FSSTAT with UNIX auth only ++@@ -666,6 +680,9 @@ static int nfs_init_server(struct nfs_server *server, ++ .net = data->net, ++ .timeparms = &timeparms, ++ .init_flags = (1UL << NFS_CS_REUSEPORT), +++#if IS_ENABLED(CONFIG_ENFS) +++ .enfs_option = data->enfs_option, +++#endif ++ }; ++ struct nfs_client *clp; ++ int error; ++diff --git a/fs/nfs/enfs_adapter.c b/fs/nfs/enfs_adapter.c ++new file mode 100644 ++index 000000000000..7f471f2072c4 ++--- /dev/null +++++ b/fs/nfs/enfs_adapter.c ++@@ -0,0 +1,230 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs3.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/sunrpc/sched.h> +++#include <linux/nfs_iostat.h> +++#include "enfs_adapter.h" +++#include "iostat.h" +++ +++struct enfs_adapter_ops __rcu *enfs_adapter; +++ +++int enfs_adapter_register(struct enfs_adapter_ops *ops) +++{ +++ struct enfs_adapter_ops *old; +++ +++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, NULL, ops); +++ if (old == NULL || old == ops) +++ return 0; +++ pr_err("regist %s ops %p failed. old %p\n", __func__, ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(enfs_adapter_register); +++ +++int enfs_adapter_unregister(struct enfs_adapter_ops *ops) +++{ +++ struct enfs_adapter_ops *old; +++ +++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, ops, NULL); +++ if (old == ops || old == NULL) +++ return 0; +++ pr_err("unregist %s ops %p failed. old %p\n", __func__, ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(enfs_adapter_unregister); +++ +++struct enfs_adapter_ops *nfs_multipath_router_get(void) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ rcu_read_lock(); +++ ops = rcu_dereference(enfs_adapter); +++ if (ops == NULL) { +++ rcu_read_unlock(); +++ return NULL; +++ } +++ if (!try_module_get(ops->owner)) +++ ops = NULL; +++ rcu_read_unlock(); +++ return ops; +++} +++ +++void nfs_multipath_router_put(struct enfs_adapter_ops *ops) +++{ +++ if (ops) +++ module_put(ops->owner); +++} +++ +++bool is_valid_option(enum nfsmultipathoptions option) +++{ +++ if (option < REMOTEADDR || option >= INVALID_OPTION) { +++ pr_warn("%s: ENFS invalid option %d\n", __func__, option); +++ return false; +++ } +++ +++ return true; +++} +++ +++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, +++ struct nfs_parsed_mount_data *mnt) +++{ +++ +++ //parseMultiPathOptions(getNfsMultiPathOpt(token), string, mnt); +++ +++ int rc; +++ struct enfs_adapter_ops *ops; +++ +++ ops = nfs_multipath_router_get(); +++ if ((ops == NULL) || (ops->parse_mount_options == NULL) || +++ !is_valid_option(option)) { +++ nfs_multipath_router_put(ops); +++ dfprintk(MOUNT, +++ "NFS: parsing nfs mount option enfs not load[%s]\n" +++ , __func__); +++ return -EOPNOTSUPP; +++ } +++ // nfs_multipath_parse_options +++ dfprintk(MOUNT, "NFS: parsing nfs mount option '%s' type: %d[%s]\n" +++ , str, option, __func__); +++ rc = ops->parse_mount_options(option, str, &mnt->enfs_option, mnt->net); +++ nfs_multipath_router_put(ops); +++ return rc; +++} +++ +++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ if (data->enfs_option == NULL) +++ return; +++ +++ ops = nfs_multipath_router_get(); +++ if ((ops == NULL) || (ops->free_mount_options == NULL)) { +++ nfs_multipath_router_put(ops); +++ return; +++ } +++ ops->free_mount_options((void *)&data->enfs_option); +++ nfs_multipath_router_put(ops); +++} +++ +++int nfs_create_multi_path_client(struct nfs_client *client, +++ const struct nfs_client_initdata *cl_init) +++{ +++ int ret = 0; +++ struct enfs_adapter_ops *ops; +++ +++ if (cl_init->enfs_option == NULL) +++ return 0; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_init != NULL) +++ ret = ops->client_info_init( +++ (void *)&client->cl_multipath_data, cl_init); +++ nfs_multipath_router_put(ops); +++ +++ return ret; +++} +++EXPORT_SYMBOL_GPL(nfs_create_multi_path_client); +++ +++void nfs_free_multi_path_client(struct nfs_client *clp) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ if (clp->cl_multipath_data == NULL) +++ return; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_free != NULL) +++ ops->client_info_free(clp->cl_multipath_data); +++ nfs_multipath_router_put(ops); +++} +++ +++int nfs_multipath_client_match(struct nfs_client *clp, +++ const struct nfs_client_initdata *sap) +++{ +++ int ret = true; +++ struct enfs_adapter_ops *ops; +++ +++ pr_info("%s src %p dst %p\n.", __func__, +++ clp->cl_multipath_data, sap->enfs_option); +++ +++ if (clp->cl_multipath_data == NULL && sap->enfs_option == NULL) +++ return true; +++ +++ if ((clp->cl_multipath_data == NULL && sap->enfs_option) || +++ (clp->cl_multipath_data && sap->enfs_option == NULL)) { +++ pr_err("not match client src %p dst %p\n.", +++ clp->cl_multipath_data, sap->enfs_option); +++ return false; +++ } +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_match != NULL) +++ ret = ops->client_info_match(clp->cl_multipath_data, +++ sap->enfs_option); +++ nfs_multipath_router_put(ops); +++ +++ return ret; +++} +++ +++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst) +++{ +++ int ret = true; +++ struct enfs_adapter_ops *ops; +++ +++ if (src->cl_multipath_data == NULL && dst->cl_multipath_data == NULL) +++ return true; +++ +++ if (src->cl_multipath_data == NULL || dst->cl_multipath_data == NULL) +++ return false; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->nfs4_client_info_match != NULL) +++ ret = ops->nfs4_client_info_match(src->cl_multipath_data, +++ src->cl_multipath_data); +++ nfs_multipath_router_put(ops); +++ +++ return ret; +++} +++EXPORT_SYMBOL_GPL(nfs4_multipath_client_match); +++ +++void nfs_multipath_show_client_info(struct seq_file *mount_option, +++ struct nfs_server *server) +++{ +++ struct enfs_adapter_ops *ops; +++ +++ if (mount_option == NULL || server == NULL || +++ server->client == NULL || +++ server->nfs_client->cl_multipath_data == NULL) +++ return; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->client_info_show != NULL) +++ ops->client_info_show(mount_option, server); +++ nfs_multipath_router_put(ops); +++} +++ +++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) +++{ +++ int ret = 0; +++ struct enfs_adapter_ops *ops; +++ +++ if (nfs_client == NULL || nfs_client->cl_rpcclient == NULL) +++ return 0; +++ +++ ops = nfs_multipath_router_get(); +++ if (ops != NULL && ops->remount_ip_list != NULL) +++ ret = ops->remount_ip_list(nfs_client, enfs_option); +++ nfs_multipath_router_put(ops); +++ return ret; +++} +++EXPORT_SYMBOL_GPL(nfs_remount_iplist); ++diff --git a/fs/nfs/enfs_adapter.h b/fs/nfs/enfs_adapter.h ++new file mode 100644 ++index 000000000000..752544e18056 ++--- /dev/null +++++ b/fs/nfs/enfs_adapter.h ++@@ -0,0 +1,101 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapt header. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _NFS_MULTIPATH_H_ +++#define _NFS_MULTIPATH_H_ +++ +++#include "internal.h" +++ +++#if IS_ENABLED(CONFIG_ENFS) +++enum nfsmultipathoptions { +++ REMOTEADDR, +++ LOCALADDR, +++ REMOTEDNSNAME, +++ REMOUNTREMOTEADDR, +++ REMOUNTLOCALADDR, +++ INVALID_OPTION +++}; +++ +++ +++struct enfs_adapter_ops { +++ const char *name; +++ struct module *owner; +++ int (*parse_mount_options)(enum nfsmultipathoptions option, +++ char *str, void **enfs_option, struct net *net_ns); +++ +++ void (*free_mount_options)(void **data); +++ +++ int (*client_info_init)(void **data, +++ const struct nfs_client_initdata *cl_init); +++ void (*client_info_free)(void *data); +++ int (*client_info_match)(void *src, void *dst); +++ int (*nfs4_client_info_match)(void *src, void *dst); +++ void (*client_info_show)(struct seq_file *mount_option, void *data); +++ int (*remount_ip_list)(struct nfs_client *nfs_client, +++ void *enfs_option); +++}; +++ +++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, +++ struct nfs_parsed_mount_data *mnt); +++void enfs_free_mount_options(struct nfs_parsed_mount_data *data); +++int nfs_create_multi_path_client(struct nfs_client *client, +++ const struct nfs_client_initdata *cl_init); +++void nfs_free_multi_path_client(struct nfs_client *clp); +++int nfs_multipath_client_match(struct nfs_client *clp, +++ const struct nfs_client_initdata *sap); +++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst); +++void nfs_multipath_show_client_info(struct seq_file *mount_option, +++ struct nfs_server *server); +++int enfs_adapter_register(struct enfs_adapter_ops *ops); +++int enfs_adapter_unregister(struct enfs_adapter_ops *ops); +++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); +++int nfs4_create_multi_path(struct nfs_server *server, +++ struct nfs_parsed_mount_data *data, +++ const struct rpc_timeout *timeparms); +++ +++#else +++static inline +++void nfs_free_multi_path_client(struct nfs_client *clp) +++{ +++ +++} +++ +++static inline +++int nfs_multipath_client_match(struct nfs_client *clp, +++ const struct nfs_client_initdata *sap) +++{ +++ return 1; +++} +++ +++static inline +++int nfs_create_multi_path_client(struct nfs_client *client, +++ const struct nfs_client_initdata *cl_init) +++{ +++ return 0; +++} +++ +++static inline +++void nfs_multipath_show_client_info(struct seq_file *mount_option, +++ struct nfs_server *server) +++{ +++ +++} +++ +++static inline +++int nfs4_multipath_client_match(struct nfs_client *src, +++ struct nfs_client *dst) +++{ +++ return 1; +++} +++ +++static inline +++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) +++{ +++ +++} +++ +++#endif // CONFIG_ENFS +++#endif // _NFS_MULTIPATH_H_ ++diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h ++index 0ce5a90640c4..c696693edc7b 100644 ++--- a/fs/nfs/internal.h +++++ b/fs/nfs/internal.h ++@@ -93,6 +93,9 @@ struct nfs_client_initdata { ++ u32 minorversion; ++ struct net *net; ++ const struct rpc_timeout *timeparms; +++#if IS_ENABLED(CONFIG_ENFS) +++ void *enfs_option; /* struct multipath_mount_options * */ +++#endif ++ }; ++ ++ /* ++@@ -135,6 +138,9 @@ struct nfs_parsed_mount_data { ++ ++ struct security_mnt_opts lsm_opts; ++ struct net *net; +++#if IS_ENABLED(CONFIG_ENFS) +++ void *enfs_option; /* struct multipath_mount_options * */ +++#endif ++ }; ++ ++ /* mount_clnt.c */ ++diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c ++index 1350ea673672..4aa6e1f961f7 100644 ++--- a/fs/nfs/nfs4client.c +++++ b/fs/nfs/nfs4client.c ++@@ -10,7 +10,7 @@ ++ #include <linux/sunrpc/xprt.h> ++ #include <linux/sunrpc/bc_xprt.h> ++ #include <linux/sunrpc/rpc_pipe_fs.h> ++-#include "internal.h" +++#include "enfs_adapter.h" ++ #include "callback.h" ++ #include "delegation.h" ++ #include "nfs4session.h" ++@@ -225,6 +225,16 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) ++ __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); ++ __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ err = nfs_create_multi_path_client(clp, cl_init); +++ if (err < 0) { +++ dprintk("%s: create failed.%d\n", __func__, err); +++ nfs_put_client(clp); +++ clp = ERR_PTR(err); +++ return clp; +++ } +++#endif +++ ++ /* ++ * Set up the connection to the server before we add add to the ++ * global list. ++@@ -529,6 +539,9 @@ static int nfs4_match_client(struct nfs_client *pos, struct nfs_client *new, ++ if (!nfs4_match_client_owner_id(pos, new)) ++ return 1; ++ +++ if (!nfs4_multipath_client_match(pos, new)) +++ return 1; +++ ++ return 0; ++ } ++ ++@@ -860,7 +873,7 @@ static int nfs4_set_client(struct nfs_server *server, ++ const size_t addrlen, ++ const char *ip_addr, ++ int proto, const struct rpc_timeout *timeparms, ++- u32 minorversion, struct net *net) +++ u32 minorversion, struct net *net, void *enfs_option) ++ { ++ struct nfs_client_initdata cl_init = { ++ .hostname = hostname, ++@@ -872,6 +885,9 @@ static int nfs4_set_client(struct nfs_server *server, ++ .minorversion = minorversion, ++ .net = net, ++ .timeparms = timeparms, +++#if IS_ENABLED(CONFIG_ENFS) +++ .enfs_option = enfs_option, +++#endif ++ }; ++ struct nfs_client *clp; ++ ++@@ -1042,6 +1058,30 @@ static int nfs4_server_common_setup(struct nfs_server *server, ++ return error; ++ } ++ +++int nfs4_create_multi_path(struct nfs_server *server, +++ struct nfs_parsed_mount_data *data, +++ const struct rpc_timeout *timeparms) +++{ +++ struct nfs_client_initdata cl_init = { +++ .hostname = data->nfs_server.hostname, +++ .addr = (const struct sockaddr *)&data->nfs_server.address, +++ .addrlen = data->nfs_server.addrlen, +++ .ip_addr = data->client_address, +++ .nfs_mod = &nfs_v4, +++ .proto = data->nfs_server.protocol, +++ .minorversion = data->minorversion, +++ .net = data->net, +++ .timeparms = timeparms, +++#if IS_ENABLED(CONFIG_ENFS) +++ .enfs_option = data->enfs_option, +++#endif // CONFIG_ENFS +++ }; +++ +++ return nfs_create_multi_path_client(server->nfs_client, &cl_init); +++ +++} +++EXPORT_SYMBOL_GPL(nfs4_create_multi_path); +++ ++ /* ++ * Create a version 4 volume record ++ */ ++@@ -1050,6 +1090,7 @@ static int nfs4_init_server(struct nfs_server *server, ++ { ++ struct rpc_timeout timeparms; ++ int error; +++ void *enfs_option = NULL; ++ ++ nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, ++ data->timeo, data->retrans); ++@@ -1067,6 +1108,10 @@ static int nfs4_init_server(struct nfs_server *server, ++ else ++ data->selected_flavor = RPC_AUTH_UNIX; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ enfs_option = data->enfs_option; +++#endif +++ ++ /* Get a client record */ ++ error = nfs4_set_client(server, ++ data->nfs_server.hostname, ++@@ -1076,7 +1121,7 @@ static int nfs4_init_server(struct nfs_server *server, ++ data->nfs_server.protocol, ++ &timeparms, ++ data->minorversion, ++- data->net); +++ data->net, enfs_option); ++ if (error < 0) ++ return error; ++ ++@@ -1161,7 +1206,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, ++ XPRT_TRANSPORT_RDMA, ++ parent_server->client->cl_timeout, ++ parent_client->cl_mvops->minor_version, ++- parent_client->cl_net); +++ parent_client->cl_net, NULL); ++ if (!error) ++ goto init_server; ++ #endif /* IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) */ ++@@ -1174,7 +1219,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, ++ XPRT_TRANSPORT_TCP, ++ parent_server->client->cl_timeout, ++ parent_client->cl_mvops->minor_version, ++- parent_client->cl_net); +++ parent_client->cl_net, NULL); ++ if (error < 0) ++ goto error; ++ ++@@ -1269,7 +1314,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, ++ set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); ++ error = nfs4_set_client(server, hostname, sap, salen, buf, ++ clp->cl_proto, clnt->cl_timeout, ++- clp->cl_minorversion, net); +++ clp->cl_minorversion, net, NULL); ++ clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); ++ if (error != 0) { ++ nfs_server_insert_lists(server); ++diff --git a/fs/nfs/super.c b/fs/nfs/super.c ++index a05e1eb2c3fd..83cd294aca15 100644 ++--- a/fs/nfs/super.c +++++ b/fs/nfs/super.c ++@@ -61,7 +61,7 @@ ++ #include "callback.h" ++ #include "delegation.h" ++ #include "iostat.h" ++-#include "internal.h" +++#include "enfs_adapter.h" ++ #include "fscache.h" ++ #include "nfs4session.h" ++ #include "pnfs.h" ++@@ -113,6 +113,12 @@ enum { ++ ++ /* Special mount options */ ++ Opt_userspace, Opt_deprecated, Opt_sloppy, +++#if IS_ENABLED(CONFIG_ENFS) +++ Opt_remote_iplist, +++ Opt_local_iplist, +++ Opt_remote_dnslist, +++ Opt_enfs_info, +++#endif ++ ++ Opt_err ++ }; ++@@ -183,6 +189,13 @@ static const match_table_t nfs_mount_option_tokens = { ++ { Opt_fscache_uniq, "fsc=%s" }, ++ { Opt_local_lock, "local_lock=%s" }, ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ { Opt_remote_iplist, "remoteaddrs=%s" }, +++ { Opt_local_iplist, "localaddrs=%s" }, +++ { Opt_remote_dnslist, "remotednsname=%s" }, +++ { Opt_enfs_info, "enfs_info=%s" }, +++#endif +++ ++ /* The following needs to be listed after all other options */ ++ { Opt_nfsvers, "v%s" }, ++ ++@@ -365,6 +378,21 @@ static struct shrinker acl_shrinker = { ++ .seeks = DEFAULT_SEEKS, ++ }; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++enum nfsmultipathoptions getNfsMultiPathOpt(int token) +++{ +++ switch (token) { +++ case Opt_remote_iplist: +++ return REMOUNTREMOTEADDR; +++ case Opt_local_iplist: +++ return REMOUNTLOCALADDR; +++ case Opt_remote_dnslist: +++ return REMOTEDNSNAME; +++ } +++ return INVALID_OPTION; +++} +++#endif +++ ++ /* ++ * Register the NFS filesystems ++ */ ++@@ -758,6 +786,9 @@ int nfs_show_options(struct seq_file *m, struct dentry *root) ++ seq_printf(m, ",addr=%s", ++ rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient, ++ RPC_DISPLAY_ADDR)); +++ +++ nfs_multipath_show_client_info(m, nfss); +++ ++ rcu_read_unlock(); ++ ++ return 0; ++@@ -853,6 +884,8 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) ++ seq_puts(m, root->d_sb->s_flags & SB_NODIRATIME ? ",nodiratime" : ""); ++ nfs_show_mount_options(m, nfss, 1); ++ +++ nfs_multipath_show_client_info(m, nfss); +++ ++ seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); ++ ++ show_implementation_id(m, nfss); ++@@ -977,6 +1010,7 @@ static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data) ++ kfree(data->nfs_server.export_path); ++ kfree(data->nfs_server.hostname); ++ kfree(data->fscache_uniq); +++ enfs_free_mount_options(data); ++ security_free_mnt_opts(&data->lsm_opts); ++ kfree(data); ++ } ++@@ -1641,7 +1675,34 @@ static int nfs_parse_mount_options(char *raw, ++ return 0; ++ }; ++ break; ++- +++#if IS_ENABLED(CONFIG_ENFS) +++ case Opt_remote_iplist: +++ case Opt_local_iplist: +++ case Opt_remote_dnslist: +++ string = match_strdup(args); +++ if (string == NULL) +++ goto out_nomem; +++ rc = enfs_parse_mount_options(getNfsMultiPathOpt(token), +++ string, mnt); +++ kfree(string); +++ switch (rc) { +++ case 0: +++ break; +++ case -ENOMEM: +++ goto out_nomem; +++ case -ENOSPC: +++ goto out_limit; +++ case -EINVAL: +++ goto out_invalid_address; +++ case -ENOTSUPP: +++ goto out_invalid_address; +++ case -EOPNOTSUPP: +++ goto out_invalid_address; +++ } +++ break; +++ case Opt_enfs_info: +++ break; +++#endif ++ /* ++ * Special options ++ */ ++@@ -1720,6 +1781,11 @@ static int nfs_parse_mount_options(char *raw, ++ free_secdata(secdata); ++ printk(KERN_INFO "NFS: security options invalid: %d\n", rc); ++ return 0; +++#if IS_ENABLED(CONFIG_ENFS) +++out_limit: +++ dprintk("NFS: param is more than supported limit: %d\n", rc); +++ return 0; +++#endif ++ } ++ ++ /* ++@@ -2335,6 +2401,14 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) ++ if (!nfs_parse_mount_options((char *)options, data)) ++ goto out; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ if (data->enfs_option) { +++ error = nfs_remount_iplist(nfss->nfs_client, data->enfs_option); +++ if (error) +++ goto out; +++ } +++#endif +++ ++ /* ++ * noac is a special case. It implies -o sync, but that's not ++ * necessarily reflected in the mtab options. do_remount_sb ++@@ -2347,6 +2421,11 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) ++ /* compare new mount options with old ones */ ++ error = nfs_compare_remount_data(nfss, data); ++ out: +++#if IS_ENABLED(CONFIG_ENFS) +++ /* release remount option member */ +++ if (data->enfs_option) +++ enfs_free_mount_options(data); +++#endif ++ nfs_free_parsed_mount_data(data); ++ return error; ++ } ++diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h ++index 7023ae64e3d7..2c19678afe8d 100644 ++--- a/include/linux/nfs_fs_sb.h +++++ b/include/linux/nfs_fs_sb.h ++@@ -123,6 +123,11 @@ struct nfs_client { ++ ++ struct net *cl_net; ++ struct list_head pending_cb_stateids; +++ +++#if IS_ENABLED(CONFIG_ENFS) +++ /* multi path private structure (struct multipath_client_info *) */ +++ void *cl_multipath_data; +++#endif ++ }; ++ ++ /* +diff --git a/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch +new file mode 100644 +index 0000000..540a2ce +--- /dev/null ++++ b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch +@@ -0,0 +1,805 @@ ++diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h ++index 8aa865bce4f6..89178f78de8c 100644 ++--- a/include/linux/sunrpc/clnt.h +++++ b/include/linux/sunrpc/clnt.h ++@@ -70,6 +70,10 @@ struct rpc_clnt { ++ struct dentry *cl_debugfs; /* debugfs directory */ ++ #endif ++ struct rpc_xprt_iter cl_xpi; +++ +++#if IS_ENABLED(CONFIG_ENFS) +++ bool cl_enfs; +++#endif ++ }; ++ ++ /* ++@@ -124,6 +128,9 @@ struct rpc_create_args { ++ unsigned long flags; ++ char *client_name; ++ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ +++#if IS_ENABLED(CONFIG_ENFS) +++ void *multipath_option; +++#endif ++ }; ++ ++ struct rpc_add_xprt_test { ++@@ -221,6 +228,12 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, ++ const struct sockaddr *sap); ++ void rpc_cleanup_clids(void); ++ +++#if IS_ENABLED(CONFIG_ENFS) +++int +++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, +++ const struct rpc_call_ops *ops, void *data, int flags); +++#endif /* CONFIG_ENFS */ +++ ++ static inline int rpc_reply_expected(struct rpc_task *task) ++ { ++ return (task->tk_msg.rpc_proc != NULL) && ++diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h ++index ad2e243f3f03..124f5a0faf3e 100644 ++--- a/include/linux/sunrpc/sched.h +++++ b/include/linux/sunrpc/sched.h ++@@ -90,6 +90,9 @@ struct rpc_task { ++ tk_garb_retry : 2, ++ tk_cred_retry : 2, ++ tk_rebind_retry : 2; +++#if IS_ENABLED(CONFIG_ENFS) +++ unsigned long tk_major_timeo; /* major timeout ticks */ +++#endif ++ }; ++ ++ typedef void (*rpc_action)(struct rpc_task *); ++@@ -118,6 +121,9 @@ struct rpc_task_setup { ++ */ ++ #define RPC_TASK_ASYNC 0x0001 /* is an async task */ ++ #define RPC_TASK_SWAPPER 0x0002 /* is swapping in/out */ +++#if IS_ENABLED(CONFIG_ENFS) +++#define RPC_TASK_FIXED 0x0004 /* detect xprt status task */ +++#endif ++ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ ++ #define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ ++ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ ++@@ -257,6 +263,9 @@ void rpc_destroy_mempool(void); ++ extern struct workqueue_struct *rpciod_workqueue; ++ extern struct workqueue_struct *xprtiod_workqueue; ++ void rpc_prepare_task(struct rpc_task *task); +++#if IS_ENABLED(CONFIG_ENFS) +++void rpc_init_task_retry_counters(struct rpc_task *task); +++#endif ++ ++ static inline int rpc_wait_for_completion_task(struct rpc_task *task) ++ { ++diff --git a/include/linux/sunrpc/sunrpc_enfs_adapter.h b/include/linux/sunrpc/sunrpc_enfs_adapter.h ++new file mode 100644 ++index 000000000000..28abedcf5cf6 ++--- /dev/null +++++ b/include/linux/sunrpc/sunrpc_enfs_adapter.h ++@@ -0,0 +1,128 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* Client-side SUNRPC ENFS adapter header. +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _SUNRPC_ENFS_ADAPTER_H_ +++#define _SUNRPC_ENFS_ADAPTER_H_ +++#include <linux/sunrpc/clnt.h> +++ +++#if IS_ENABLED(CONFIG_ENFS) +++ +++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) +++{ +++ xps->xps_nactive--; +++} +++ +++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) +++{ +++ xps->xps_nactive--; +++} +++ +++struct rpc_xprt *rpc_task_get_xprt +++(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +++ +++struct rpc_multipath_ops { +++ struct module *owner; +++ void (*create_clnt)(struct rpc_create_args *args, +++ struct rpc_clnt *clnt); +++ void (*releas_clnt)(struct rpc_clnt *clnt); +++ void (*create_xprt)(struct rpc_xprt *xprt); +++ void (*destroy_xprt)(struct rpc_xprt *xprt); +++ void (*xprt_iostat)(struct rpc_task *task); +++ void (*failover_handle)(struct rpc_task *task); +++ bool (*task_need_call_start_again)(struct rpc_task *task); +++ void (*adjust_task_timeout)(struct rpc_task *task, void *condition); +++ void (*init_task_req)(struct rpc_task *task, struct rpc_rqst *req); +++ bool (*prepare_transmit)(struct rpc_task *task); +++}; +++ +++extern struct rpc_multipath_ops __rcu *multipath_ops; +++void rpc_init_task_retry_counters(struct rpc_task *task); +++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops); +++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops); +++struct rpc_multipath_ops *rpc_multipath_ops_get(void); +++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops); +++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, +++ struct rpc_clnt *clnt); +++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt); +++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt); +++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt); +++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task); +++void rpc_multipath_ops_failover_handle(struct rpc_task *task); +++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task); +++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, +++ void *condition); +++void rpc_multipath_ops_init_task_req(struct rpc_task *task, +++ struct rpc_rqst *req); +++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task); +++ +++#else +++static inline struct rpc_xprt *rpc_task_get_xprt(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt) +++{ +++ return NULL; +++} +++ +++static inline void rpc_task_release_xprt(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt) +++{ +++} +++ +++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) +++{ +++} +++ +++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) +++{ +++} +++ +++static inline void rpc_multipath_ops_create_clnt +++(struct rpc_create_args *args, struct rpc_clnt *clnt) +++{ +++} +++ +++static inline void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) +++{ +++} +++ +++static inline bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) +++{ +++ return false; +++} +++ +++static inline void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) +++{ +++} +++ +++static inline void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) +++{ +++} +++ +++static inline void rpc_multipath_ops_failover_handle(struct rpc_task *task) +++{ +++} +++ +++static inline +++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) +++{ +++ return false; +++} +++ +++static inline void +++rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, void *condition) +++{ +++} +++ +++static inline void +++rpc_multipath_ops_init_task_req(struct rpc_task *task, struct rpc_rqst *req) +++{ +++} +++ +++static inline bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) +++{ +++ return false; +++} +++ +++#endif +++#endif // _SUNRPC_ENFS_ADAPTER_H_ ++diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h ++index ccfacca1eba9..2e47b3577947 100644 ++--- a/include/linux/sunrpc/xprt.h +++++ b/include/linux/sunrpc/xprt.h ++@@ -279,6 +279,10 @@ struct rpc_xprt { ++ atomic_t inject_disconnect; ++ #endif ++ struct rcu_head rcu; +++#if IS_ENABLED(CONFIG_ENFS) +++ atomic_long_t queuelen; +++ void *multipath_context; +++#endif ++ }; ++ ++ #if defined(CONFIG_SUNRPC_BACKCHANNEL) ++diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h ++index af1257c030d2..d54e4dbbbf34 100644 ++--- a/include/linux/sunrpc/xprtmultipath.h +++++ b/include/linux/sunrpc/xprtmultipath.h ++@@ -22,6 +22,10 @@ struct rpc_xprt_switch { ++ const struct rpc_xprt_iter_ops *xps_iter_ops; ++ ++ struct rcu_head xps_rcu; +++#if IS_ENABLED(CONFIG_ENFS) +++ unsigned int xps_nactive; +++ atomic_long_t xps_queuelen; +++#endif ++ }; ++ ++ struct rpc_xprt_iter { ++@@ -69,4 +73,8 @@ extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); ++ ++ extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, ++ const struct sockaddr *sap); +++#if IS_ENABLED(CONFIG_ENFS) +++extern void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, +++ struct rpc_xprt *xprt); +++#endif ++ #endif ++diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c ++index 0fc540b0d183..d7ffee637148 100644 ++--- a/net/sunrpc/clnt.c +++++ b/net/sunrpc/clnt.c ++@@ -37,6 +37,7 @@ ++ #include <linux/sunrpc/rpc_pipe_fs.h> ++ #include <linux/sunrpc/metrics.h> ++ #include <linux/sunrpc/bc_xprt.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ #include <trace/events/sunrpc.h> ++ ++ #include "sunrpc.h" ++@@ -490,6 +491,8 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, ++ } ++ } ++ +++ rpc_multipath_ops_create_clnt(args, clnt); +++ ++ clnt->cl_softrtry = 1; ++ if (args->flags & RPC_CLNT_CREATE_HARDRTRY) ++ clnt->cl_softrtry = 0; ++@@ -869,6 +872,8 @@ void rpc_shutdown_client(struct rpc_clnt *clnt) ++ list_empty(&clnt->cl_tasks), 1*HZ); ++ } ++ +++ rpc_multipath_ops_releas_clnt(clnt); +++ ++ rpc_release_client(clnt); ++ } ++ EXPORT_SYMBOL_GPL(rpc_shutdown_client); ++@@ -981,7 +986,13 @@ void rpc_task_release_transport(struct rpc_task *task) ++ ++ if (xprt) { ++ task->tk_xprt = NULL; ++- xprt_put(xprt); +++#if IS_ENABLED(CONFIG_ENFS) +++ if (task->tk_client) { +++ rpc_task_release_xprt(task->tk_client, xprt); +++ return; +++ } +++#endif +++ xprt_put(xprt); ++ } ++ } ++ EXPORT_SYMBOL_GPL(rpc_task_release_transport); ++@@ -990,6 +1001,10 @@ void rpc_task_release_client(struct rpc_task *task) ++ { ++ struct rpc_clnt *clnt = task->tk_client; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ rpc_task_release_transport(task); +++#endif +++ ++ if (clnt != NULL) { ++ /* Remove from client task list */ ++ spin_lock(&clnt->cl_lock); ++@@ -999,14 +1014,29 @@ void rpc_task_release_client(struct rpc_task *task) ++ ++ rpc_release_client(clnt); ++ } +++#if IS_ENABLED(CONFIG_ENFS) +++#else ++ rpc_task_release_transport(task); +++#endif ++ } ++ +++#if IS_ENABLED(CONFIG_ENFS) +++static struct rpc_xprt * +++rpc_task_get_next_xprt(struct rpc_clnt *clnt) +++{ +++ return rpc_task_get_xprt(clnt, xprt_iter_get_next(&clnt->cl_xpi)); +++} +++#endif +++ ++ static ++ void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) ++ { ++ if (!task->tk_xprt) +++#if IS_ENABLED(CONFIG_ENFS) +++ task->tk_xprt = rpc_task_get_next_xprt(clnt); +++#else ++ task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); +++#endif ++ } ++ ++ static ++@@ -1597,6 +1627,14 @@ call_reserveresult(struct rpc_task *task) ++ return; ++ case -EIO: /* probably a shutdown */ ++ break; +++#if IS_ENABLED(CONFIG_ENFS) +++ case -ETIMEDOUT: /* woken up; restart */ +++ if (rpc_multipath_ops_task_need_call_start_again(task)) { +++ rpc_task_release_transport(task); +++ task->tk_action = call_start; +++ return; +++ } +++#endif ++ default: ++ printk(KERN_ERR "%s: unrecognized error %d, exiting\n", ++ __func__, status); ++@@ -1962,6 +2000,10 @@ call_transmit(struct rpc_task *task) ++ return; ++ if (!xprt_prepare_transmit(task)) ++ return; +++ +++ if (rpc_multipath_ops_prepare_transmit(task)) +++ return; +++ ++ task->tk_action = call_transmit_status; ++ /* Encode here so that rpcsec_gss can use correct sequence number. */ ++ if (rpc_task_need_encode(task)) { ++@@ -2277,6 +2319,9 @@ call_timeout(struct rpc_task *task) ++ ++ retry: ++ task->tk_action = call_bind; +++#if IS_ENABLED(CONFIG_ENFS) +++ rpc_multipath_ops_failover_handle(task); +++#endif ++ task->tk_status = 0; ++ } ++ ++@@ -2961,3 +3006,30 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) ++ } ++ EXPORT_SYMBOL_GPL(rpc_clnt_swap_deactivate); ++ #endif /* CONFIG_SUNRPC_SWAP */ +++ +++#if IS_ENABLED(CONFIG_ENFS) +++/* rpc_clnt_test_xprt - Test and add a new transport to a rpc_clnt +++ * @clnt: pointer to struct rpc_clnt +++ * @xprt: pointer struct rpc_xprt +++ * @ops: async operation +++ */ +++int +++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, +++ const struct rpc_call_ops *ops, void *data, int flags) +++{ +++ struct rpc_cred *cred; +++ struct rpc_task *task; +++ +++ cred = authnull_ops.lookup_cred(NULL, NULL, 0); +++ task = rpc_call_null_helper(clnt, xprt, cred, +++ RPC_TASK_SOFT | RPC_TASK_SOFTCONN | flags, +++ ops, data); +++ put_rpccred(cred); +++ if (IS_ERR(task)) +++ return PTR_ERR(task); +++ +++ rpc_put_task(task); +++ return 1; +++} +++EXPORT_SYMBOL_GPL(rpc_clnt_test_xprt); +++#endif ++diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c ++index a873c92a4898..2254fea0e863 100644 ++--- a/net/sunrpc/sched.c +++++ b/net/sunrpc/sched.c ++@@ -20,7 +20,7 @@ ++ #include <linux/mutex.h> ++ #include <linux/freezer.h> ++ ++-#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ ++ #include "sunrpc.h" ++ ++@@ -962,7 +962,12 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta ++ /* Initialize workqueue for async tasks */ ++ task->tk_workqueue = task_setup_data->workqueue; ++ +++#if IS_ENABLED(CONFIG_ENFS) +++ task->tk_xprt = rpc_task_get_xprt(task_setup_data->rpc_client, +++ xprt_get(task_setup_data->rpc_xprt)); +++#else ++ task->tk_xprt = xprt_get(task_setup_data->rpc_xprt); +++#endif ++ ++ if (task->tk_ops->rpc_call_prepare != NULL) ++ task->tk_action = rpc_prepare_task; ++diff --git a/net/sunrpc/sunrpc_enfs_adapter.c b/net/sunrpc/sunrpc_enfs_adapter.c ++new file mode 100644 ++index 000000000000..c1543545c6de ++--- /dev/null +++++ b/net/sunrpc/sunrpc_enfs_adapter.c ++@@ -0,0 +1,214 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* Client-side SUNRPC ENFS adapter header. +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> +++ +++struct rpc_multipath_ops __rcu *multipath_ops; +++ +++void rpc_init_task_retry_counters(struct rpc_task *task) +++{ +++ /* Initialize retry counters */ +++ task->tk_garb_retry = 2; +++ task->tk_cred_retry = 2; +++ task->tk_rebind_retry = 2; +++} +++EXPORT_SYMBOL_GPL(rpc_init_task_retry_counters); +++ +++struct rpc_xprt * +++rpc_task_get_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) +++{ +++ struct rpc_xprt_switch *xps; +++ +++ if (!xprt) +++ return NULL; +++ rcu_read_lock(); +++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); +++ atomic_long_inc(&xps->xps_queuelen); +++ rcu_read_unlock(); +++ atomic_long_inc(&xprt->queuelen); +++ +++ return xprt; +++} +++ +++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops) +++{ +++ struct rpc_multipath_ops *old; +++ +++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, NULL, ops); +++ if (!old || old == ops) +++ return 0; +++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_register); +++ +++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops) +++{ +++ struct rpc_multipath_ops *old; +++ +++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, ops, NULL); +++ if (!old || old == ops) +++ return 0; +++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); +++ return -EPERM; +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_unregister); +++ +++struct rpc_multipath_ops *rpc_multipath_ops_get(void) +++{ +++ struct rpc_multipath_ops *ops; +++ +++ rcu_read_lock(); +++ ops = rcu_dereference(multipath_ops); +++ if (!ops) { +++ rcu_read_unlock(); +++ return NULL; +++ } +++ if (!try_module_get(ops->owner)) +++ ops = NULL; +++ rcu_read_unlock(); +++ return ops; +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_get); +++ +++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops) +++{ +++ if (ops) +++ module_put(ops->owner); +++} +++EXPORT_SYMBOL_GPL(rpc_multipath_ops_put); +++ +++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) +++{ +++ struct rpc_xprt_switch *xps; +++ +++ atomic_long_dec(&xprt->queuelen); +++ rcu_read_lock(); +++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); +++ atomic_long_dec(&xps->xps_queuelen); +++ rcu_read_unlock(); +++ +++ xprt_put(xprt); +++} +++ +++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, +++ struct rpc_clnt *clnt) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ if (args->multipath_option) { +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->create_clnt) +++ mops->create_clnt(args, clnt); +++ rpc_multipath_ops_put(mops); +++ } +++} +++ +++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->releas_clnt) +++ mops->releas_clnt(clnt); +++ +++ rpc_multipath_ops_put(mops); +++} +++ +++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->create_xprt) { +++ mops->create_xprt(xprt); +++ if (!xprt->multipath_context) { +++ rpc_multipath_ops_put(mops); +++ return true; +++ } +++ } +++ rpc_multipath_ops_put(mops); +++ return false; +++} +++ +++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ if (xprt->multipath_context) { +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->destroy_xprt) +++ mops->destroy_xprt(xprt); +++ rpc_multipath_ops_put(mops); +++ } +++} +++ +++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mops; +++ +++ mops = rpc_multipath_ops_get(); +++ if (task->tk_client && mops && mops->xprt_iostat) +++ mops->xprt_iostat(task); +++ rpc_multipath_ops_put(mops); +++} +++ +++void rpc_multipath_ops_failover_handle(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mpath_ops = NULL; +++ +++ mpath_ops = rpc_multipath_ops_get(); +++ if (mpath_ops && mpath_ops->failover_handle) +++ mpath_ops->failover_handle(task); +++ rpc_multipath_ops_put(mpath_ops); +++} +++ +++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mpath_ops = NULL; +++ bool ret = false; +++ +++ mpath_ops = rpc_multipath_ops_get(); +++ if (mpath_ops && mpath_ops->task_need_call_start_again) +++ ret = mpath_ops->task_need_call_start_again(task); +++ rpc_multipath_ops_put(mpath_ops); +++ return ret; +++} +++ +++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, +++ void *condition) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->adjust_task_timeout) +++ mops->adjust_task_timeout(task, NULL); +++ rpc_multipath_ops_put(mops); +++} +++ +++void rpc_multipath_ops_init_task_req(struct rpc_task *task, +++ struct rpc_rqst *req) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->init_task_req) +++ mops->init_task_req(task, req); +++ rpc_multipath_ops_put(mops); +++} +++ +++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) +++{ +++ struct rpc_multipath_ops *mops = NULL; +++ +++ mops = rpc_multipath_ops_get(); +++ if (mops && mops->prepare_transmit) { +++ if (!(mops->prepare_transmit(task))) { +++ rpc_multipath_ops_put(mops); +++ return true; +++ } +++ } +++ rpc_multipath_ops_put(mops); +++ return false; +++} ++diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c ++index c912bf20faa2..c2b63b3d5217 100644 ++--- a/net/sunrpc/xprt.c +++++ b/net/sunrpc/xprt.c ++@@ -48,6 +48,7 @@ ++ #include <linux/sunrpc/clnt.h> ++ #include <linux/sunrpc/metrics.h> ++ #include <linux/sunrpc/bc_xprt.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ #include <linux/rcupdate.h> ++ ++ #include <trace/events/sunrpc.h> ++@@ -259,6 +260,9 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) ++ dprintk("RPC: %5u failed to lock transport %p\n", ++ task->tk_pid, xprt); ++ task->tk_timeout = 0; +++ +++ rpc_multipath_ops_adjust_task_timeout(task, NULL); +++ ++ task->tk_status = -EAGAIN; ++ if (req == NULL) ++ priority = RPC_PRIORITY_LOW; ++@@ -560,6 +564,9 @@ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action) ++ struct rpc_xprt *xprt = req->rq_xprt; ++ ++ task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0; +++ +++ rpc_multipath_ops_adjust_task_timeout(task, NULL); +++ ++ rpc_sleep_on(&xprt->pending, task, action); ++ } ++ EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space); ++@@ -1347,6 +1354,9 @@ xprt_request_init(struct rpc_task *task) ++ req->rq_rcv_buf.buflen = 0; ++ req->rq_release_snd_buf = NULL; ++ xprt_reset_majortimeo(req); +++ +++ rpc_multipath_ops_init_task_req(task, req); +++ ++ dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, ++ req, ntohl(req->rq_xid)); ++ } ++@@ -1427,6 +1437,9 @@ void xprt_release(struct rpc_task *task) ++ task->tk_ops->rpc_count_stats(task, task->tk_calldata); ++ else if (task->tk_client) ++ rpc_count_iostats(task, task->tk_client->cl_metrics); +++ +++ rpc_multipath_ops_xprt_iostat(task); +++ ++ spin_lock(&xprt->recv_lock); ++ if (!list_empty(&req->rq_list)) { ++ list_del_init(&req->rq_list); ++@@ -1455,6 +1468,7 @@ void xprt_release(struct rpc_task *task) ++ else ++ xprt_free_bc_request(req); ++ } +++EXPORT_SYMBOL_GPL(xprt_release); ++ ++ static void xprt_init(struct rpc_xprt *xprt, struct net *net) ++ { ++@@ -1528,6 +1542,10 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) ++ return ERR_PTR(-ENOMEM); ++ } ++ +++if (rpc_multipath_ops_create_xprt(xprt)) { +++ xprt_destroy(xprt); +++ return ERR_PTR(-ENOMEM); +++} ++ rpc_xprt_debugfs_register(xprt); ++ ++ dprintk("RPC: created transport %p with %u slots\n", xprt, ++@@ -1547,6 +1565,9 @@ static void xprt_destroy_cb(struct work_struct *work) ++ rpc_destroy_wait_queue(&xprt->sending); ++ rpc_destroy_wait_queue(&xprt->backlog); ++ kfree(xprt->servername); +++ +++ rpc_multipath_ops_destroy_xprt(xprt); +++ ++ /* ++ * Tear down transport state and free the rpc_xprt ++ */ ++diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c ++index 6ebaa58b4eff..6202a0be1327 100644 ++--- a/net/sunrpc/xprtmultipath.c +++++ b/net/sunrpc/xprtmultipath.c ++@@ -18,6 +18,7 @@ ++ #include <linux/sunrpc/xprt.h> ++ #include <linux/sunrpc/addr.h> ++ #include <linux/sunrpc/xprtmultipath.h> +++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ ++ typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct list_head *head, ++ const struct rpc_xprt *cur); ++@@ -26,8 +27,8 @@ static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular; ++ static const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin; ++ static const struct rpc_xprt_iter_ops rpc_xprt_iter_listall; ++ ++-static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++- struct rpc_xprt *xprt) +++void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, +++ struct rpc_xprt *xprt) ++ { ++ if (unlikely(xprt_get(xprt) == NULL)) ++ return; ++@@ -36,7 +37,9 @@ static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++ if (xps->xps_nxprts == 0) ++ xps->xps_net = xprt->xprt_net; ++ xps->xps_nxprts++; +++ rpc_xps_nactive_add_one(xps); ++ } +++EXPORT_SYMBOL(xprt_switch_add_xprt_locked); ++ ++ /** ++ * rpc_xprt_switch_add_xprt - Add a new rpc_xprt to an rpc_xprt_switch ++@@ -63,6 +66,7 @@ static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps, ++ if (unlikely(xprt == NULL)) ++ return; ++ xps->xps_nxprts--; +++ rpc_xps_nactive_sub_one(xps); ++ if (xps->xps_nxprts == 0) ++ xps->xps_net = NULL; ++ smp_wmb(); ++@@ -84,7 +88,7 @@ void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, ++ spin_unlock(&xps->xps_lock); ++ xprt_put(xprt); ++ } ++- +++EXPORT_SYMBOL(rpc_xprt_switch_remove_xprt); ++ /** ++ * xprt_switch_alloc - Allocate a new struct rpc_xprt_switch ++ * @xprt: pointer to struct rpc_xprt ++@@ -102,7 +106,13 @@ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, ++ if (xps != NULL) { ++ spin_lock_init(&xps->xps_lock); ++ kref_init(&xps->xps_kref); +++#if IS_ENABLED(CONFIG_ENFS) +++ xps->xps_nxprts = 0; +++ xps->xps_nactive = 0; +++ atomic_long_set(&xps->xps_queuelen, 0); +++#else ++ xps->xps_nxprts = 0; +++#endif ++ INIT_LIST_HEAD(&xps->xps_xprt_list); ++ xps->xps_iter_ops = &rpc_xprt_iter_singular; ++ xprt_switch_add_xprt_locked(xps, xprt); ++@@ -148,6 +158,7 @@ struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps) ++ return xps; ++ return NULL; ++ } +++EXPORT_SYMBOL(xprt_switch_get); ++ ++ /** ++ * xprt_switch_put - Release a reference to a rpc_xprt_switch ++@@ -160,6 +171,7 @@ void xprt_switch_put(struct rpc_xprt_switch *xps) ++ if (xps != NULL) ++ kref_put(&xps->xps_kref, xprt_switch_free); ++ } +++EXPORT_SYMBOL(xprt_switch_put); ++ ++ /** ++ * rpc_xprt_switch_set_roundrobin - Set a round-robin policy on rpc_xprt_switch +diff --git a/0003-add_enfs_module_for_nfs_mount_option.patch b/0003-add_enfs_module_for_nfs_mount_option.patch +new file mode 100644 +index 0000000..70753b5 +--- /dev/null ++++ b/0003-add_enfs_module_for_nfs_mount_option.patch +@@ -0,0 +1,1209 @@ ++diff --git a/fs/nfs/enfs/Makefile b/fs/nfs/enfs/Makefile ++new file mode 100644 ++index 000000000000..6e83eb23c668 ++--- /dev/null +++++ b/fs/nfs/enfs/Makefile ++@@ -0,0 +1,18 @@ +++obj-m += enfs.o +++ +++#EXTRA_CFLAGS += -I$(PWD)/.. +++ +++enfs-y := enfs_init.o +++enfs-y += enfs_config.o +++enfs-y += mgmt_init.o +++enfs-y += enfs_multipath_client.o +++enfs-y += enfs_multipath_parse.o +++enfs-y += failover_path.o +++enfs-y += failover_time.o +++enfs-y += enfs_roundrobin.o +++enfs-y += enfs_multipath.o +++enfs-y += enfs_path.o +++enfs-y += enfs_proc.o +++enfs-y += enfs_remount.o +++enfs-y += pm_ping.o +++enfs-y += pm_state.o ++diff --git a/fs/nfs/enfs/enfs.h b/fs/nfs/enfs/enfs.h ++new file mode 100644 ++index 000000000000..be3d95220088 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs.h ++@@ -0,0 +1,62 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS multipath adapt header. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++ +++#ifndef _ENFS_H_ +++#define _ENFS_H_ +++#include <linux/atomic.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs3.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include "../enfs_adapter.h" +++ +++#define IP_ADDRESS_LEN_MAX 64 +++#define MAX_IP_PAIR_PER_MOUNT 8 +++#define MAX_IP_INDEX (MAX_IP_PAIR_PER_MOUNT) +++#define MAX_SUPPORTED_LOCAL_IP_COUNT 8 +++#define MAX_SUPPORTED_REMOTE_IP_COUNT 32 +++#define MAX_DNS_NAME_LEN 512 +++#define MAX_DNS_SUPPORTED 2 +++#define EXTEND_CMD_MAX_BUF_LEN 65356 +++ +++ +++struct nfs_ip_list { +++ int count; +++ struct sockaddr_storage address[MAX_SUPPORTED_REMOTE_IP_COUNT]; +++ size_t addrlen[MAX_SUPPORTED_REMOTE_IP_COUNT]; +++}; +++ +++struct NFS_ROUTE_DNS_S { +++ char dnsname[MAX_DNS_NAME_LEN]; // valid only if dnsExist is true +++}; +++ +++struct NFS_ROUTE_DNS_INFO_S { +++ int dnsNameCount; // Count of DNS name in the list +++ // valid only if dnsExist is true +++ struct NFS_ROUTE_DNS_S routeRemoteDnsList[MAX_DNS_SUPPORTED]; +++}; +++ +++struct rpc_iostats; +++struct enfs_xprt_context { +++ struct sockaddr_storage srcaddr; +++ struct rpc_iostats *stats; +++ bool main; +++ atomic_t path_state; +++ atomic_t path_check_state; +++}; +++ +++static inline bool enfs_is_main_xprt(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = xprt->multipath_context; +++ +++ if (!ctx) +++ return false; +++ return ctx->main; +++} +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_init.c b/fs/nfs/enfs/enfs_init.c ++new file mode 100644 ++index 000000000000..4b55608191a7 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_init.c ++@@ -0,0 +1,98 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/module.h> +++#include <linux/sunrpc/sched.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs3.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include "enfs.h" +++#include "enfs_multipath_parse.h" +++#include "enfs_multipath_client.h" +++#include "enfs_remount.h" +++#include "init.h" +++#include "enfs_log.h" +++#include "enfs_multipath.h" +++#include "mgmt_init.h" +++ +++struct enfs_adapter_ops enfs_adapter = { +++ .name = "enfs", +++ .owner = THIS_MODULE, +++ .parse_mount_options = nfs_multipath_parse_options, +++ .free_mount_options = nfs_multipath_free_options, +++ .client_info_init = nfs_multipath_client_info_init, +++ .client_info_free = nfs_multipath_client_info_free, +++ .client_info_match = nfs_multipath_client_info_match, +++ .client_info_show = nfs_multipath_client_info_show, +++ .remount_ip_list = enfs_remount_iplist, +++}; +++ +++int32_t enfs_init(void) +++{ +++ int err; +++ +++ err = enfs_multipath_init(); +++ if (err) { +++ enfs_log_error("init multipath failed.\n"); +++ goto out; +++ } +++ +++ err = mgmt_init(); +++ if (err != 0) { +++ enfs_log_error("init mgmt failed.\n"); +++ goto out_tp_exit; +++ } +++ +++ return 0; +++ +++out_tp_exit: +++ enfs_multipath_exit(); +++out: +++ return err; +++} +++ +++void enfs_fini(void) +++{ +++ mgmt_fini(); +++ +++ enfs_multipath_exit(); +++} +++ +++static int __init init_enfs(void) +++{ +++ int ret; +++ +++ ret = enfs_adapter_register(&enfs_adapter); +++ if (ret) { +++ pr_err("regist enfs_adapter fail. ret %d\n", ret); +++ return -1; +++ } +++ +++ ret = enfs_init(); +++ if (ret) { +++ enfs_adapter_unregister(&enfs_adapter); +++ return -1; +++ } +++ +++ return 0; +++} +++ +++static void __exit exit_enfs(void) +++{ +++ enfs_fini(); +++ enfs_adapter_unregister(&enfs_adapter); +++} +++ +++MODULE_LICENSE("GPL"); +++MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +++MODULE_DESCRIPTION("Nfs client router"); +++MODULE_VERSION("1.0"); +++ +++module_init(init_enfs); +++module_exit(exit_enfs); ++diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c ++new file mode 100644 ++index 000000000000..63c02898a42c ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.c ++@@ -0,0 +1,340 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/proc_fs.h> +++#include <linux/seq_file.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/addr.h> +++#include "enfs_multipath_client.h" +++#include "enfs_multipath_parse.h" +++ +++int +++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, +++ const struct nfs_client_initdata *client_init_data) +++{ +++ struct multipath_mount_options *mount_options = +++ (struct multipath_mount_options *)client_init_data->enfs_option; +++ +++ if (mount_options->local_ip_list) { +++ client_info->local_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->local_ip_list) +++ return -ENOMEM; +++ +++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->remote_ip_list) { +++ +++ client_info->remote_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->remote_ip_list) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->remote_ip_list, +++ mount_options->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->pRemoteDnsInfo) { +++ client_info->pRemoteDnsInfo = +++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); +++ +++ if (!client_info->pRemoteDnsInfo) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ kfree(client_info->remote_ip_list); +++ client_info->remote_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->pRemoteDnsInfo, +++ mount_options->pRemoteDnsInfo, +++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); +++ } +++ return 0; +++} +++ +++void nfs_multipath_client_info_free_work(struct work_struct *work) +++{ +++ +++ struct multipath_client_info *clp_info; +++ +++ if (work == NULL) +++ return; +++ +++ clp_info = container_of(work, struct multipath_client_info, work); +++ +++ if (clp_info->local_ip_list != NULL) { +++ kfree(clp_info->local_ip_list); +++ clp_info->local_ip_list = NULL; +++ } +++ if (clp_info->remote_ip_list != NULL) { +++ kfree(clp_info->remote_ip_list); +++ clp_info->remote_ip_list = NULL; +++ } +++ kfree(clp_info); +++} +++ +++void nfs_multipath_client_info_free(void *data) +++{ +++ struct multipath_client_info *clp_info = +++ (struct multipath_client_info *)data; +++ +++ if (clp_info == NULL) +++ return; +++ pr_info("free client info %p.\n", clp_info); +++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); +++ schedule_work(&clp_info->work); +++} +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init) +++{ +++ int rc; +++ struct multipath_client_info *info; +++ struct multipath_client_info **enfs_info; +++ /* no multi path info, no need do multipath init */ +++ if (cl_init->enfs_option == NULL) +++ return 0; +++ enfs_info = (struct multipath_client_info **)data; +++ if (enfs_info == NULL) +++ return -EINVAL; +++ +++ if (*enfs_info == NULL) +++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), +++ GFP_KERNEL); +++ +++ if (*enfs_info == NULL) +++ return -ENOMEM; +++ +++ info = (struct multipath_client_info *)*enfs_info; +++ pr_info("init client info %p.\n", info); +++ rc = nfs_multipath_client_mount_info_init(info, cl_init); +++ if (rc) { +++ nfs_multipath_client_info_free((void *)info); +++ return rc; +++ } +++ return rc; +++} +++ +++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, +++ const struct nfs_ip_list *ip_list_dst) +++{ +++ int i; +++ int j; +++ bool is_find; +++ /* if both are equal or NULL, then return true. */ +++ if (ip_list_src == ip_list_dst) +++ return true; +++ +++ if ((ip_list_src == NULL || ip_list_dst == NULL)) +++ return false; +++ +++ if (ip_list_src->count != ip_list_dst->count) +++ return false; +++ +++ for (i = 0; i < ip_list_src->count; i++) { +++ is_find = false; +++ for (j = 0; j < ip_list_src->count; j++) { +++ if (rpc_cmp_addr_port( +++ (const struct sockaddr *) +++ &ip_list_src->address[i], +++ (const struct sockaddr *) +++ &ip_list_dst->address[j]) +++ ) { +++ is_find = true; +++ break; +++ } +++ } +++ if (is_find == false) +++ return false; +++ } +++ return true; +++} +++ +++int +++nfs_multipath_dns_list_info_match( +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) +++{ +++ int i; +++ +++ /* if both are equal or NULL, then return true. */ +++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) +++ return true; +++ +++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) +++ return false; +++ +++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) +++ return false; +++ +++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { +++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, +++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) +++ return false; +++ } +++ return true; +++} +++ +++int nfs_multipath_client_info_match(void *src, void *dst) +++{ +++ int ret = true; +++ +++ struct multipath_client_info *src_info; +++ struct multipath_mount_options *dst_info; +++ +++ src_info = (struct multipath_client_info *)src; +++ dst_info = (struct multipath_mount_options *)dst; +++ pr_info("try match client .\n"); +++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, +++ dst_info->local_ip_list); +++ if (ret == false) { +++ pr_err("local_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, +++ dst_info->remote_ip_list); +++ if (ret == false) { +++ pr_err("remote_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, +++ dst_info->pRemoteDnsInfo); +++ if (ret == false) { +++ pr_err("dns not match.\n"); +++ return ret; +++ } +++ pr_info("try match client ret %d.\n", ret); +++ return ret; +++} +++ +++void nfs_multipath_print_ip_info(struct seq_file *mount_option, +++ struct nfs_ip_list *ip_list, +++ const char *type) +++{ +++ char buf[IP_ADDRESS_LEN_MAX + 1]; +++ int len = 0; +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < ip_list->count; i++) { +++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], +++ buf, IP_ADDRESS_LEN_MAX); +++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) +++ buf[len] = '\0'; +++ +++ if (i == 0) +++ seq_printf(mount_option, "%s", buf); +++ else +++ seq_printf(mount_option, "~%s", buf); +++ dfprintk(MOUNT, +++ "NFS: show nfs mount option type:%s %s [%s]\n", +++ type, buf, __func__); +++ } +++} +++ +++void nfs_multipath_print_dns_info(struct seq_file *mount_option, +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, +++ const char *type) +++{ +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { +++ if (i == 0) +++ seq_printf(mount_option, +++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) +++ seq_printf(mount_option, ",%s]", +++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else +++ seq_printf(mount_option, +++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ } +++} +++ +++ +++static void multipath_print_sockaddr(struct seq_file *seq, +++ struct sockaddr *addr) +++{ +++ switch (addr->sa_family) { +++ case AF_INET: { +++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; +++ +++ seq_printf(seq, "%pI4", &sin->sin_addr); +++ return; +++ } +++ case AF_INET6: { +++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; +++ +++ seq_printf(seq, "%pI6", &sin6->sin6_addr); +++ return; +++ } +++ default: +++ break; +++ } +++ pr_err("unsupport family:%d\n", addr->sa_family); +++} +++ +++static void multipath_print_enfs_info(struct seq_file *seq, +++ struct nfs_server *server) +++{ +++ struct sockaddr_storage peeraddr; +++ struct rpc_clnt *next = server->client; +++ +++ rpc_peeraddr(server->client, +++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); +++ seq_puts(seq, ",enfs_info="); +++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); +++ +++ while (next->cl_parent) { +++ if (next == next->cl_parent) +++ break; +++ next = next->cl_parent; +++ } +++ seq_printf(seq, "_%u", next->cl_clid); +++} +++ +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) +++{ +++ struct nfs_server *server = data; +++ struct multipath_client_info *client_info = +++ server->nfs_client->cl_multipath_data; +++ +++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); +++ if ((client_info->remote_ip_list) && +++ (client_info->remote_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->remote_ip_list, +++ "remoteaddrs"); +++ +++ if ((client_info->local_ip_list) && +++ (client_info->local_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->local_ip_list, +++ "localaddrs"); +++ +++ if ((client_info->pRemoteDnsInfo) && +++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) +++ nfs_multipath_print_dns_info(mount_option, +++ client_info->pRemoteDnsInfo, +++ "remotednsname"); +++ +++ multipath_print_enfs_info(mount_option, server); +++} ++diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h ++new file mode 100644 ++index 000000000000..208f7260690d ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.h ++@@ -0,0 +1,26 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _ENFS_MULTIPATH_CLIENT_H_ +++#define _ENFS_MULTIPATH_CLIENT_H_ +++ +++#include "enfs.h" +++ +++struct multipath_client_info { +++ struct work_struct work; +++ struct nfs_ip_list *remote_ip_list; +++ struct nfs_ip_list *local_ip_list; +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; +++ s64 client_id; +++}; +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init); +++void nfs_multipath_client_info_free(void *data); +++int nfs_multipath_client_info_match(void *src, void *dst); +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_multipath_parse.c b/fs/nfs/enfs/enfs_multipath_parse.c ++new file mode 100644 ++index 000000000000..9c4c6c1880b6 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_parse.c ++@@ -0,0 +1,601 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/parser.h> +++#include <linux/kern_levels.h> +++#include <linux/sunrpc/addr.h> +++#include "enfs_multipath_parse.h" +++#include "enfs_log.h" +++ +++#define NFSDBG_FACILITY NFSDBG_CLIENT +++ +++void nfs_multipath_parse_ip_ipv6_add(struct sockaddr_in6 *sin6, int add_num) +++{ +++ int i; +++ +++ pr_info("NFS: before %08x%08x%08x%08x add_num: %d[%s]\n", +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), +++ add_num, __func__); +++ for (i = 0; i < add_num; i++) { +++ sin6->sin6_addr.in6_u.u6_addr32[3] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[3] != 0) +++ continue; +++ +++ sin6->sin6_addr.in6_u.u6_addr32[2] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[2] != 0) +++ continue; +++ +++ sin6->sin6_addr.in6_u.u6_addr32[1] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[1] != 0) +++ continue; +++ +++ sin6->sin6_addr.in6_u.u6_addr32[0] = +++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]) + 1); +++ +++ if (sin6->sin6_addr.in6_u.u6_addr32[0] != 0) +++ continue; +++ } +++ +++ return; +++ +++} +++ +++static int nfs_multipath_parse_ip_range(struct net *net_ns, const char *cursor, +++ struct nfs_ip_list *ip_list, enum nfsmultipathoptions type) +++{ +++ struct sockaddr_storage addr; +++ struct sockaddr_storage tmp_addr; +++ int i; +++ size_t len; +++ int add_num = 1; +++ bool duplicate_flag = false; +++ bool is_complete = false; +++ struct sockaddr_in *sin4; +++ struct sockaddr_in6 *sin6; +++ +++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", +++ cursor, type, __func__); +++ len = rpc_pton(net_ns, cursor, strlen(cursor), +++ (struct sockaddr *)&addr, sizeof(addr)); +++ if (!len) +++ return -EINVAL; +++ +++ if (addr.ss_family != ip_list->address[ip_list->count - 1].ss_family) { +++ pr_info("NFS: %s parsing nfs mount option type: %d fail.\n", +++ __func__, type); +++ return -EINVAL; +++ } +++ +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &ip_list->address[ip_list->count - 1], +++ (const struct sockaddr *)&addr)) { +++ +++ pr_info("range ip is same ip.\n"); +++ return 0; +++ +++ } +++ +++ while (true) { +++ +++ tmp_addr = ip_list->address[ip_list->count - 1]; +++ +++ switch (addr.ss_family) { +++ case AF_INET: +++ sin4 = (struct sockaddr_in *)&tmp_addr; +++ +++ sin4->sin_addr.s_addr = +++ htonl(ntohl(sin4->sin_addr.s_addr) + add_num); +++ +++ pr_info("NFS: mount option ip%08x type: %d ipcont %d [%s]\n", +++ ntohl(sin4->sin_addr.s_addr), +++ type, ip_list->count, __func__); +++ break; +++ case AF_INET6: +++ sin6 = (struct sockaddr_in6 *)&tmp_addr; +++ nfs_multipath_parse_ip_ipv6_add(sin6, add_num); +++ pr_info("NFS: mount option ip %08x%08x%08x%08x type: %d ipcont %d [%s]\n", +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), +++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), +++ type, ip_list->count, __func__); +++ break; +++ // return -EOPNOTSUPP; +++ default: +++ return -EOPNOTSUPP; +++ } +++ +++ if (rpc_cmp_addr((const struct sockaddr *)&tmp_addr, +++ (const struct sockaddr *)&addr)) { +++ is_complete = true; +++ } +++ // delete duplicate ip, continuosly repeat, skip it +++ for (i = 0; i < ip_list->count; i++) { +++ duplicate_flag = false; +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &ip_list->address[i], +++ (const struct sockaddr *)&tmp_addr)) { +++ add_num++; +++ duplicate_flag = true; +++ break; +++ } +++ } +++ +++ if (duplicate_flag == false) { +++ pr_info("this ip not duplicate;"); +++ add_num = 1; +++ // if not repeat but omit limit return false +++ if ((type == LOCALADDR && +++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || +++ (type == REMOTEADDR && +++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { +++ +++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", +++ __func__, type, ip_list->count, +++ type == LOCALADDR ? +++ MAX_SUPPORTED_LOCAL_IP_COUNT : +++ MAX_SUPPORTED_REMOTE_IP_COUNT); +++ ip_list->count = 0; +++ return -ENOSPC; +++ } +++ ip_list->address[ip_list->count] = tmp_addr; +++ +++ ip_list->addrlen[ip_list->count] = +++ ip_list->addrlen[ip_list->count - 1]; +++ +++ ip_list->count += 1; +++ } +++ if (is_complete == true) +++ break; +++ } +++ return 0; +++} +++ +++int nfs_multipath_parse_ip_list_inter(struct nfs_ip_list *ip_list, +++ struct net *net_ns, +++ char *cursor, enum nfsmultipathoptions type) +++{ +++ int i = 0; +++ struct sockaddr_storage addr; +++ struct sockaddr_storage swap; +++ int len; +++ +++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", +++ cursor, type, __func__); +++ +++ len = rpc_pton(net_ns, cursor, +++ strlen(cursor), +++ (struct sockaddr *)&addr, sizeof(addr)); +++ if (!len) +++ return -EINVAL; +++ +++ // check repeated ip +++ for (i = 0; i < ip_list->count; i++) { +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &ip_list->address[i], +++ (const struct sockaddr *)&addr)) { +++ +++ pr_info("NFS: mount option '%s' type:%d index %d same as before index %d [%s]\n", +++ cursor, type, ip_list->count, i, __func__); +++ // prevent this ip is beginning +++ // if repeated take it to the end of list +++ swap = ip_list->address[i]; +++ +++ ip_list->address[i] = +++ ip_list->address[ip_list->count-1]; +++ +++ ip_list->address[ip_list->count-1] = swap; +++ return 0; +++ } +++ } +++ // if not repeated, check exceed limit +++ if ((type == LOCALADDR && +++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || +++ (type == REMOTEADDR && +++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { +++ +++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", +++ __func__, type, ip_list->count, +++ type == LOCALADDR ? +++ MAX_SUPPORTED_LOCAL_IP_COUNT : +++ MAX_SUPPORTED_REMOTE_IP_COUNT); +++ +++ ip_list->count = 0; +++ return -ENOSPC; +++ } +++ ip_list->address[ip_list->count] = addr; +++ ip_list->addrlen[ip_list->count] = len; +++ ip_list->count++; +++ +++ return 0; +++} +++ +++char *nfs_multipath_parse_ip_list_get_cursor(char **buf_to_parse, bool *single) +++{ +++ char *cursor = NULL; +++ const char *single_sep = strchr(*buf_to_parse, '~'); +++ const char *range_sep = strchr(*buf_to_parse, '-'); +++ +++ *single = true; +++ if (range_sep) { +++ if (range_sep > single_sep) { // A-B or A~B-C +++ if (single_sep == NULL) { // A-B +++ cursor = strsep(buf_to_parse, "-"); +++ if (cursor) +++ *single = false; +++ } else// A~B-C +++ cursor = strsep(buf_to_parse, "~"); +++ } else { // A-B~C +++ cursor = strsep(buf_to_parse, "-"); +++ if (cursor) +++ *single = false; +++ } +++ } else { // A~B~C +++ cursor = strsep(buf_to_parse, "~"); +++ } +++ return cursor; +++} +++ +++bool nfs_multipath_parse_param_check(enum nfsmultipathoptions type, +++ struct multipath_mount_options *options) +++{ +++ if (type == REMOUNTREMOTEADDR && options->remote_ip_list->count != 0) { +++ memset(options->remote_ip_list, 0, sizeof(struct nfs_ip_list)); +++ return true; +++ } +++ if (type == REMOUNTLOCALADDR && options->local_ip_list->count != 0) { +++ memset(options->local_ip_list, 0, sizeof(struct nfs_ip_list)); +++ return true; +++ } +++ if ((type == REMOTEADDR || type == REMOTEDNSNAME) && +++ options->pRemoteDnsInfo->dnsNameCount != 0) { +++ +++ pr_info("[MULTIPATH:%s] parse for %d ,already have dns\n", +++ __func__, type); +++ return false; +++ } else if ((type == REMOTEADDR || type == REMOTEDNSNAME) && +++ options->remote_ip_list->count != 0) { +++ +++ pr_info("[MULTIPATH:%s] parse for %d ,already have iplist\n", +++ __func__, type); +++ return false; +++ } +++ return true; +++} +++ +++int nfs_multipath_parse_ip_list(char *buffer, struct net *net_ns, +++ struct multipath_mount_options *options, +++ enum nfsmultipathoptions type) +++{ +++ char *buf_to_parse = NULL; +++ bool prev_range = false; +++ int ret = 0; +++ char *cursor = NULL; +++ bool single = true; +++ struct nfs_ip_list *ip_list_tmp = NULL; +++ +++ if (!nfs_multipath_parse_param_check(type, options)) +++ return -ENOTSUPP; +++ +++ if (type == REMOUNTREMOTEADDR) +++ type = REMOTEADDR; +++ +++ if (type == REMOUNTLOCALADDR) +++ type = LOCALADDR; +++ +++ if (type == LOCALADDR) +++ ip_list_tmp = options->local_ip_list; +++ else +++ ip_list_tmp = options->remote_ip_list; +++ +++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", +++ buffer, type, __func__); +++ +++ buf_to_parse = buffer; +++ while (buf_to_parse != NULL) { +++ cursor = +++ nfs_multipath_parse_ip_list_get_cursor(&buf_to_parse, &single); +++ if (!cursor) +++ break; +++ +++ if (single == false && prev_range == true) { +++ pr_info("NFS: mount option type: %d fail. Multiple Range.[%s]\n", +++ type, __func__); +++ +++ ret = -EINVAL; +++ goto out; +++ } +++ +++ if (prev_range == false) { +++ ret = nfs_multipath_parse_ip_list_inter(ip_list_tmp, +++ net_ns, cursor, type); +++ if (ret) +++ goto out; +++ if (single == false) +++ prev_range = true; +++ } else { +++ ret = nfs_multipath_parse_ip_range(net_ns, cursor, +++ ip_list_tmp, type); +++ if (ret != 0) +++ goto out; +++ prev_range = false; +++ } +++ } +++ +++out: +++ if (ret) +++ memset(ip_list_tmp, 0, sizeof(struct nfs_ip_list)); +++ +++ return ret; +++} +++ +++int nfs_multipath_parse_dns_list(char *buffer, struct net *net_ns, +++ struct multipath_mount_options *options) +++{ +++ struct NFS_ROUTE_DNS_INFO_S *dns_name_list_tmp = NULL; +++ char *cursor = NULL; +++ char *bufToParse; +++ +++ if (!nfs_multipath_parse_param_check(REMOTEDNSNAME, options)) +++ return -ENOTSUPP; +++ +++ pr_info("[MULTIPATH:%s] buffer %s\n", __func__, buffer); +++ // freed in nfs_free_parsed_mount_data +++ dns_name_list_tmp = kmalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), +++ GFP_KERNEL); +++ if (!dns_name_list_tmp) +++ return -ENOMEM; +++ +++ dns_name_list_tmp->dnsNameCount = 0; +++ bufToParse = buffer; +++ while (bufToParse) { +++ if (dns_name_list_tmp->dnsNameCount >= MAX_DNS_SUPPORTED) { +++ pr_err("%s: dnsname for %s reached %d,more than supported limit %d\n", +++ __func__, cursor, +++ dns_name_list_tmp->dnsNameCount, +++ MAX_DNS_SUPPORTED); +++ dns_name_list_tmp->dnsNameCount = 0; +++ return -ENOSPC; +++ } +++ cursor = strsep(&bufToParse, "~"); +++ if (!cursor) +++ break; +++ +++ strcpy(dns_name_list_tmp->routeRemoteDnsList +++ [dns_name_list_tmp->dnsNameCount].dnsname, +++ cursor); +++ dns_name_list_tmp->dnsNameCount++; +++ } +++ if (dns_name_list_tmp->dnsNameCount == 0) +++ return -EINVAL; +++ options->pRemoteDnsInfo = dns_name_list_tmp; +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check_ipv4_valid(struct sockaddr_in *addr) +++{ +++ if (addr->sin_addr.s_addr == 0 || addr->sin_addr.s_addr == 0xffffffff) +++ return -EINVAL; +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check_ipv6_valid(struct sockaddr_in6 *addr) +++{ +++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0 && +++ addr->sin6_addr.in6_u.u6_addr32[1] == 0 && +++ addr->sin6_addr.in6_u.u6_addr32[2] == 0 && +++ addr->sin6_addr.in6_u.u6_addr32[3] == 0) +++ return -EINVAL; +++ +++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0xffffffff && +++ addr->sin6_addr.in6_u.u6_addr32[1] == 0xffffffff && +++ addr->sin6_addr.in6_u.u6_addr32[2] == 0xffffffff && +++ addr->sin6_addr.in6_u.u6_addr32[3] == 0xffffffff) +++ return -EINVAL; +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check_ip_valid(struct sockaddr_storage *address) +++{ +++ int rc = 0; +++ +++ if (address->ss_family == AF_INET) +++ rc = nfs_multipath_parse_options_check_ipv4_valid( +++ (struct sockaddr_in *)address); +++ else if (address->ss_family == AF_INET6) +++ rc = nfs_multipath_parse_options_check_ipv6_valid( +++ (struct sockaddr_in6 *)address); +++ else +++ rc = -EINVAL; +++ +++ return rc; +++} +++ +++int nfs_multipath_parse_options_check_valid( +++ struct multipath_mount_options *options) +++{ +++ int rc; +++ int i; +++ +++ if (options == NULL) +++ return 0; +++ +++ for (i = 0; i < options->local_ip_list->count; i++) { +++ rc = nfs_multipath_parse_options_check_ip_valid( +++ &options->local_ip_list->address[i]); +++ if (rc != 0) +++ return rc; +++ } +++ +++ for (i = 0; i < options->remote_ip_list->count; i++) { +++ rc = nfs_multipath_parse_options_check_ip_valid( +++ &options->remote_ip_list->address[i]); +++ if (rc != 0) +++ return rc; +++ } +++ +++ return 0; +++} +++int nfs_multipath_parse_options_check_duplicate( +++ struct multipath_mount_options *options) +++{ +++ int i; +++ int j; +++ +++ if (options == NULL || +++ options->local_ip_list->count == 0 || +++ options->remote_ip_list->count == 0) +++ +++ return 0; +++ +++ for (i = 0; i < options->local_ip_list->count; i++) { +++ for (j = 0; j < options->remote_ip_list->count; j++) { +++ if (rpc_cmp_addr((const struct sockaddr *) +++ &options->local_ip_list->address[i], +++ (const struct sockaddr *) +++ &options->remote_ip_list->address[j])) +++ return -ENOTSUPP; +++ } +++ } +++ return 0; +++} +++ +++int nfs_multipath_parse_options_check(struct multipath_mount_options *options) +++{ +++ int rc = 0; +++ +++ rc = nfs_multipath_parse_options_check_valid(options); +++ +++ if (rc != 0) { +++ pr_err("has invaild ip.\n"); +++ return rc; +++ } +++ +++ rc = nfs_multipath_parse_options_check_duplicate(options); +++ if (rc != 0) +++ return rc; +++ return rc; +++} +++ +++int nfs_multipath_alloc_options(void **enfs_option) +++{ +++ struct multipath_mount_options *options = NULL; +++ +++ options = kzalloc(sizeof(struct multipath_mount_options), GFP_KERNEL); +++ +++ if (options == NULL) +++ return -ENOMEM; +++ +++ options->local_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ if (options->local_ip_list == NULL) { +++ kfree(options); +++ return -ENOMEM; +++ } +++ +++ options->remote_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ if (options->remote_ip_list == NULL) { +++ kfree(options->local_ip_list); +++ kfree(options); +++ return -ENOMEM; +++ } +++ +++ options->pRemoteDnsInfo = kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), +++ GFP_KERNEL); +++ if (options->pRemoteDnsInfo == NULL) { +++ kfree(options->remote_ip_list); +++ kfree(options->local_ip_list); +++ kfree(options); +++ return -ENOMEM; +++ } +++ +++ *enfs_option = options; +++ return 0; +++} +++ +++int nfs_multipath_parse_options(enum nfsmultipathoptions type, +++ char *str, void **enfs_option, struct net *net_ns) +++{ +++ int rc; +++ struct multipath_mount_options *options = NULL; +++ +++ if ((str == NULL) || (enfs_option == NULL) || (net_ns == NULL)) +++ return -EINVAL; +++ +++ if (*enfs_option == NULL) { +++ rc = nfs_multipath_alloc_options(enfs_option); +++ if (rc != 0) { +++ enfs_log_error( +++ "alloc enfs_options failed! errno:%d\n", rc); +++ return rc; +++ } +++ } +++ +++ options = (struct multipath_mount_options *)*enfs_option; +++ +++ if (type == LOCALADDR || type == REMOUNTLOCALADDR || +++ type == REMOTEADDR || type == REMOUNTREMOTEADDR) { +++ rc = nfs_multipath_parse_ip_list(str, net_ns, options, type); +++ } else if (type == REMOTEDNSNAME) { +++ /* alloc and release need to modify */ +++ rc = nfs_multipath_parse_dns_list(str, net_ns, options); +++ } else { +++ rc = -EOPNOTSUPP; +++ } +++ +++ // after parsing cmd, need checking local and remote +++ // IP is same. if not means illegal cmd +++ if (rc == 0) +++ rc = nfs_multipath_parse_options_check_duplicate(options); +++ +++ if (rc == 0) +++ rc = nfs_multipath_parse_options_check(options); +++ +++ return rc; +++} +++ +++void nfs_multipath_free_options(void **enfs_option) +++{ +++ struct multipath_mount_options *options; +++ +++ if (enfs_option == NULL || *enfs_option == NULL) +++ return; +++ +++ options = (struct multipath_mount_options *)*enfs_option; +++ +++ if (options->remote_ip_list != NULL) { +++ kfree(options->remote_ip_list); +++ options->remote_ip_list = NULL; +++ } +++ +++ if (options->local_ip_list != NULL) { +++ kfree(options->local_ip_list); +++ options->local_ip_list = NULL; +++ } +++ +++ if (options->pRemoteDnsInfo != NULL) { +++ kfree(options->pRemoteDnsInfo); +++ options->pRemoteDnsInfo = NULL; +++ } +++ +++ kfree(options); +++ *enfs_option = NULL; +++} ++diff --git a/fs/nfs/enfs/enfs_multipath_parse.h b/fs/nfs/enfs/enfs_multipath_parse.h ++new file mode 100644 ++index 000000000000..6f3e8703e3e2 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_parse.h ++@@ -0,0 +1,22 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _ENFS_MULTIPATH_PARSE_H_ +++#define _ENFS_MULTIPATH_PARSE_H_ +++ +++#include "enfs.h" +++ +++struct multipath_mount_options { +++ struct nfs_ip_list *remote_ip_list; +++ struct nfs_ip_list *local_ip_list; +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; +++}; +++ +++int nfs_multipath_parse_options(enum nfsmultipathoptions type, +++ char *str, void **enfs_option, struct net *net_ns); +++void nfs_multipath_free_options(void **enfs_option); +++ +++#endif +diff --git a/0004-add_enfs_module_for_sunrpc_multipatch.patch b/0004-add_enfs_module_for_sunrpc_multipatch.patch +new file mode 100644 +index 0000000..2c0fcc7 +--- /dev/null ++++ b/0004-add_enfs_module_for_sunrpc_multipatch.patch +@@ -0,0 +1,1581 @@ ++diff --git a/fs/nfs/enfs/enfs_multipath.h b/fs/nfs/enfs/enfs_multipath.h ++new file mode 100644 ++index 000000000000..e064c2929ced ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath.h ++@@ -0,0 +1,24 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: enfs multipath +++ * Author: +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef ENFS_MULTIPATH_H +++#define ENFS_MULTIPATH_H +++#include <linux/sunrpc/clnt.h> +++ +++#define MAX_XPRT_NUM_PER_CLIENT 32 +++ +++int enfs_multipath_init(void); +++void enfs_multipath_exit(void); +++void enfs_xprt_ippair_create(struct xprt_create *xprtargs, +++ struct rpc_clnt *clnt, void *data); +++int enfs_config_xprt_create_args(struct xprt_create *xprtargs, +++ struct rpc_create_args *args, +++ char *servername, size_t length); +++void print_enfs_multipath_addr(struct sockaddr *local, struct sockaddr *remote); +++ +++#endif // ENFS_MULTIPATH_H ++diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c ++new file mode 100644 ++index 000000000000..63c02898a42c ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.c ++@@ -0,0 +1,340 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#include <linux/types.h> +++#include <linux/nfs.h> +++#include <linux/nfs4.h> +++#include <linux/nfs_fs.h> +++#include <linux/nfs_fs_sb.h> +++#include <linux/proc_fs.h> +++#include <linux/seq_file.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/addr.h> +++#include "enfs_multipath_client.h" +++#include "enfs_multipath_parse.h" +++ +++int +++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, +++ const struct nfs_client_initdata *client_init_data) +++{ +++ struct multipath_mount_options *mount_options = +++ (struct multipath_mount_options *)client_init_data->enfs_option; +++ +++ if (mount_options->local_ip_list) { +++ client_info->local_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->local_ip_list) +++ return -ENOMEM; +++ +++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->remote_ip_list) { +++ +++ client_info->remote_ip_list = +++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); +++ +++ if (!client_info->remote_ip_list) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->remote_ip_list, +++ mount_options->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (mount_options->pRemoteDnsInfo) { +++ client_info->pRemoteDnsInfo = +++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); +++ +++ if (!client_info->pRemoteDnsInfo) { +++ kfree(client_info->local_ip_list); +++ client_info->local_ip_list = NULL; +++ kfree(client_info->remote_ip_list); +++ client_info->remote_ip_list = NULL; +++ return -ENOMEM; +++ } +++ memcpy(client_info->pRemoteDnsInfo, +++ mount_options->pRemoteDnsInfo, +++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); +++ } +++ return 0; +++} +++ +++void nfs_multipath_client_info_free_work(struct work_struct *work) +++{ +++ +++ struct multipath_client_info *clp_info; +++ +++ if (work == NULL) +++ return; +++ +++ clp_info = container_of(work, struct multipath_client_info, work); +++ +++ if (clp_info->local_ip_list != NULL) { +++ kfree(clp_info->local_ip_list); +++ clp_info->local_ip_list = NULL; +++ } +++ if (clp_info->remote_ip_list != NULL) { +++ kfree(clp_info->remote_ip_list); +++ clp_info->remote_ip_list = NULL; +++ } +++ kfree(clp_info); +++} +++ +++void nfs_multipath_client_info_free(void *data) +++{ +++ struct multipath_client_info *clp_info = +++ (struct multipath_client_info *)data; +++ +++ if (clp_info == NULL) +++ return; +++ pr_info("free client info %p.\n", clp_info); +++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); +++ schedule_work(&clp_info->work); +++} +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init) +++{ +++ int rc; +++ struct multipath_client_info *info; +++ struct multipath_client_info **enfs_info; +++ /* no multi path info, no need do multipath init */ +++ if (cl_init->enfs_option == NULL) +++ return 0; +++ enfs_info = (struct multipath_client_info **)data; +++ if (enfs_info == NULL) +++ return -EINVAL; +++ +++ if (*enfs_info == NULL) +++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), +++ GFP_KERNEL); +++ +++ if (*enfs_info == NULL) +++ return -ENOMEM; +++ +++ info = (struct multipath_client_info *)*enfs_info; +++ pr_info("init client info %p.\n", info); +++ rc = nfs_multipath_client_mount_info_init(info, cl_init); +++ if (rc) { +++ nfs_multipath_client_info_free((void *)info); +++ return rc; +++ } +++ return rc; +++} +++ +++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, +++ const struct nfs_ip_list *ip_list_dst) +++{ +++ int i; +++ int j; +++ bool is_find; +++ /* if both are equal or NULL, then return true. */ +++ if (ip_list_src == ip_list_dst) +++ return true; +++ +++ if ((ip_list_src == NULL || ip_list_dst == NULL)) +++ return false; +++ +++ if (ip_list_src->count != ip_list_dst->count) +++ return false; +++ +++ for (i = 0; i < ip_list_src->count; i++) { +++ is_find = false; +++ for (j = 0; j < ip_list_src->count; j++) { +++ if (rpc_cmp_addr_port( +++ (const struct sockaddr *) +++ &ip_list_src->address[i], +++ (const struct sockaddr *) +++ &ip_list_dst->address[j]) +++ ) { +++ is_find = true; +++ break; +++ } +++ } +++ if (is_find == false) +++ return false; +++ } +++ return true; +++} +++ +++int +++nfs_multipath_dns_list_info_match( +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, +++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) +++{ +++ int i; +++ +++ /* if both are equal or NULL, then return true. */ +++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) +++ return true; +++ +++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) +++ return false; +++ +++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) +++ return false; +++ +++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { +++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, +++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) +++ return false; +++ } +++ return true; +++} +++ +++int nfs_multipath_client_info_match(void *src, void *dst) +++{ +++ int ret = true; +++ +++ struct multipath_client_info *src_info; +++ struct multipath_mount_options *dst_info; +++ +++ src_info = (struct multipath_client_info *)src; +++ dst_info = (struct multipath_mount_options *)dst; +++ pr_info("try match client .\n"); +++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, +++ dst_info->local_ip_list); +++ if (ret == false) { +++ pr_err("local_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, +++ dst_info->remote_ip_list); +++ if (ret == false) { +++ pr_err("remote_ip not match.\n"); +++ return ret; +++ } +++ +++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, +++ dst_info->pRemoteDnsInfo); +++ if (ret == false) { +++ pr_err("dns not match.\n"); +++ return ret; +++ } +++ pr_info("try match client ret %d.\n", ret); +++ return ret; +++} +++ +++void nfs_multipath_print_ip_info(struct seq_file *mount_option, +++ struct nfs_ip_list *ip_list, +++ const char *type) +++{ +++ char buf[IP_ADDRESS_LEN_MAX + 1]; +++ int len = 0; +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < ip_list->count; i++) { +++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], +++ buf, IP_ADDRESS_LEN_MAX); +++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) +++ buf[len] = '\0'; +++ +++ if (i == 0) +++ seq_printf(mount_option, "%s", buf); +++ else +++ seq_printf(mount_option, "~%s", buf); +++ dfprintk(MOUNT, +++ "NFS: show nfs mount option type:%s %s [%s]\n", +++ type, buf, __func__); +++ } +++} +++ +++void nfs_multipath_print_dns_info(struct seq_file *mount_option, +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, +++ const char *type) +++{ +++ int i = 0; +++ +++ seq_printf(mount_option, ",%s=", type); +++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { +++ if (i == 0) +++ seq_printf(mount_option, +++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) +++ seq_printf(mount_option, ",%s]", +++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ else +++ seq_printf(mount_option, +++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); +++ } +++} +++ +++ +++static void multipath_print_sockaddr(struct seq_file *seq, +++ struct sockaddr *addr) +++{ +++ switch (addr->sa_family) { +++ case AF_INET: { +++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; +++ +++ seq_printf(seq, "%pI4", &sin->sin_addr); +++ return; +++ } +++ case AF_INET6: { +++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; +++ +++ seq_printf(seq, "%pI6", &sin6->sin6_addr); +++ return; +++ } +++ default: +++ break; +++ } +++ pr_err("unsupport family:%d\n", addr->sa_family); +++} +++ +++static void multipath_print_enfs_info(struct seq_file *seq, +++ struct nfs_server *server) +++{ +++ struct sockaddr_storage peeraddr; +++ struct rpc_clnt *next = server->client; +++ +++ rpc_peeraddr(server->client, +++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); +++ seq_puts(seq, ",enfs_info="); +++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); +++ +++ while (next->cl_parent) { +++ if (next == next->cl_parent) +++ break; +++ next = next->cl_parent; +++ } +++ seq_printf(seq, "_%u", next->cl_clid); +++} +++ +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) +++{ +++ struct nfs_server *server = data; +++ struct multipath_client_info *client_info = +++ server->nfs_client->cl_multipath_data; +++ +++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); +++ if ((client_info->remote_ip_list) && +++ (client_info->remote_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->remote_ip_list, +++ "remoteaddrs"); +++ +++ if ((client_info->local_ip_list) && +++ (client_info->local_ip_list->count > 0)) +++ nfs_multipath_print_ip_info(mount_option, +++ client_info->local_ip_list, +++ "localaddrs"); +++ +++ if ((client_info->pRemoteDnsInfo) && +++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) +++ nfs_multipath_print_dns_info(mount_option, +++ client_info->pRemoteDnsInfo, +++ "remotednsname"); +++ +++ multipath_print_enfs_info(mount_option, server); +++} ++diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h ++new file mode 100644 ++index 000000000000..208f7260690d ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_multipath_client.h ++@@ -0,0 +1,26 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS adapter. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef _ENFS_MULTIPATH_CLIENT_H_ +++#define _ENFS_MULTIPATH_CLIENT_H_ +++ +++#include "enfs.h" +++ +++struct multipath_client_info { +++ struct work_struct work; +++ struct nfs_ip_list *remote_ip_list; +++ struct nfs_ip_list *local_ip_list; +++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; +++ s64 client_id; +++}; +++ +++int nfs_multipath_client_info_init(void **data, +++ const struct nfs_client_initdata *cl_init); +++void nfs_multipath_client_info_free(void *data); +++int nfs_multipath_client_info_match(void *src, void *dst); +++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_path.c b/fs/nfs/enfs/enfs_path.c ++new file mode 100644 ++index 000000000000..7355f8c2f672 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_path.c ++@@ -0,0 +1,47 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++ +++#include <linux/sunrpc/metrics.h> +++#include <linux/sunrpc/xprt.h> +++ +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_path.h" +++ +++// only create ctx in this function +++// alloc iostat memory in create_clnt +++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx; +++ +++ if (!xprt) { +++ enfs_log_error("invalid xprt pointer.\n"); +++ return -EINVAL; +++ } +++ +++ ctx = kzalloc(sizeof(struct enfs_xprt_context), GFP_KERNEL); +++ if (!ctx) { +++ enfs_log_error("add xprt test failed.\n"); +++ return -ENOMEM; +++ } +++ +++ xprt->multipath_context = (void *)ctx; +++ return 0; +++} +++ +++// free multi_context and iostat memory +++void enfs_free_xprt_ctx(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = xprt->multipath_context; +++ +++ if (ctx) { +++ if (ctx->stats) { +++ rpc_free_iostats(ctx->stats); +++ ctx->stats = NULL; +++ } +++ kfree(xprt->multipath_context); +++ xprt->multipath_context = NULL; +++ } +++} ++diff --git a/fs/nfs/enfs/enfs_path.h b/fs/nfs/enfs/enfs_path.h ++new file mode 100644 ++index 000000000000..97b1ef3730b8 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_path.h ++@@ -0,0 +1,12 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++ +++#ifndef ENFS_PATH_H +++#define ENFS_PATH_H +++ +++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt); +++void enfs_free_xprt_ctx(struct rpc_xprt *xprt); +++ +++#endif // ENFS_PATH_H ++diff --git a/fs/nfs/enfs/enfs_proc.c b/fs/nfs/enfs/enfs_proc.c ++new file mode 100644 ++index 000000000000..53fa1a07642f ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_proc.c ++@@ -0,0 +1,545 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#include <linux/module.h> +++#include <linux/proc_fs.h> +++#include <linux/seq_file.h> +++#include <linux/spinlock.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/metrics.h> +++#include <linux/sunrpc/xprtsock.h> +++#include <net/netns/generic.h> +++ +++#include "../../../net/sunrpc/netns.h" +++ +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_proc.h" +++#include "enfs_multipath.h" +++#include "pm_state.h" +++ +++#define ENFS_PROC_DIR "enfs" +++#define ENFS_PROC_PATH_STATUS_LEN 256 +++ +++static struct proc_dir_entry *enfs_proc_parent; +++ +++void +++enfs_iterate_each_rpc_clnt(int (*fn)(struct rpc_clnt *clnt, void *data), +++ void *data) +++{ +++ struct net *net; +++ struct sunrpc_net *sn; +++ struct rpc_clnt *clnt; +++ +++ rcu_read_lock(); +++ for_each_net_rcu(net) { +++ sn = net_generic(net, sunrpc_net_id); +++ if (sn == NULL) +++ continue; +++ spin_lock(&sn->rpc_client_lock); +++ list_for_each_entry(clnt, &sn->all_clients, cl_clients) { +++ fn(clnt, data); +++ } +++ spin_unlock(&sn->rpc_client_lock); +++ } +++ rcu_read_unlock(); +++} +++ +++struct proc_dir_entry *enfs_get_proc_parent(void) +++{ +++ return enfs_proc_parent; +++} +++ +++static int sockaddr_ip_to_str(struct sockaddr *addr, char *buf, int len) +++{ +++ switch (addr->sa_family) { +++ case AF_INET: { +++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; +++ +++ snprintf(buf, len, "%pI4", &sin->sin_addr); +++ return 0; +++ } +++ case AF_INET6: { +++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; +++ +++ snprintf(buf, len, "%pI6", &sin6->sin6_addr); +++ return 0; +++ } +++ default: +++ break; +++ } +++ return 1; +++} +++ +++static bool should_print(const char *name) +++{ +++ int i; +++ static const char * const proc_names[] = { +++ "READ", +++ "WRITE", +++ }; +++ +++ if (name == NULL) +++ return false; +++ +++ for (i = 0; i < ARRAY_SIZE(proc_names); i++) { +++ if (strcmp(name, proc_names[i]) == 0) +++ return true; +++ } +++ return false; +++} +++ +++struct enfs_xprt_iter { +++ unsigned int id; +++ struct seq_file *seq; +++ unsigned int max_addrs_length; +++}; +++ +++static int debug_show_xprt(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ +++ if (xprt->multipath_context) +++ ctx = xprt->multipath_context; +++ +++ pr_info(" xprt:%p ctx:%p main:%d queue_len:%lu.\n", xprt, +++ xprt->multipath_context, +++ ctx ? ctx->main : false, +++ atomic_long_read(&xprt->queuelen)); +++ return 0; +++} +++ +++static int debug_show_clnt(struct rpc_clnt *clnt, void *data) +++{ +++ pr_info(" clnt %d addr:%p enfs:%d\n", +++ clnt->cl_clid, clnt, +++ clnt->cl_enfs); +++ rpc_clnt_iterate_for_each_xprt(clnt, debug_show_xprt, NULL); +++ return 0; +++} +++ +++static void debug_print_all_xprt(void) +++{ +++ enfs_iterate_each_rpc_clnt(debug_show_clnt, NULL); +++} +++ +++static +++void enfs_proc_format_xprt_addr_display(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ char *local_name_buf, +++ int local_name_buf_len, +++ char *remote_name_buf, +++ int remote_name_buf_len) +++{ +++ int err; +++ struct sockaddr_storage srcaddr; +++ struct enfs_xprt_context *ctx; +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ sockaddr_ip_to_str((struct sockaddr *)&xprt->addr, +++ remote_name_buf, remote_name_buf_len); +++ +++ // get local address depend one main or not +++ if (enfs_is_main_xprt(xprt)) { +++ err = rpc_localaddr(clnt, (struct sockaddr *)&srcaddr, +++ sizeof(srcaddr)); +++ if (err != 0) +++ (void)snprintf(local_name_buf, +++ local_name_buf_len, "Unknown"); +++ else +++ sockaddr_ip_to_str((struct sockaddr *)&srcaddr, +++ local_name_buf, +++ local_name_buf_len); +++ } else { +++ sockaddr_ip_to_str((struct sockaddr *)&ctx->srcaddr, +++ local_name_buf, +++ local_name_buf_len); +++ } +++} +++ +++static int enfs_show_xprt_stats(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ unsigned int op; +++ unsigned int maxproc = clnt->cl_maxproc; +++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; +++ struct enfs_xprt_context *ctx; +++ char local_name[INET6_ADDRSTRLEN]; +++ char remote_name[INET6_ADDRSTRLEN]; +++ +++ if (!xprt->multipath_context) +++ return 0; +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ enfs_proc_format_xprt_addr_display(clnt, xprt, local_name, +++ sizeof(local_name), +++ remote_name, sizeof(remote_name)); +++ +++ seq_printf(iter->seq, "%-6u%-*s%-*s", iter->id, +++ iter->max_addrs_length + 4, +++ local_name, +++ iter->max_addrs_length + 4, +++ remote_name); +++ +++ iter->id++; +++ +++ for (op = 0; op < maxproc; op++) { +++ if (!should_print(clnt->cl_procinfo[op].p_name)) +++ continue; +++ +++ seq_printf(iter->seq, "%-22lu%-22Lu%-22Lu", +++ ctx->stats[op].om_ops, +++ ctx->stats[op].om_ops == 0 ? 0 : +++ ktime_to_ms(ctx->stats[op].om_rtt) / +++ ctx->stats[op].om_ops, +++ ctx->stats[op].om_ops == 0 ? 0 : +++ ktime_to_ms(ctx->stats[op].om_execute) / +++ ctx->stats[op].om_ops); +++ } +++ seq_puts(iter->seq, "\n"); +++ return 0; +++} +++ +++static int rpc_proc_show_path_status(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; +++ struct enfs_xprt_context *ctx = NULL; +++ char local_name[INET6_ADDRSTRLEN] = {0}; +++ char remote_name[INET6_ADDRSTRLEN] = {0}; +++ char multiapth_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; +++ char xprt_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; +++ +++ if (!xprt->multipath_context) { +++ enfs_log_debug("multipath_context is null.\n"); +++ return 0; +++ } +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ enfs_proc_format_xprt_addr_display(clnt, xprt, +++ local_name, +++ sizeof(local_name), +++ remote_name, sizeof(remote_name)); +++ +++ pm_get_path_state_desc(xprt, +++ multiapth_status, +++ ENFS_PROC_PATH_STATUS_LEN); +++ +++ pm_get_xprt_state_desc(xprt, +++ xprt_status, +++ ENFS_PROC_PATH_STATUS_LEN); +++ +++ seq_printf(iter->seq, "%-6u%-*s%-*s%-12s%-12s\n", +++ iter->id, iter->max_addrs_length + 4, +++ local_name, iter->max_addrs_length + 4, +++ remote_name, multiapth_status, +++ xprt_status); +++ iter->id++; +++ return 0; +++} +++ +++static int enfs_get_max_addrs_length(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; +++ char local_name[INET6_ADDRSTRLEN]; +++ char remote_name[INET6_ADDRSTRLEN]; +++ +++ enfs_proc_format_xprt_addr_display(clnt, xprt, +++ local_name, sizeof(local_name), +++ remote_name, sizeof(remote_name)); +++ +++ if (iter->max_addrs_length < strlen(local_name)) +++ iter->max_addrs_length = strlen(local_name); +++ +++ if (iter->max_addrs_length < strlen(remote_name)) +++ iter->max_addrs_length = strlen(remote_name); +++ +++ return 0; +++} +++ +++static int rpc_proc_clnt_showpath(struct seq_file *seq, void *v) +++{ +++ struct rpc_clnt *clnt = seq->private; +++ struct enfs_xprt_iter iter; +++ +++ iter.seq = seq; +++ iter.id = 0; +++ iter.max_addrs_length = 0; +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ enfs_get_max_addrs_length, +++ (void *)&iter); +++ +++ seq_printf(seq, "%-6s%-*s%-*s%-12s%-12s\n", "id", +++ iter.max_addrs_length + 4, +++ "local_addr", +++ iter.max_addrs_length + 4, +++ "remote_addr", +++ "path_state", +++ "xprt_state"); +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ rpc_proc_show_path_status, +++ (void *)&iter); +++ return 0; +++} +++ +++static int enfs_rpc_proc_show(struct seq_file *seq, void *v) +++{ +++ struct rpc_clnt *clnt = seq->private; +++ struct enfs_xprt_iter iter; +++ +++ iter.seq = seq; +++ iter.id = 0; +++ iter.max_addrs_length = 0; +++ +++ debug_print_all_xprt(); +++ pr_info("enfs proc clnt:%p\n", clnt); +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ enfs_get_max_addrs_length, +++ (void *)&iter); +++ +++ seq_printf(seq, "%-6s%-*s%-*s%-22s%-22s%-22s%-22s%-22s%-22s\n", "id", +++ iter.max_addrs_length + 4, "local_addr", +++ iter.max_addrs_length + 4, +++ "remote_addr", "r_count", +++ "r_rtt", "r_exec", "w_count", "w_rtt", "w_exec"); +++ +++ // rpc_clnt_show_stats(seq, clnt); +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ enfs_show_xprt_stats, +++ (void *)&iter); +++ return 0; +++} +++ +++static int rpc_proc_open(struct inode *inode, struct file *file) +++{ +++ struct rpc_clnt *clnt = PDE_DATA(inode); +++ +++ pr_info("%s %p\n", __func__, clnt); +++ return single_open(file, enfs_rpc_proc_show, clnt); +++} +++ +++static int enfs_reset_xprt_stats(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void *data) +++{ +++ unsigned int op; +++ struct enfs_xprt_context *ctx; +++ unsigned int maxproc = clnt->cl_maxproc; +++ struct rpc_iostats stats = {0}; +++ +++ if (!xprt->multipath_context) +++ return 0; +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ +++ for (op = 0; op < maxproc; op++) { +++ spin_lock(&ctx->stats[op].om_lock); +++ ctx->stats[op] = stats; +++ spin_unlock(&ctx->stats[op].om_lock); +++ } +++ return 0; +++} +++ +++static void trim_newline_ch(char *str, int len) +++{ +++ int i; +++ +++ for (i = 0; str[i] != '\0' && i < len; i++) { +++ if (str[i] == '\n') +++ str[i] = '\0'; +++ } +++} +++ +++static ssize_t enfs_proc_write(struct file *file, +++ const char __user *user_buf, +++ size_t len, +++ loff_t *offset) +++{ +++ char buffer[128]; +++ struct rpc_clnt *clnt = +++ ((struct seq_file *)file->private_data)->private; +++ +++ if (len >= sizeof(buffer)) +++ return -E2BIG; +++ +++ if (copy_from_user(buffer, user_buf, len) != 0) +++ return -EFAULT; +++ +++ buffer[len] = '\0'; +++ trim_newline_ch(buffer, len); +++ if (strcmp(buffer, "reset") != 0) +++ return -EINVAL; +++ +++ rpc_clnt_iterate_for_each_xprt(clnt, enfs_reset_xprt_stats, NULL); +++ return len; +++} +++ +++static int rpc_proc_show_path(struct inode *inode, struct file *file) +++{ +++ struct rpc_clnt *clnt = PDE_DATA(inode); +++ +++ return single_open(file, rpc_proc_clnt_showpath, clnt); +++} +++ +++static const struct file_operations rpc_proc_fops = { +++ .owner = THIS_MODULE, +++ .open = rpc_proc_open, +++ .read = seq_read, +++ .llseek = seq_lseek, +++ .release = single_release, +++ .write = enfs_proc_write, +++}; +++ +++static const struct file_operations rpc_show_path_fops = { +++ .owner = THIS_MODULE, +++ .open = rpc_proc_show_path, +++ .read = seq_read, +++ .llseek = seq_lseek, +++ .release = single_release, +++}; +++ +++static int clnt_proc_name(struct rpc_clnt *clnt, char *buf, int len) +++{ +++ int ret; +++ +++ ret = snprintf(buf, len, "%s_%u", +++ rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR), +++ clnt->cl_clid); +++ if (ret > len) +++ return -E2BIG; +++ return 0; +++} +++ +++static int enfs_proc_create_file(struct rpc_clnt *clnt) +++{ +++ int err; +++ char buf[128]; +++ +++ struct proc_dir_entry *clnt_entry; +++ struct proc_dir_entry *stat_entry; +++ +++ err = clnt_proc_name(clnt, buf, sizeof(buf)); +++ if (err) +++ return err; +++ +++ clnt_entry = proc_mkdir(buf, enfs_proc_parent); +++ if (clnt_entry == NULL) +++ return -EINVAL; +++ +++ stat_entry = proc_create_data("stat", +++ 0, clnt_entry, +++ &rpc_proc_fops, clnt); +++ +++ if (stat_entry == NULL) +++ return -EINVAL; +++ +++ stat_entry = proc_create_data("path", +++ 0, clnt_entry, +++ &rpc_show_path_fops, clnt); +++ +++ if (stat_entry == NULL) +++ return -EINVAL; +++ +++ return 0; +++} +++ +++void enfs_count_iostat(struct rpc_task *task) +++{ +++ struct enfs_xprt_context *ctx = task->tk_xprt->multipath_context; +++ +++ if (!ctx || !ctx->stats) +++ return; +++ rpc_count_iostats(task, ctx->stats); +++} +++ +++static void enfs_proc_delete_file(struct rpc_clnt *clnt) +++{ +++ int err; +++ char buf[128]; +++ +++ err = clnt_proc_name(clnt, buf, sizeof(buf)); +++ if (err) { +++ pr_err("gen clnt name failed.\n"); +++ return; +++ } +++ remove_proc_subtree(buf, enfs_proc_parent); +++} +++ +++// create proc file "/porc/enfs/[mount_ip]_[id]/stat" +++int enfs_proc_create_clnt(struct rpc_clnt *clnt) +++{ +++ int err; +++ +++ err = enfs_proc_create_file(clnt); +++ if (err) { +++ pr_err("create client %d\n", err); +++ return err; +++ } +++ +++ return 0; +++} +++ +++void enfs_proc_delete_clnt(struct rpc_clnt *clnt) +++{ +++ if (clnt->cl_enfs) +++ enfs_proc_delete_file(clnt); +++} +++ +++static int enfs_proc_create_parent(void) +++{ +++ enfs_proc_parent = proc_mkdir(ENFS_PROC_DIR, NULL); +++ +++ if (enfs_proc_parent == NULL) { +++ pr_err("Enfs create proc dir err\n"); +++ return -ENOMEM; +++ } +++ return 0; +++} +++ +++static void enfs_proc_delete_parent(void) +++{ +++ remove_proc_entry(ENFS_PROC_DIR, NULL); +++} +++ +++static int enfs_proc_init_create_clnt(struct rpc_clnt *clnt, void *data) +++{ +++ if (clnt->cl_enfs) +++ enfs_proc_create_file(clnt); +++ return 0; +++} +++ +++static int enfs_proc_destroy_clnt(struct rpc_clnt *clnt, void *data) +++{ +++ if (clnt->cl_enfs) +++ enfs_proc_delete_file(clnt); +++ return 0; +++} +++ +++int enfs_proc_init(void) +++{ +++ int err; +++ +++ err = enfs_proc_create_parent(); +++ if (err) +++ return err; +++ +++ enfs_iterate_each_rpc_clnt(enfs_proc_init_create_clnt, NULL); +++ return 0; +++} +++ +++void enfs_proc_exit(void) +++{ +++ enfs_iterate_each_rpc_clnt(enfs_proc_destroy_clnt, NULL); +++ enfs_proc_delete_parent(); +++} ++diff --git a/fs/nfs/enfs/enfs_proc.h b/fs/nfs/enfs/enfs_proc.h ++new file mode 100644 ++index 000000000000..321951031c2e ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_proc.h ++@@ -0,0 +1,21 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Client-side ENFS PROC. +++ * +++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. +++ */ +++#ifndef ENFS_PROC_H +++#define ENFS_PROC_H +++ +++struct rpc_clnt; +++struct rpc_task; +++struct proc_dir_entry; +++ +++int enfs_proc_init(void); +++void enfs_proc_exit(void); +++struct proc_dir_entry *enfs_get_proc_parent(void); +++int enfs_proc_create_clnt(struct rpc_clnt *clnt); +++void enfs_proc_delete_clnt(struct rpc_clnt *clnt); +++void enfs_count_iostat(struct rpc_task *task); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_remount.c b/fs/nfs/enfs/enfs_remount.c ++new file mode 100644 ++index 000000000000..2c3fe125c735 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_remount.c ++@@ -0,0 +1,221 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: remount ip source file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++#include "enfs_remount.h" +++ +++#include <linux/string.h> +++#include <linux/in.h> +++#include <linux/in6.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/spinlock.h> +++#include <linux/sunrpc/addr.h> +++#include <linux/sunrpc/metrics.h> +++#include <linux/sunrpc/xprtmultipath.h> +++#include <linux/sunrpc/xprtsock.h> +++#include <linux/sunrpc/xprt.h> +++#include <linux/smp.h> +++#include <linux/delay.h> +++ +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_multipath.h" +++#include "enfs_multipath_parse.h" +++#include "enfs_path.h" +++#include "enfs_proc.h" +++#include "enfs_multipath_client.h" +++ +++static bool enfs_rpc_xprt_switch_need_delete_addr( +++ struct multipath_mount_options *enfs_option, +++ struct sockaddr *dstaddr, struct sockaddr *srcaddr) +++{ +++ int i; +++ bool find_same_ip = false; +++ int32_t local_total; +++ int32_t remote_total; +++ +++ local_total = enfs_option->local_ip_list->count; +++ remote_total = enfs_option->remote_ip_list->count; +++ if (local_total == 0 || remote_total == 0) { +++ pr_err("no ip list is present.\n"); +++ return false; +++ } +++ +++ for (i = 0; i < local_total; i++) { +++ find_same_ip = +++ rpc_cmp_addr((struct sockaddr *) +++ &enfs_option->local_ip_list->address[i], +++ srcaddr); +++ if (find_same_ip) +++ break; +++ } +++ +++ if (find_same_ip == false) +++ return true; +++ +++ find_same_ip = false; +++ for (i = 0; i < remote_total; i++) { +++ find_same_ip = +++ rpc_cmp_addr((struct sockaddr *) +++ &enfs_option->remote_ip_list->address[i], +++ dstaddr); +++ if (find_same_ip) +++ break; +++ } +++ +++ if (find_same_ip == false) +++ return true; +++ +++ return false; +++} +++ +++// Used in rcu_lock +++static bool enfs_delete_xprt_from_switch(struct rpc_xprt *xprt, +++ void *enfs_option, +++ struct rpc_xprt_switch *xps) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ struct multipath_mount_options *mopt = +++ (struct multipath_mount_options *)enfs_option; +++ +++ if (enfs_is_main_xprt(xprt)) +++ return true; +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (enfs_rpc_xprt_switch_need_delete_addr(mopt, +++ (struct sockaddr *)&xprt->addr, +++ (struct sockaddr *)&ctx->srcaddr)) { +++ +++ print_enfs_multipath_addr((struct sockaddr *)&ctx->srcaddr, +++ (struct sockaddr *)&xprt->addr); +++ rpc_xprt_switch_remove_xprt(xps, xprt); +++ return true; +++ } +++ +++ return false; +++} +++ +++void enfs_clnt_delete_obsolete_xprts(struct nfs_client *nfs_client, +++ void *enfs_option) +++{ +++ int xprt_count = 0; +++ struct rpc_xprt *pos = NULL; +++ struct rpc_xprt_switch *xps = NULL; +++ +++ rcu_read_lock(); +++ xps = xprt_switch_get( +++ rcu_dereference( +++ nfs_client->cl_rpcclient->cl_xpi.xpi_xpswitch)); +++ if (xps == NULL) { +++ rcu_read_unlock(); +++ xprt_switch_put(xps); +++ return; +++ } +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (xprt_count < MAX_XPRT_NUM_PER_CLIENT) { +++ if (enfs_delete_xprt_from_switch( +++ pos, enfs_option, xps) == false) +++ xprt_count++; +++ } else +++ rpc_xprt_switch_remove_xprt(xps, pos); +++ } +++ rcu_read_unlock(); +++ xprt_switch_put(xps); +++} +++ +++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) +++{ +++ int errno = 0; +++ char servername[48]; +++ struct multipath_mount_options *remount_lists = +++ (struct multipath_mount_options *)enfs_option; +++ struct multipath_client_info *client_info = +++ (struct multipath_client_info *)nfs_client->cl_multipath_data; +++ struct xprt_create xprtargs; +++ struct rpc_create_args args = { +++ .protocol = nfs_client->cl_proto, +++ .net = nfs_client->cl_net, +++ .addrsize = nfs_client->cl_addrlen, +++ .servername = nfs_client->cl_hostname, +++ }; +++ +++ memset(&xprtargs, 0, sizeof(struct xprt_create)); +++ +++ //mount is not use multipath +++ if (client_info == NULL || enfs_option == NULL) { +++ enfs_log_error( +++ "mount information or remount information is empty.\n"); +++ return -EINVAL; +++ } +++ +++ //remount : localaddrs and remoteaddrs are empty +++ if (remount_lists->local_ip_list->count == 0 && +++ remount_lists->remote_ip_list->count == 0) { +++ enfs_log_info("remount local_ip_list and remote_ip_list are NULL\n"); +++ return 0; +++ } +++ +++ errno = enfs_config_xprt_create_args(&xprtargs, +++ &args, servername, sizeof(servername)); +++ +++ if (errno) { +++ enfs_log_error("config_xprt_create failed! errno:%d\n", errno); +++ return errno; +++ } +++ +++ if (remount_lists->local_ip_list->count == 0) { +++ if (client_info->local_ip_list->count == 0) { +++ errno = rpc_localaddr(nfs_client->cl_rpcclient, +++ (struct sockaddr *) +++ &remount_lists->local_ip_list->address[0], +++ sizeof(struct sockaddr_storage)); +++ if (errno) { +++ enfs_log_error("get clnt srcaddr errno:%d\n", +++ errno); +++ return errno; +++ } +++ remount_lists->local_ip_list->count = 1; +++ } else +++ memcpy(remount_lists->local_ip_list, +++ client_info->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ if (remount_lists->remote_ip_list->count == 0) { +++ if (client_info->remote_ip_list->count == 0) { +++ errno = rpc_peeraddr(nfs_client->cl_rpcclient, +++ (struct sockaddr *) +++ &remount_lists->remote_ip_list->address[0], +++ sizeof(struct sockaddr_storage)); +++ if (errno == 0) { +++ enfs_log_error("get clnt dstaddr errno:%d\n", +++ errno); +++ return errno; +++ } +++ remount_lists->remote_ip_list->count = 1; +++ } else +++ memcpy(remount_lists->remote_ip_list, +++ client_info->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ } +++ +++ enfs_log_info("Remount creating new links...\n"); +++ enfs_xprt_ippair_create(&xprtargs, +++ nfs_client->cl_rpcclient, +++ remount_lists); +++ +++ enfs_log_info("Remount deleting obsolete links...\n"); +++ enfs_clnt_delete_obsolete_xprts(nfs_client, remount_lists); +++ +++ memcpy(client_info->local_ip_list, +++ remount_lists->local_ip_list, +++ sizeof(struct nfs_ip_list)); +++ memcpy(client_info->remote_ip_list, +++ remount_lists->remote_ip_list, +++ sizeof(struct nfs_ip_list)); +++ +++ return 0; +++} ++diff --git a/fs/nfs/enfs/enfs_remount.h b/fs/nfs/enfs/enfs_remount.h ++new file mode 100644 ++index 000000000000..a663ed257004 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_remount.h ++@@ -0,0 +1,15 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: remount ip header file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++#ifndef _ENFS_REMOUNT_ +++#define _ENFS_REMOUNT_ +++#include <linux/string.h> +++#include "enfs.h" +++ +++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); +++ +++#endif ++diff --git a/fs/nfs/enfs/enfs_roundrobin.c b/fs/nfs/enfs/enfs_roundrobin.c ++new file mode 100644 ++index 000000000000..4e4eda784a3e ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_roundrobin.c ++@@ -0,0 +1,255 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#include <linux/spinlock.h> +++#include <linux/module.h> +++#include <linux/printk.h> +++#include <linux/kref.h> +++#include <linux/rculist.h> +++#include <linux/types.h> +++#include <linux/sunrpc/xprt.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/xprtmultipath.h> +++#include "enfs_roundrobin.h" +++ +++#include "enfs.h" +++#include "enfs_config.h" +++#include "pm_state.h" +++ +++typedef struct rpc_xprt *(*enfs_xprt_switch_find_xprt_t)( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur); +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin; +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular; +++ +++static bool enfs_xprt_is_active(struct rpc_xprt *xprt) +++{ +++ enum pm_path_state state; +++ +++ if (kref_read(&xprt->kref) <= 0) +++ return false; +++ +++ state = pm_get_path_state(xprt); +++ if (state == PM_STATE_NORMAL) +++ return true; +++ +++ return false; +++} +++ +++static struct rpc_xprt *enfs_lb_set_cursor_xprt( +++ struct rpc_xprt_switch *xps, struct rpc_xprt **cursor, +++ enfs_xprt_switch_find_xprt_t find_next) +++{ +++ struct rpc_xprt *pos; +++ struct rpc_xprt *old; +++ +++ old = smp_load_acquire(cursor); /* read latest cursor */ +++ pos = find_next(xps, old); +++ smp_store_release(cursor, pos); /* let cursor point to pos */ +++ return pos; +++} +++ +++static +++struct rpc_xprt *enfs_lb_find_next_entry_roundrobin( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *pos; +++ struct rpc_xprt *prev = NULL; +++ bool found = false; +++ struct rpc_xprt *min_queuelen_xprt = NULL; +++ unsigned long pos_xprt_queuelen; +++ unsigned long min_xprt_queuelen = 0; +++ +++ unsigned long xps_queuelen = atomic_long_read(&xps->xps_queuelen); +++ // delete origin xprt +++ unsigned int multipath_nactive = READ_ONCE(xps->xps_nactive) - 1; +++ +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (enfs_is_main_xprt(pos) || !enfs_xprt_is_active(pos)) { +++ prev = pos; +++ continue; +++ } +++ +++ pos_xprt_queuelen = atomic_long_read(&pos->queuelen); +++ if (min_queuelen_xprt == NULL || +++ pos_xprt_queuelen < min_xprt_queuelen) { +++ +++ min_queuelen_xprt = pos; +++ min_xprt_queuelen = pos_xprt_queuelen; +++ } +++ +++ if (cur == prev) +++ found = true; +++ +++ if (found && pos_xprt_queuelen * +++ multipath_nactive <= xps_queuelen) +++ return pos; +++ prev = pos; +++ }; +++ +++ return min_queuelen_xprt; +++} +++ +++struct rpc_xprt *enfs_lb_switch_find_first_active_xprt( +++ struct rpc_xprt_switch *xps) +++{ +++ struct rpc_xprt *pos; +++ +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (enfs_xprt_is_active(pos)) +++ return pos; +++ }; +++ return NULL; +++} +++ +++struct rpc_xprt *enfs_lb_switch_get_main_xprt(struct rpc_xprt_switch *xps) +++{ +++ return list_first_or_null_rcu(&xps->xps_xprt_list, +++ struct rpc_xprt, xprt_switch); +++} +++ +++static struct rpc_xprt *enfs_lb_switch_get_next_xprt_roundrobin( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *xprt; +++ +++ // disable multipath +++ if (enfs_get_config_multipath_state()) +++ return enfs_lb_switch_get_main_xprt(xps); +++ +++ xprt = enfs_lb_find_next_entry_roundrobin(xps, cur); +++ if (xprt != NULL) +++ return xprt; +++ +++ return enfs_lb_switch_get_main_xprt(xps); +++} +++ +++static +++struct rpc_xprt *enfs_lb_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi) +++{ +++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); +++ +++ if (xps == NULL) +++ return NULL; +++ +++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, +++ enfs_lb_switch_get_next_xprt_roundrobin); +++} +++ +++static +++struct rpc_xprt *enfs_lb_switch_find_singular_entry( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *pos; +++ bool found = false; +++ +++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { +++ if (cur == pos) +++ found = true; +++ +++ if (found && enfs_xprt_is_active(pos)) +++ return pos; +++ } +++ return NULL; +++} +++ +++struct rpc_xprt *enfs_lb_get_singular_xprt( +++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *xprt; +++ +++ if (xps == NULL) +++ return NULL; +++ +++ // disable multipath +++ if (enfs_get_config_multipath_state()) +++ return enfs_lb_switch_get_main_xprt(xps); +++ +++ if (cur == NULL || xps->xps_nxprts < 2) +++ return enfs_lb_switch_find_first_active_xprt(xps); +++ +++ xprt = enfs_lb_switch_find_singular_entry(xps, cur); +++ if (!xprt) +++ return enfs_lb_switch_get_main_xprt(xps); +++ +++ return xprt; +++} +++ +++static +++struct rpc_xprt *enfs_lb_iter_next_entry_sigular(struct rpc_xprt_iter *xpi) +++{ +++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); +++ +++ if (xps == NULL) +++ return NULL; +++ +++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, +++ enfs_lb_get_singular_xprt); +++} +++ +++static void enfs_lb_iter_default_rewind(struct rpc_xprt_iter *xpi) +++{ +++ WRITE_ONCE(xpi->xpi_cursor, NULL); +++} +++ +++static void enfs_lb_switch_set_roundrobin(struct rpc_clnt *clnt) +++{ +++ struct rpc_xprt_switch *xps; +++ +++ rcu_read_lock(); +++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); +++ rcu_read_unlock(); +++ if (clnt->cl_vers == 3) { +++ +++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_roundrobin) +++ WRITE_ONCE(xps->xps_iter_ops, +++ &enfs_xprt_iter_roundrobin); +++ +++ return; +++ } +++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_singular) +++ WRITE_ONCE(xps->xps_iter_ops, &enfs_xprt_iter_singular); +++} +++ +++static +++struct rpc_xprt *enfs_lb_switch_find_current(struct list_head *head, +++ const struct rpc_xprt *cur) +++{ +++ struct rpc_xprt *pos; +++ +++ list_for_each_entry_rcu(pos, head, xprt_switch) { +++ if (cur == pos) +++ return pos; +++ } +++ return NULL; +++} +++ +++static struct rpc_xprt *enfs_lb_iter_current_entry(struct rpc_xprt_iter *xpi) +++{ +++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); +++ struct list_head *head; +++ +++ if (xps == NULL) +++ return NULL; +++ head = &xps->xps_xprt_list; +++ if (xpi->xpi_cursor == NULL || xps->xps_nxprts < 2) +++ return enfs_lb_switch_get_main_xprt(xps); +++ return enfs_lb_switch_find_current(head, xpi->xpi_cursor); +++} +++ +++void enfs_lb_set_policy(struct rpc_clnt *clnt) +++{ +++ enfs_lb_switch_set_roundrobin(clnt); +++} +++ +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin = { +++ .xpi_rewind = enfs_lb_iter_default_rewind, +++ .xpi_xprt = enfs_lb_iter_current_entry, +++ .xpi_next = enfs_lb_iter_next_entry_roundrobin, +++}; +++ +++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular = { +++ .xpi_rewind = enfs_lb_iter_default_rewind, +++ .xpi_xprt = enfs_lb_iter_current_entry, +++ .xpi_next = enfs_lb_iter_next_entry_sigular, +++}; ++diff --git a/fs/nfs/enfs/enfs_roundrobin.h b/fs/nfs/enfs/enfs_roundrobin.h ++new file mode 100644 ++index 000000000000..b72b088a6258 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_roundrobin.h ++@@ -0,0 +1,9 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#ifndef ENFS_ROUNDROBIN_H +++#define ENFS_ROUNDROBIN_H +++ +++void enfs_lb_set_policy(struct rpc_clnt *clnt); +++#endif +diff --git a/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch +new file mode 100644 +index 0000000..cc6b677 +--- /dev/null ++++ b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch +@@ -0,0 +1,1607 @@ ++diff --git a/fs/nfs/enfs/enfs_config.c b/fs/nfs/enfs/enfs_config.c ++new file mode 100644 ++index 000000000000..11aa7a00385b ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_config.c ++@@ -0,0 +1,378 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ */ +++#include <linux/cdev.h> +++#include <linux/errno.h> +++#include <linux/fcntl.h> +++#include <linux/fs.h> +++#include <linux/kernel.h> +++#include <linux/kthread.h> +++#include <linux/slab.h> +++#include <linux/string.h> +++#include <linux/uaccess.h> +++#include <linux/delay.h> +++ +++#include "enfs_errcode.h" +++#include "enfs_log.h" +++#include "enfs_config.h" +++ +++#define MAX_FILE_SIZE 8192 +++#define STRING_BUF_SIZE 128 +++#define CONFIG_FILE_PATH "/etc/enfs/config.ini" +++#define ENFS_NOTIFY_FILE_PERIOD 1000UL +++ +++#define MAX_PATH_DETECT_INTERVAL 300 +++#define MIN_PATH_DETECT_INTERVAL 5 +++#define MAX_PATH_DETECT_TIMEOUT 60 +++#define MIN_PATH_DETECT_TIMEOUT 1 +++#define MAX_MULTIPATH_TIMEOUT 60 +++#define MIN_MULTIPATH_TIMEOUT 0 +++#define MAX_MULTIPATH_STATE ENFS_MULTIPATH_DISABLE +++#define MIN_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE +++ +++#define DEFAULT_PATH_DETECT_INTERVAL 10 +++#define DEFAULT_PATH_DETECT_TIMEOUT 5 +++#define DEFAULT_MULTIPATH_TIMEOUT 0 +++#define DEFAULT_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE +++#define DEFAULT_LOADBALANCE_MODE ENFS_LOADBALANCE_RR +++ +++typedef int (*check_and_assign_func)(char *, char *, int, int); +++ +++struct enfs_config_info { +++ int32_t path_detect_interval; +++ int32_t path_detect_timeout; +++ int32_t multipath_timeout; +++ int32_t loadbalance_mode; +++ int32_t multipath_state; +++}; +++ +++struct check_and_assign_value { +++ char *field_name; +++ check_and_assign_func func; +++ int min_value; +++ int max_value; +++}; +++ +++static struct enfs_config_info g_enfs_config_info; +++static struct timespec64 modify_time; +++static struct task_struct *thread; +++ +++static int enfs_check_config_value(char *value, int min_value, int max_value) +++{ +++ unsigned long num_value; +++ int ret; +++ +++ ret = kstrtol(value, 10, &num_value); +++ if (ret != 0) { +++ enfs_log_error("Failed to convert string to int\n"); +++ return -EINVAL; +++ } +++ +++ if (num_value < min_value || num_value > max_value) +++ return -EINVAL; +++ +++ return num_value; +++} +++ +++static int32_t enfs_check_and_assign_int_value(char *field_name, char *value, +++ int min_value, int max_value) +++{ +++ int int_value = enfs_check_config_value(value, min_value, max_value); +++ +++ if (int_value < 0) +++ return -EINVAL; +++ +++ if (strcmp(field_name, "path_detect_interval") == 0) { +++ g_enfs_config_info.path_detect_interval = int_value; +++ return ENFS_RET_OK; +++ } +++ if (strcmp(field_name, "path_detect_timeout") == 0) { +++ g_enfs_config_info.path_detect_timeout = int_value; +++ return ENFS_RET_OK; +++ } +++ if (strcmp(field_name, "multipath_timeout") == 0) { +++ g_enfs_config_info.multipath_timeout = int_value; +++ return ENFS_RET_OK; +++ } +++ if (strcmp(field_name, "multipath_disable") == 0) { +++ g_enfs_config_info.multipath_state = int_value; +++ return ENFS_RET_OK; +++ } +++ return -EINVAL; +++} +++ +++static int32_t enfs_check_and_assign_loadbalance_mode(char *field_name, +++ char *value, +++ int min_value, +++ int max_value) +++{ +++ if (value == NULL) +++ return -EINVAL; +++ +++ if (strcmp(field_name, "multipath_select_policy") == 0) { +++ if (strcmp(value, "roundrobin") == 0) { +++ g_enfs_config_info.loadbalance_mode +++ = ENFS_LOADBALANCE_RR; +++ return ENFS_RET_OK; +++ } +++ } +++ return -EINVAL; +++} +++ +++static const struct check_and_assign_value g_check_and_assign_value[] = { +++ {"path_detect_interval", enfs_check_and_assign_int_value, +++ MIN_PATH_DETECT_INTERVAL, MAX_PATH_DETECT_INTERVAL}, +++ {"path_detect_timeout", enfs_check_and_assign_int_value, +++ MIN_PATH_DETECT_TIMEOUT, MAX_PATH_DETECT_TIMEOUT}, +++ {"multipath_timeout", enfs_check_and_assign_int_value, +++ MIN_MULTIPATH_TIMEOUT, MAX_MULTIPATH_TIMEOUT}, +++ {"multipath_disable", enfs_check_and_assign_int_value, +++ MIN_MULTIPATH_STATE, MAX_MULTIPATH_STATE}, +++ {"multipath_select_policy", enfs_check_and_assign_loadbalance_mode, +++ 0, 0}, +++}; +++ +++static int32_t enfs_read_config_file(char *buffer, char *file_path) +++{ +++ int ret; +++ struct file *filp = NULL; +++ loff_t f_pos = 0; +++ mm_segment_t fs; +++ +++ +++ filp = filp_open(file_path, O_RDONLY, 0); +++ +++ if (IS_ERR(filp)) { +++ enfs_log_error("Failed to open file %s\n", CONFIG_FILE_PATH); +++ ret = -ENOENT; +++ return ret; +++ } +++ +++ fs = get_fs(); +++ set_fs(get_ds()); +++ kernel_read(filp, buffer, MAX_FILE_SIZE, &f_pos); +++ set_fs(fs); +++ +++ ret = filp_close(filp, NULL); +++ if (ret) { +++ enfs_log_error("Close File:%s failed:%d.\n", +++ CONFIG_FILE_PATH, ret); +++ return -EINVAL; +++ } +++ return ENFS_RET_OK; +++} +++ +++static int32_t enfs_deal_with_comment_line(char *buffer) +++{ +++ int ret; +++ char *pos = strchr(buffer, '\n'); +++ +++ if (pos != NULL) +++ ret = strlen(buffer) - strlen(pos); +++ else +++ ret = strlen(buffer); +++ +++ return ret; +++} +++ +++static int32_t enfs_parse_key_value_from_config(char *buffer, char *key, +++ char *value, int keyLen, +++ int valueLen) +++{ +++ char *line; +++ char *tokenPtr; +++ int len; +++ char *tem; +++ char *pos = strchr(buffer, '\n'); +++ +++ if (pos != NULL) +++ len = strlen(buffer) - strlen(pos); +++ else +++ len = strlen(buffer); +++ +++ line = kmalloc(len + 1, GFP_KERNEL); +++ if (!line) { +++ enfs_log_error("Failed to allocate memory.\n"); +++ return -ENOMEM; +++ } +++ line[len] = '\0'; +++ strncpy(line, buffer, len); +++ +++ tem = line; +++ tokenPtr = strsep(&tem, "="); +++ if (tokenPtr == NULL || tem == NULL) { +++ kfree(line); +++ return len; +++ } +++ strncpy(key, strim(tokenPtr), keyLen); +++ strncpy(value, strim(tem), valueLen); +++ +++ kfree(line); +++ return len; +++} +++ +++static int32_t enfs_get_value_from_config_file(char *buffer, char *field_name, +++ char *value, int valueLen) +++{ +++ int ret; +++ char key[STRING_BUF_SIZE + 1] = {0}; +++ char val[STRING_BUF_SIZE + 1] = {0}; +++ +++ while (buffer[0] != '\0') { +++ if (buffer[0] == '\n') { +++ buffer++; +++ } else if (buffer[0] == '#') { +++ ret = enfs_deal_with_comment_line(buffer); +++ if (ret > 0) +++ buffer += ret; +++ } else { +++ ret = enfs_parse_key_value_from_config(buffer, key, val, +++ STRING_BUF_SIZE, +++ STRING_BUF_SIZE); +++ if (ret < 0) { +++ enfs_log_error("failed parse key value, %d\n" +++ , ret); +++ return ret; +++ } +++ key[STRING_BUF_SIZE] = '\0'; +++ val[STRING_BUF_SIZE] = '\0'; +++ +++ buffer += ret; +++ +++ if (strcmp(field_name, key) == 0) { +++ strncpy(value, val, valueLen); +++ return ENFS_RET_OK; +++ } +++ } +++ } +++ enfs_log_error("can not find value which matched field_name: %s.\n", +++ field_name); +++ return -EINVAL; +++} +++ +++int32_t enfs_config_load(void) +++{ +++ char value[STRING_BUF_SIZE + 1]; +++ int ret; +++ int table_len; +++ int min; +++ int max; +++ int i; +++ char *buffer; +++ +++ buffer = kmalloc(MAX_FILE_SIZE, GFP_KERNEL); +++ if (!buffer) { +++ enfs_log_error("Failed to allocate memory.\n"); +++ return -ENOMEM; +++ } +++ memset(buffer, 0, MAX_FILE_SIZE); +++ +++ g_enfs_config_info.path_detect_interval = DEFAULT_PATH_DETECT_INTERVAL; +++ g_enfs_config_info.path_detect_timeout = DEFAULT_PATH_DETECT_TIMEOUT; +++ g_enfs_config_info.multipath_timeout = DEFAULT_MULTIPATH_TIMEOUT; +++ g_enfs_config_info.multipath_state = DEFAULT_MULTIPATH_STATE; +++ g_enfs_config_info.loadbalance_mode = DEFAULT_LOADBALANCE_MODE; +++ +++ table_len = sizeof(g_check_and_assign_value) / +++ sizeof(g_check_and_assign_value[0]); +++ +++ ret = enfs_read_config_file(buffer, CONFIG_FILE_PATH); +++ if (ret != 0) { +++ kfree(buffer); +++ return ret; +++ } +++ +++ for (i = 0; i < table_len; i++) { +++ ret = enfs_get_value_from_config_file(buffer, +++ g_check_and_assign_value[i].field_name, +++ value, STRING_BUF_SIZE); +++ if (ret < 0) +++ continue; +++ +++ value[STRING_BUF_SIZE] = '\0'; +++ min = g_check_and_assign_value[i].min_value; +++ max = g_check_and_assign_value[i].max_value; +++ if (g_check_and_assign_value[i].func != NULL) +++ (*g_check_and_assign_value[i].func)( +++ g_check_and_assign_value[i].field_name, +++ value, min, max); +++ } +++ +++ kfree(buffer); +++ return ENFS_RET_OK; +++} +++ +++int32_t enfs_get_config_path_detect_interval(void) +++{ +++ return g_enfs_config_info.path_detect_interval; +++} +++ +++int32_t enfs_get_config_path_detect_timeout(void) +++{ +++ return g_enfs_config_info.path_detect_timeout; +++} +++ +++int32_t enfs_get_config_multipath_timeout(void) +++{ +++ return g_enfs_config_info.multipath_timeout; +++} +++ +++int32_t enfs_get_config_multipath_state(void) +++{ +++ return g_enfs_config_info.multipath_state; +++} +++ +++int32_t enfs_get_config_loadbalance_mode(void) +++{ +++ return g_enfs_config_info.loadbalance_mode; +++} +++ +++static bool enfs_file_changed(const char *filename) +++{ +++ int err; +++ struct kstat file_stat; +++ +++ err = vfs_stat(filename, &file_stat); +++ if (err) { +++ pr_err("failed to open file:%s err:%d\n", filename, err); +++ return false; +++ } +++ +++ if (timespec64_compare(&modify_time, &file_stat.mtime) == -1) { +++ modify_time = file_stat.mtime; +++ pr_info("file change: %lld %lld\n", modify_time.tv_sec, +++ file_stat.mtime.tv_sec); +++ return true; +++ } +++ +++ return false; +++} +++ +++static int enfs_thread_func(void *data) +++{ +++ while (!kthread_should_stop()) { +++ if (enfs_file_changed(CONFIG_FILE_PATH)) +++ enfs_config_load(); +++ +++ msleep(ENFS_NOTIFY_FILE_PERIOD); +++ } +++ return 0; +++} +++ +++int enfs_config_timer_init(void) +++{ +++ thread = kthread_run(enfs_thread_func, NULL, "enfs_notiy_file_thread"); +++ if (IS_ERR(thread)) { +++ pr_err("Failed to create kernel thread\n"); +++ return PTR_ERR(thread); +++ } +++ return 0; +++} +++ +++void enfs_config_timer_exit(void) +++{ +++ pr_info("enfs_notify_file_exit\n"); +++ if (thread) +++ kthread_stop(thread); +++} ++diff --git a/fs/nfs/enfs/enfs_config.h b/fs/nfs/enfs/enfs_config.h ++new file mode 100644 ++index 000000000000..752710129170 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_config.h ++@@ -0,0 +1,32 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs configuration +++ * Author: y00583252 +++ * Create: 2023-07-27 +++ */ +++ +++#ifndef ENFS_CONFIG_H +++#define ENFS_CONFIG_H +++ +++#include <linux/types.h> +++ +++enum enfs_multipath_state { +++ ENFS_MULTIPATH_ENABLE = 0, +++ ENFS_MULTIPATH_DISABLE = 1, +++}; +++ +++enum enfs_loadbalance_mode { +++ ENFS_LOADBALANCE_RR, +++}; +++ +++ +++int32_t enfs_get_config_path_detect_interval(void); +++int32_t enfs_get_config_path_detect_timeout(void); +++int32_t enfs_get_config_multipath_timeout(void); +++int32_t enfs_get_config_multipath_state(void); +++int32_t enfs_get_config_loadbalance_mode(void); +++int32_t enfs_config_load(void); +++int32_t enfs_config_timer_init(void); +++void enfs_config_timer_exit(void); +++#endif // ENFS_CONFIG_H ++diff --git a/fs/nfs/enfs/enfs_errcode.h b/fs/nfs/enfs/enfs_errcode.h ++new file mode 100644 ++index 000000000000..cca47ab9a191 ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_errcode.h ++@@ -0,0 +1,17 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs errocode +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef ENFS_ERRCODE_H +++#define ENFS_ERRCODE_H +++ +++enum { +++ ENFS_RET_OK = 0, +++ ENFS_RET_FAIL +++}; +++ +++#endif // ENFS_ERRCODE_H ++diff --git a/fs/nfs/enfs/enfs_log.h b/fs/nfs/enfs/enfs_log.h ++new file mode 100644 ++index 000000000000..177b404f05df ++--- /dev/null +++++ b/fs/nfs/enfs/enfs_log.h ++@@ -0,0 +1,25 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: enfs log +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++#ifndef ENFS_LOG_H +++#define ENFS_LOG_H +++ +++#include <linux/printk.h> +++ +++#define enfs_log_info(fmt, ...) \ +++ pr_info("enfs:[%s]" pr_fmt(fmt), \ +++ __func__, ##__VA_ARGS__) +++ +++#define enfs_log_error(fmt, ...) \ +++ pr_err("enfs:[%s]" pr_fmt(fmt), \ +++ __func__, ##__VA_ARGS__) +++ +++#define enfs_log_debug(fmt, ...) \ +++ pr_debug("enfs:[%s]" pr_fmt(fmt), \ +++ __func__, ##__VA_ARGS__) +++ +++#endif // ENFS_ERRCODE_H ++diff --git a/fs/nfs/enfs/failover_com.h b/fs/nfs/enfs/failover_com.h ++new file mode 100644 ++index 000000000000..c52940da232e ++--- /dev/null +++++ b/fs/nfs/enfs/failover_com.h ++@@ -0,0 +1,23 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: failover time commont header file +++ * Create: 2023-08-02 +++ */ +++#ifndef FAILOVER_COMMON_H +++#define FAILOVER_COMMON_H +++ +++static inline bool failover_is_enfs_clnt(struct rpc_clnt *clnt) +++{ +++ struct rpc_clnt *next = clnt->cl_parent; +++ +++ while (next) { +++ if (next == next->cl_parent) +++ break; +++ next = next->cl_parent; +++ } +++ +++ return next != NULL ? next->cl_enfs : clnt->cl_enfs; +++} +++ +++#endif // FAILOVER_COMMON_H ++diff --git a/fs/nfs/enfs/failover_path.c b/fs/nfs/enfs/failover_path.c ++new file mode 100644 ++index 000000000000..93b454de29d1 ++--- /dev/null +++++ b/fs/nfs/enfs/failover_path.c ++@@ -0,0 +1,207 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs path failover file +++ * Author: y00583252 +++ * Create: 2023-08-02 +++ */ +++ +++#include "failover_path.h" +++#include <linux/nfs.h> +++#include <linux/nfs3.h> +++#include <linux/nfs4.h> +++#include <linux/sunrpc/clnt.h> +++#include <linux/sunrpc/sched.h> +++#include <linux/sunrpc/xprt.h> +++#include "enfs_config.h" +++#include "enfs_log.h" +++#include "failover_com.h" +++#include "pm_state.h" +++#include "pm_ping.h" +++ +++enum failover_policy_t { +++ FAILOVER_NOACTION = 1, +++ FAILOVER_RETRY, +++ FAILOVER_RETRY_DELAY, +++}; +++ +++static void failover_retry_path(struct rpc_task *task) +++{ +++ xprt_release(task); +++ rpc_init_task_retry_counters(task); +++ rpc_task_release_transport(task); +++ rpc_restart_call(task); +++} +++ +++static void failover_retry_path_delay(struct rpc_task *task, int32_t delay) +++{ +++ failover_retry_path(task); +++ rpc_delay(task, delay); +++} +++ +++static void failover_retry_path_by_policy(struct rpc_task *task, +++ enum failover_policy_t policy) +++{ +++ if (policy == FAILOVER_RETRY) +++ failover_retry_path(task); +++ else if (policy == FAILOVER_RETRY_DELAY) +++ failover_retry_path_delay(task, 3 * HZ); // delay 3s +++} +++ +++static +++enum failover_policy_t failover_get_nfs3_retry_policy(struct rpc_task *task) +++{ +++ enum failover_policy_t policy = FAILOVER_NOACTION; +++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; +++ u32 proc; +++ +++ if (unlikely(procinfo == NULL)) { +++ enfs_log_error("the task contains no valid proc.\n"); +++ return FAILOVER_NOACTION; +++ } +++ +++ proc = procinfo->p_proc; +++ +++ switch (proc) { +++ case NFS3PROC_CREATE: +++ case NFS3PROC_MKDIR: +++ case NFS3PROC_REMOVE: +++ case NFS3PROC_RMDIR: +++ case NFS3PROC_SYMLINK: +++ case NFS3PROC_LINK: +++ case NFS3PROC_SETATTR: +++ case NFS3PROC_WRITE: +++ policy = FAILOVER_RETRY_DELAY; +++ default: +++ policy = FAILOVER_RETRY; +++ } +++ return policy; +++} +++ +++static +++enum failover_policy_t failover_get_nfs4_retry_policy(struct rpc_task *task) +++{ +++ enum failover_policy_t policy = FAILOVER_NOACTION; +++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; +++ u32 proc_idx; +++ +++ if (unlikely(procinfo == NULL)) { +++ enfs_log_error("the task contains no valid proc.\n"); +++ return FAILOVER_NOACTION; +++ } +++ +++ proc_idx = procinfo->p_statidx; +++ +++ switch (proc_idx) { +++ case NFSPROC4_CLNT_CREATE: +++ case NFSPROC4_CLNT_REMOVE: +++ case NFSPROC4_CLNT_LINK: +++ case NFSPROC4_CLNT_SYMLINK: +++ case NFSPROC4_CLNT_SETATTR: +++ case NFSPROC4_CLNT_WRITE: +++ case NFSPROC4_CLNT_RENAME: +++ case NFSPROC4_CLNT_SETACL: +++ policy = FAILOVER_RETRY_DELAY; +++ default: +++ policy = FAILOVER_RETRY; +++ } +++ return policy; +++} +++ +++static enum failover_policy_t failover_get_retry_policy(struct rpc_task *task) +++{ +++ struct rpc_clnt *clnt = task->tk_client; +++ u32 version = clnt->cl_vers; +++ enum failover_policy_t policy = FAILOVER_NOACTION; +++ +++ // 1. if the task meant to send to certain xprt, take no action +++ if (task->tk_flags & RPC_TASK_FIXED) +++ return FAILOVER_NOACTION; +++ +++ // 2. get policy by different version of nfs protocal +++ if (version == 3) // nfs v3 +++ policy = failover_get_nfs3_retry_policy(task); +++ else if (version == 4) // nfs v4 +++ policy = failover_get_nfs4_retry_policy(task); +++ else +++ return FAILOVER_NOACTION; +++ +++ // 3. if the task is not send to target, retry immediately +++ if (!RPC_WAS_SENT(task)) +++ policy = FAILOVER_RETRY; +++ +++ return policy; +++} +++ +++static int failover_check_task(struct rpc_task *task) +++{ +++ struct rpc_clnt *clnt = NULL; +++ int disable_mpath = enfs_get_config_multipath_state(); +++ +++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return -EINVAL; +++ } +++ +++ if (unlikely((task == NULL) || (task->tk_client == NULL))) { +++ enfs_log_error("The task is not valid.\n"); +++ return -EINVAL; +++ } +++ +++ clnt = task->tk_client; +++ +++ if (clnt->cl_prog != NFS_PROGRAM) { +++ enfs_log_debug("The clnt is not prog{%u} type.\n", +++ clnt->cl_prog); +++ return -EINVAL; +++ } +++ +++ if (!failover_is_enfs_clnt(clnt)) { +++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); +++ return -EINVAL; +++ } +++ return 0; +++} +++ +++void failover_handle(struct rpc_task *task) +++{ +++ enum failover_policy_t policy; +++ int ret; +++ +++ ret = failover_check_task(task); +++ if (ret != 0) +++ return; +++ +++ pm_set_path_state(task->tk_xprt, PM_STATE_FAULT); +++ +++ policy = failover_get_retry_policy(task); +++ +++ failover_retry_path_by_policy(task, policy); +++} +++ +++bool failover_task_need_call_start_again(struct rpc_task *task) +++{ +++ int ret; +++ +++ ret = failover_check_task(task); +++ if (ret != 0) +++ return false; +++ +++ return true; +++} +++ +++bool failover_prepare_transmit(struct rpc_task *task) +++{ +++ if (task->tk_flags & RPC_TASK_FIXED) +++ return true; +++ +++ if (pm_ping_is_test_xprt_task(task)) +++ return true; +++ +++ if (pm_get_path_state(task->tk_xprt) == PM_STATE_FAULT) { +++ task->tk_status = -ETIMEDOUT; +++ return false; +++ } +++ +++ return true; +++} ++diff --git a/fs/nfs/enfs/failover_path.h b/fs/nfs/enfs/failover_path.h ++new file mode 100644 ++index 000000000000..6f1294829a6e ++--- /dev/null +++++ b/fs/nfs/enfs/failover_path.h ++@@ -0,0 +1,17 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs path failover header file +++ * Author: y00583252 +++ * Create: 2023-08-02 +++ */ +++ +++#ifndef FAILOVER_PATH_H +++#define FAILOVER_PATH_H +++ +++#include <linux/sunrpc/sched.h> +++ +++void failover_handle(struct rpc_task *task); +++bool failover_prepare_transmit(struct rpc_task *task); +++ +++#endif // FAILOVER_PATH_H ++diff --git a/fs/nfs/enfs/failover_time.c b/fs/nfs/enfs/failover_time.c ++new file mode 100644 ++index 000000000000..866ea82d13fc ++--- /dev/null +++++ b/fs/nfs/enfs/failover_time.c ++@@ -0,0 +1,99 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: failover time file +++ * Create: 2023-08-02 +++ */ +++ +++#include "failover_time.h" +++#include <linux/jiffies.h> +++#include <linux/sunrpc/clnt.h> +++#include "enfs_config.h" +++#include "enfs_log.h" +++#include "failover_com.h" +++#include "pm_ping.h" +++ +++static unsigned long failover_get_mulitipath_timeout(struct rpc_clnt *clnt) +++{ +++ unsigned long config_tmo = enfs_get_config_multipath_timeout() * HZ; +++ unsigned long clnt_tmo = clnt->cl_timeout->to_initval; +++ +++ if (config_tmo == 0) +++ return clnt_tmo; +++ +++ return config_tmo > clnt_tmo ? clnt_tmo : config_tmo; +++} +++ +++void failover_adjust_task_timeout(struct rpc_task *task, void *condition) +++{ +++ struct rpc_clnt *clnt = NULL; +++ unsigned long tmo; +++ int disable_mpath = enfs_get_config_multipath_state(); +++ +++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return; +++ } +++ +++ clnt = task->tk_client; +++ if (unlikely(clnt == NULL)) { +++ enfs_log_error("task associate client is NULL.\n"); +++ return; +++ } +++ +++ if (!failover_is_enfs_clnt(clnt)) { +++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); +++ return; +++ } +++ +++ tmo = failover_get_mulitipath_timeout(clnt); +++ if (tmo == 0) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return; +++ } +++ +++ if (task->tk_timeout != 0) +++ task->tk_timeout = +++ task->tk_timeout < tmo ? task->tk_timeout : tmo; +++ else +++ task->tk_timeout = tmo; +++} +++ +++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req) +++{ +++ struct rpc_clnt *clnt = NULL; +++ int disable_mpath = enfs_get_config_multipath_state(); +++ +++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { +++ enfs_log_debug("Multipath is not enabled.\n"); +++ return; +++ } +++ +++ clnt = task->tk_client; +++ if (unlikely(clnt == NULL)) { +++ enfs_log_error("task associate client is NULL.\n"); +++ return; +++ } +++ +++ if (!failover_is_enfs_clnt(clnt)) { +++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); +++ return; +++ } +++ +++ if (!pm_ping_is_test_xprt_task(task)) +++ req->rq_timeout = failover_get_mulitipath_timeout(clnt); +++ else { +++ req->rq_timeout = enfs_get_config_path_detect_timeout() * HZ; +++ req->rq_majortimeo = req->rq_timeout + jiffies; +++ } +++ +++ /* +++ * when task is retried, the req is new, we lost major-timeout times, +++ * so we have to restore req major +++ * timeouts from the task, if it is stored. +++ */ +++ if (task->tk_major_timeo != 0) +++ req->rq_majortimeo = task->tk_major_timeo; +++ else +++ task->tk_major_timeo = req->rq_majortimeo; +++} ++diff --git a/fs/nfs/enfs/failover_time.h b/fs/nfs/enfs/failover_time.h ++new file mode 100644 ++index 000000000000..ede25b577a2a ++--- /dev/null +++++ b/fs/nfs/enfs/failover_time.h ++@@ -0,0 +1,16 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: failover time header file +++ * Create: 2023-08-02 +++ */ +++ +++#ifndef FAILOVER_TIME_H +++#define FAILOVER_TIME_H +++ +++#include <linux/sunrpc/sched.h> +++ +++void failover_adjust_task_timeout(struct rpc_task *task, void *condition); +++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req); +++ +++#endif // FAILOVER_TIME_H ++diff --git a/fs/nfs/enfs/init.h b/fs/nfs/enfs/init.h ++new file mode 100644 ++index 000000000000..fdabb9084e19 ++--- /dev/null +++++ b/fs/nfs/enfs/init.h ++@@ -0,0 +1,17 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs client init +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef ENFS_INIT_H +++#define ENFS_INIT_H +++ +++#include <linux/types.h> +++ +++int32_t enfs_init(void); +++void enfs_fini(void); +++ +++#endif ++diff --git a/fs/nfs/enfs/mgmt_init.c b/fs/nfs/enfs/mgmt_init.c ++new file mode 100644 ++index 000000000000..75a40c5e0f6c ++--- /dev/null +++++ b/fs/nfs/enfs/mgmt_init.c ++@@ -0,0 +1,22 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: mgmt component init +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#include "mgmt_init.h" +++#include <linux/printk.h> +++#include "enfs_errcode.h" +++#include "enfs_config.h" +++ +++int32_t mgmt_init(void) +++{ +++ return enfs_config_timer_init(); +++} +++ +++void mgmt_fini(void) +++{ +++ enfs_config_timer_exit(); +++} ++diff --git a/fs/nfs/enfs/mgmt_init.h b/fs/nfs/enfs/mgmt_init.h ++new file mode 100644 ++index 000000000000..aa78303b9f01 ++--- /dev/null +++++ b/fs/nfs/enfs/mgmt_init.h ++@@ -0,0 +1,18 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: mgmt component init +++ * Author: y00583252 +++ * Create: 2023-07-31 +++ */ +++ +++#ifndef MGMT_INIT_H +++#define MGMT_INIT_H +++ +++#include <linux/types.h> +++ +++int32_t mgmt_init(void); +++void mgmt_fini(void); +++ +++ +++#endif // MGMT_INIT_H ++diff --git a/fs/nfs/enfs/pm_ping.c b/fs/nfs/enfs/pm_ping.c ++new file mode 100644 ++index 000000000000..24153cd4c7f3 ++--- /dev/null +++++ b/fs/nfs/enfs/pm_ping.c ++@@ -0,0 +1,421 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: path state header file +++ * Author: x00833432 +++ * Create: 2023-08-21 +++ */ +++ +++#include "pm_ping.h" +++#include <linux/err.h> +++#include <linux/spinlock.h> +++#include <linux/slab.h> +++#include <linux/module.h> +++#include <linux/printk.h> +++#include <linux/kthread.h> +++#include <linux/nfs.h> +++#include <linux/errno.h> +++#include <linux/rcupdate.h> +++#include <linux/workqueue.h> +++#include <net/netns/generic.h> +++#include <linux/atomic.h> +++#include <linux/sunrpc/clnt.h> +++ +++#include "../../../net/sunrpc/netns.h" +++#include "pm_state.h" +++#include "enfs.h" +++#include "enfs_log.h" +++#include "enfs_config.h" +++ +++#define SLEEP_INTERVAL 2 +++extern unsigned int sunrpc_net_id; +++ +++static struct task_struct *pm_ping_timer_thread; +++//protect pint_execute_workq +++static spinlock_t ping_execute_workq_lock; +++// timer for test xprt workqueue +++static struct workqueue_struct *ping_execute_workq; +++// count the ping xprt work on flight +++static atomic_t check_xprt_count; +++ +++struct ping_xprt_work { +++ struct rpc_xprt *xprt; // use this specific xprt +++ struct rpc_clnt *clnt; // use this specific rpc_client +++ struct work_struct ping_work; +++}; +++ +++struct pm_ping_async_callback { +++ void *data; +++ void (*func)(void *data); +++}; +++ +++// set xprt's enum pm_check_state +++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, +++ enum pm_check_state state) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ +++ if (IS_ERR(xprt)) { +++ enfs_log_error("The xprt ptr is not exist.\n"); +++ return; +++ } +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ xprt_get(xprt); +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ xprt_put(xprt); +++ return; +++ } +++ +++ atomic_set(&ctx->path_check_state, state); +++ xprt_put(xprt); +++} +++ +++// get xprt's enum pm_check_state +++static enum pm_check_state pm_ping_get_path_check_state(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ enum pm_check_state state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return PM_CHECK_UNDEFINE; +++ } +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ return PM_CHECK_UNDEFINE; +++ } +++ +++ state = atomic_read(&ctx->path_check_state); +++ +++ return state; +++} +++ +++static void pm_ping_call_done_callback(void *data) +++{ +++ struct pm_ping_async_callback *callback_data = +++ (struct pm_ping_async_callback *)data; +++ +++ if (callback_data == NULL) +++ return; +++ +++ callback_data->func(callback_data->data); +++ +++ kfree(callback_data); +++} +++ +++// Default callback for async RPC calls +++static void pm_ping_call_done(struct rpc_task *task, void *data) +++{ +++ struct rpc_xprt *xprt = task->tk_xprt; +++ +++ atomic_dec(&check_xprt_count); +++ if (task->tk_status >= 0) +++ pm_set_path_state(xprt, PM_STATE_NORMAL); +++ else +++ pm_set_path_state(xprt, PM_STATE_FAULT); +++ +++ pm_ping_set_path_check_state(xprt, PM_CHECK_FINISH); +++ +++ pm_ping_call_done_callback(data); +++} +++ +++// register func to rpc_call_done +++static const struct rpc_call_ops pm_ping_set_status_ops = { +++ .rpc_call_done = pm_ping_call_done, +++}; +++ +++// execute work which in work_queue +++static void pm_ping_execute_work(struct work_struct *work) +++{ +++ int ret = 0; +++ +++ // get the work information +++ struct ping_xprt_work *work_info = +++ container_of(work, struct ping_xprt_work, ping_work); +++ +++ // if check state is pending +++ if (pm_ping_get_path_check_state(work_info->xprt) == PM_CHECK_WAITING) { +++ +++ pm_ping_set_path_check_state(work_info->xprt, +++ PM_CHECK_CHECKING); +++ +++ ret = rpc_clnt_test_xprt(work_info->clnt, +++ work_info->xprt, +++ &pm_ping_set_status_ops, +++ NULL, +++ RPC_TASK_ASYNC | RPC_TASK_FIXED); +++ +++ if (ret < 0) { +++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); +++ +++ pm_ping_set_path_check_state(work_info->xprt, +++ PM_CHECK_FINISH); +++ +++ } else +++ atomic_inc(&check_xprt_count); +++ +++ } +++ +++ atomic_dec(&work_info->clnt->cl_count); +++ xprt_put(work_info->xprt); +++ kfree(work_info); +++ work_info = NULL; +++} +++ +++static bool pm_ping_workqueue_queue_work(struct work_struct *work) +++{ +++ bool ret = false; +++ +++ spin_lock(&ping_execute_workq_lock); +++ +++ if (ping_execute_workq != NULL) +++ ret = queue_work(ping_execute_workq, work); +++ +++ spin_unlock(&ping_execute_workq_lock); +++ return ret; +++} +++ +++// init test work and add this work to workqueue +++static int pm_ping_add_work(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, void *data) +++{ +++ struct ping_xprt_work *work_info; +++ bool ret = false; +++ +++ if (IS_ERR(xprt) || xprt == NULL) { +++ enfs_log_error("The xprt ptr is not exist.\n"); +++ return -EINVAL; +++ } +++ +++ if (IS_ERR(clnt) || clnt == NULL) { +++ enfs_log_error("The clnt ptr is not exist.\n"); +++ return -EINVAL; +++ } +++ +++ if (!xprt->multipath_context) { +++ enfs_log_error("multipath_context is null.\n"); +++ return -EINVAL; +++ } +++ +++ // check xprt pending status, if pending status equals Finish +++ // means this xprt can inster to work queue +++ if (pm_ping_get_path_check_state(xprt) == +++ PM_CHECK_FINISH || +++ pm_ping_get_path_check_state(xprt) == +++ PM_CHECK_INIT) { +++ +++ enfs_log_debug("find xprt pointer. %p\n", xprt); +++ work_info = kzalloc(sizeof(struct ping_xprt_work), GFP_ATOMIC); +++ if (work_info == NULL) +++ return -ENOMEM; +++ work_info->clnt = clnt; +++ atomic_inc(&clnt->cl_count); +++ work_info->xprt = xprt; +++ xprt_get(xprt); +++ INIT_WORK(&work_info->ping_work, pm_ping_execute_work); +++ pm_ping_set_path_check_state(xprt, PM_CHECK_WAITING); +++ +++ ret = pm_ping_workqueue_queue_work(&work_info->ping_work); +++ if (!ret) { +++ atomic_dec(&work_info->clnt->cl_count); +++ xprt_put(work_info->xprt); +++ kfree(work_info); +++ return -EINVAL; +++ } +++ } +++ return 0; +++} +++ +++// encapsulate pm_ping_add_work() +++static int pm_ping_execute_xprt_test(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, void *data) +++{ +++ pm_ping_add_work(clnt, xprt, NULL); +++ // return 0 for rpc_clnt_iterate_for_each_xprt(); +++ // because negative value will stop iterate all xprt +++ // and we need return negative value for debug +++ // Therefore, we need this function to iterate all xprt +++ return 0; +++} +++ +++// export to other module add ping work to workqueue +++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) +++{ +++ int ret; +++ +++ ret = pm_ping_add_work(clnt, xprt, NULL); +++ return ret; +++} +++ +++// iterate xprt in the client +++static void pm_ping_loop_rpclnt(struct sunrpc_net *sn) +++{ +++ struct rpc_clnt *clnt; +++ +++ spin_lock(&sn->rpc_client_lock); +++ list_for_each_entry_rcu(clnt, &sn->all_clients, cl_clients) { +++ if (clnt->cl_enfs) { +++ enfs_log_debug("find rpc_clnt. %p\n", clnt); +++ rpc_clnt_iterate_for_each_xprt(clnt, +++ pm_ping_execute_xprt_test, NULL); +++ } +++ } +++ spin_unlock(&sn->rpc_client_lock); +++} +++ +++// iterate each clnt in the sunrpc_net +++static void pm_ping_loop_sunrpc_net(void) +++{ +++ struct net *net; +++ struct sunrpc_net *sn; +++ +++ rcu_read_lock(); +++ for_each_net_rcu(net) { +++ sn = net_generic(net, sunrpc_net_id); +++ if (sn == NULL) +++ continue; +++ pm_ping_loop_rpclnt(sn); +++ } +++ rcu_read_unlock(); +++} +++ +++static int pm_ping_routine(void *data) +++{ +++ while (!kthread_should_stop()) { +++ // equale 0 means open multipath +++ if (enfs_get_config_multipath_state() == +++ ENFS_MULTIPATH_ENABLE) +++ pm_ping_loop_sunrpc_net(); +++ +++ msleep((unsigned int) +++ enfs_get_config_path_detect_interval() * 1000); +++ } +++ return 0; +++} +++ +++// start thread to cycly ping +++static int pm_ping_start(void) +++{ +++ pm_ping_timer_thread = +++ kthread_run(pm_ping_routine, NULL, "pm_ping_routine"); +++ if (IS_ERR(pm_ping_timer_thread)) { +++ enfs_log_error("Failed to create kernel thread\n"); +++ return PTR_ERR(pm_ping_timer_thread); +++ } +++ return 0; +++} +++ +++// initialize workqueue +++static int pm_ping_workqueue_init(void) +++{ +++ struct workqueue_struct *queue = NULL; +++ +++ queue = create_workqueue("pm_ping_workqueue"); +++ +++ if (queue == NULL) { +++ enfs_log_error("create workqueue failed.\n"); +++ return -ENOMEM; +++ } +++ +++ spin_lock(&ping_execute_workq_lock); +++ ping_execute_workq = queue; +++ spin_unlock(&ping_execute_workq_lock); +++ enfs_log_info("create workqueue succeeeded.\n"); +++ return 0; +++} +++ +++static void pm_ping_workqueue_fini(void) +++{ +++ struct workqueue_struct *queue = NULL; +++ +++ spin_lock(&ping_execute_workq_lock); +++ queue = ping_execute_workq; +++ ping_execute_workq = NULL; +++ spin_unlock(&ping_execute_workq_lock); +++ +++ enfs_log_info("delete work queue\n"); +++ +++ if (queue != NULL) { +++ flush_workqueue(queue); +++ destroy_workqueue(queue); +++ } +++} +++ +++// module exit func +++void pm_ping_fini(void) +++{ +++ if (pm_ping_timer_thread) +++ kthread_stop(pm_ping_timer_thread); +++ +++ pm_ping_workqueue_fini(); +++ +++ while (atomic_read(&check_xprt_count) != 0) +++ msleep(SLEEP_INTERVAL); +++} +++ +++// module init func +++int pm_ping_init(void) +++{ +++ int ret; +++ +++ atomic_set(&check_xprt_count, 0); +++ ret = pm_ping_workqueue_init(); +++ if (ret != 0) { +++ enfs_log_error("PM_PING Module loading failed.\n"); +++ return ret; +++ } +++ ret = pm_ping_start(); +++ if (ret != 0) { +++ enfs_log_error("PM_PING Module loading failed.\n"); +++ pm_ping_workqueue_fini(); +++ return ret; +++ } +++ +++ return ret; +++} +++ +++bool pm_ping_is_test_xprt_task(struct rpc_task *task) +++{ +++ return task->tk_ops == &pm_ping_set_status_ops ? true : false; +++} +++ +++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void (*func)(void *data), +++ void *data) +++{ +++ int ret; +++ +++ struct pm_ping_async_callback *callback_data = +++ kzalloc(sizeof(struct pm_ping_async_callback), GFP_KERNEL); +++ +++ if (callback_data == NULL) { +++ enfs_log_error("failed to mzalloc mem\n"); +++ return -ENOMEM; +++ } +++ +++ callback_data->data = data; +++ callback_data->func = func; +++ atomic_inc(&check_xprt_count); +++ ret = rpc_clnt_test_xprt(clnt, xprt, +++ &pm_ping_set_status_ops, +++ callback_data, +++ RPC_TASK_ASYNC | RPC_TASK_FIXED); +++ +++ if (ret < 0) { +++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); +++ atomic_dec(&check_xprt_count); +++ } +++ +++ return ret; +++} ++diff --git a/fs/nfs/enfs/pm_ping.h b/fs/nfs/enfs/pm_ping.h ++new file mode 100644 ++index 000000000000..6bcb94bfc836 ++--- /dev/null +++++ b/fs/nfs/enfs/pm_ping.h ++@@ -0,0 +1,33 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: nfs configuration +++ * Author: x00833432 +++ * Create: 2023-07-27 +++ */ +++ +++#ifndef PM_PING_H +++#define PM_PING_H +++ +++#include <linux/sunrpc/clnt.h> +++ +++enum pm_check_state { +++ PM_CHECK_INIT, // this xprt never been queued +++ PM_CHECK_WAITING, // this xprt waiting in the queue +++ PM_CHECK_CHECKING, // this xprt is testing +++ PM_CHECK_FINISH, // this xprt has been finished +++ PM_CHECK_UNDEFINE, // undefine multipath struct +++}; +++ +++int pm_ping_init(void); +++void pm_ping_fini(void); +++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, +++ enum pm_check_state state); +++bool pm_ping_is_test_xprt_task(struct rpc_task *task); +++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, +++ struct rpc_xprt *xprt, +++ void (*func)(void *data), +++ void *data); +++ +++#endif // PM_PING_H ++diff --git a/fs/nfs/enfs/pm_state.c b/fs/nfs/enfs/pm_state.c ++new file mode 100644 ++index 000000000000..220621a207a2 ++--- /dev/null +++++ b/fs/nfs/enfs/pm_state.c ++@@ -0,0 +1,158 @@ +++// SPDX-License-Identifier: GPL-2.0 +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: path state file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++#include "pm_state.h" +++#include <linux/sunrpc/xprt.h> +++ +++#include "enfs.h" +++#include "enfs_log.h" +++ +++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ enum pm_path_state state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return PM_STATE_UNDEFINED; +++ } +++ +++ xprt_get(xprt); +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ xprt_put(xprt); +++ return PM_STATE_UNDEFINED; +++ } +++ +++ state = atomic_read(&ctx->path_state); +++ +++ xprt_put(xprt); +++ +++ return state; +++} +++ +++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state) +++{ +++ struct enfs_xprt_context *ctx = NULL; +++ enum pm_path_state cur_state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ xprt_get(xprt); +++ +++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; +++ if (ctx == NULL) { +++ enfs_log_error("The xprt multipath ctx is not valid.\n"); +++ xprt_put(xprt); +++ return; +++ } +++ +++ cur_state = atomic_read(&ctx->path_state); +++ if (cur_state == state) { +++ enfs_log_debug("The xprt is already {%d}.\n", state); +++ xprt_put(xprt); +++ return; +++ } +++ +++ atomic_set(&ctx->path_state, state); +++ enfs_log_info("The xprt {%p} path state change from {%d} to {%d}.\n", +++ xprt, cur_state, state); +++ +++ xprt_put(xprt); +++} +++ +++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len) +++{ +++ enum pm_path_state state; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ if ((buf == NULL) || (len <= 0)) { +++ enfs_log_error("Buffer is not valid, len=%d.\n", len); +++ return; +++ } +++ +++ state = pm_get_path_state(xprt); +++ +++ switch (state) { +++ case PM_STATE_INIT: +++ (void)snprintf(buf, len, "Init"); +++ break; +++ case PM_STATE_NORMAL: +++ (void)snprintf(buf, len, "Normal"); +++ break; +++ case PM_STATE_FAULT: +++ (void)snprintf(buf, len, "Fault"); +++ break; +++ default: +++ (void)snprintf(buf, len, "Unknown"); +++ break; +++ } +++} +++ +++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len) +++{ +++ int i; +++ unsigned long state; +++ static unsigned long xprt_mask[] = { +++ XPRT_LOCKED, XPRT_CONNECTED, +++ XPRT_CONNECTING, XPRT_CLOSE_WAIT, +++ XPRT_BOUND, XPRT_BINDING, XPRT_CLOSING, +++ XPRT_CONGESTED}; +++ +++ static const char *const xprt_state_desc[] = { +++ "LOCKED", "CONNECTED", "CONNECTING", +++ "CLOSE_WAIT", "BOUND", "BINDING", +++ "CLOSING", "CONGESTED"}; +++ int pos = 0; +++ int ret = 0; +++ +++ if (xprt == NULL) { +++ enfs_log_error("The xprt is not valid.\n"); +++ return; +++ } +++ +++ if ((buf == NULL) || (len <= 0)) { +++ enfs_log_error( +++ "Xprt state buffer is not valid, len=%d.\n", +++ len); +++ return; +++ } +++ +++ xprt_get(xprt); +++ state = READ_ONCE(xprt->state); +++ xprt_put(xprt); +++ +++ for (i = 0; i < ARRAY_SIZE(xprt_mask); ++i) { +++ if (pos >= len) +++ break; +++ +++ if (!test_bit(xprt_mask[i], &state)) +++ continue; +++ +++ if (pos == 0) +++ ret = snprintf(buf, len, "%s", xprt_state_desc[i]); +++ else +++ ret = snprintf(buf + pos, len - pos, "|%s", +++ xprt_state_desc[i]); +++ +++ if (ret < 0) { +++ enfs_log_error("format state failed, ret %d.\n", ret); +++ break; +++ } +++ +++ pos += ret; +++ } +++} ++diff --git a/fs/nfs/enfs/pm_state.h b/fs/nfs/enfs/pm_state.h ++new file mode 100644 ++index 000000000000..f5f52e5ab91d ++--- /dev/null +++++ b/fs/nfs/enfs/pm_state.h ++@@ -0,0 +1,28 @@ +++/* SPDX-License-Identifier: GPL-2.0 */ +++/* +++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. +++ * Description: path state header file +++ * Author: y00583252 +++ * Create: 2023-08-12 +++ */ +++ +++#ifndef PM_STATE_H +++#define PM_STATE_H +++ +++#include <linux/types.h> +++#include <linux/sunrpc/xprt.h> +++ +++enum pm_path_state { +++ PM_STATE_INIT, +++ PM_STATE_NORMAL, +++ PM_STATE_FAULT, +++ PM_STATE_UNDEFINED // xprt is not multipath xprt +++}; +++ +++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state); +++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt); +++ +++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len); +++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len); +++ +++#endif // PM_STATE_H +diff --git a/0006-add_enfs_compile_option.patch b/0006-add_enfs_compile_option.patch +new file mode 100644 +index 0000000..ff3bc0e +--- /dev/null ++++ b/0006-add_enfs_compile_option.patch +@@ -0,0 +1,70 @@ ++diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig ++index b04256636d4b..ae53510c0627 100644 ++--- a/arch/arm64/configs/openeuler_defconfig +++++ b/arch/arm64/configs/openeuler_defconfig ++@@ -5344,6 +5344,7 @@ CONFIG_LOCKD=m ++ CONFIG_LOCKD_V4=y ++ CONFIG_NFS_ACL_SUPPORT=m ++ CONFIG_NFS_COMMON=y +++# CONFIG_ENFS is not set ++ CONFIG_SUNRPC=m ++ CONFIG_SUNRPC_GSS=m ++ CONFIG_SUNRPC_BACKCHANNEL=y ++diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig ++index 59baeb2973af..ccc317f7fdb2 100644 ++--- a/arch/x86/configs/openeuler_defconfig +++++ b/arch/x86/configs/openeuler_defconfig ++@@ -6825,6 +6825,7 @@ CONFIG_LOCKD=m ++ CONFIG_LOCKD_V4=y ++ CONFIG_NFS_ACL_SUPPORT=m ++ CONFIG_NFS_COMMON=y +++# CONFIG_ENFS is not set ++ CONFIG_SUNRPC=m ++ CONFIG_SUNRPC_GSS=m ++ CONFIG_SUNRPC_BACKCHANNEL=y ++diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig ++index e55f86713948..872c9b7671b1 100644 ++--- a/fs/nfs/Kconfig +++++ b/fs/nfs/Kconfig ++@@ -196,3 +196,14 @@ config NFS_DEBUG ++ depends on NFS_FS && SUNRPC_DEBUG ++ select CRC32 ++ default y +++ +++config ENFS +++ tristate "NFS client support for ENFS" +++ depends on NFS_FS +++ default n +++ help +++ This option enables support multipath of the NFS protocol +++ in the kernel's NFS client. +++ This feature will improve performance and reliability. +++ +++ If sure, say Y. ++diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile ++index c587e3c4c6a6..19d0ac2ba3b8 100644 ++--- a/fs/nfs/Makefile +++++ b/fs/nfs/Makefile ++@@ -12,6 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ ++ nfs-$(CONFIG_ROOT_NFS) += nfsroot.o ++ nfs-$(CONFIG_SYSCTL) += sysctl.o ++ nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o +++nfs-$(CONFIG_ENFS) += enfs_adapter.o ++ ++ obj-$(CONFIG_NFS_V2) += nfsv2.o ++ nfsv2-y := nfs2super.o proc.o nfs2xdr.o ++@@ -34,3 +35,5 @@ nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o ++ obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ ++ obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ ++ obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ +++ +++obj-$(CONFIG_ENFS) += enfs/ ++diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile ++index 090658c3da12..fe4e3b28c5d1 100644 ++--- a/net/sunrpc/Makefile +++++ b/net/sunrpc/Makefile ++@@ -19,3 +19,4 @@ sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o ++ sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o ++ sunrpc-$(CONFIG_PROC_FS) += stats.o ++ sunrpc-$(CONFIG_SYSCTL) += sysctl.o +++sunrpc-$(CONFIG_ENFS) += sunrpc_enfs_adapter.o +diff --git a/kernel.spec b/kernel.spec +index 3215446..e242c00 100644 +--- a/kernel.spec ++++ b/kernel.spec +@@ -60,6 +60,13 @@ Source9002: series.conf + Source9998: patches.tar.bz2 + %endif + ++Patch0001: 0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch ++Patch0002: 0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch ++Patch0003: 0003-add_enfs_module.patch ++Patch0004: 0004-add_enfs_module_for_sunrpc_multipatch.patch ++Patch0005: 0005-add_enfs_module_for_sunrpc_failover_and_configure.patch ++Patch0006: 0006-add_enfs_compile_option.patch ++ + #BuildRequires: + BuildRequires: module-init-tools, patch >= 2.5.4, bash >= 2.03, tar + BuildRequires: bzip2, xz, findutils, gzip, m4, perl, make >= 3.78, diffutils, gawk +@@ -256,6 +263,12 @@ Applypatches() + Applypatches series.conf %{_builddir}/kernel-%{version}/linux-%{KernelVer} + %endif + ++%patch0001 -p1 ++%patch0002 -p1 ++%patch0003 -p1 ++%patch0004 -p1 ++%patch0005 -p1 ++%patch0006 -p1 + touch .scmversion + + find . $ -name "*.orig" -o -name "*~" $ -exec rm -f {} \; >/dev/null +-- +2.25.0.windows.1 + diff --git a/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch new file mode 100644 index 0000000..38e57a9 --- /dev/null +++ b/0001-nfs_add_api_to_support_enfs_registe_and_handle_mount_option.patch @@ -0,0 +1,757 @@ +diff --git a/fs/nfs/client.c b/fs/nfs/client.c +index 7d02dc52209d..50820a8a684a 100644 +--- a/fs/nfs/client.c ++++ b/fs/nfs/client.c +@@ -48,7 +48,7 @@ + #include "callback.h" + #include "delegation.h" + #include "iostat.h" +-#include "internal.h" ++#include "enfs_adapter.h" + #include "fscache.h" + #include "pnfs.h" + #include "nfs.h" +@@ -255,6 +255,7 @@ void nfs_free_client(struct nfs_client *clp) + put_nfs_version(clp->cl_nfs_mod); + kfree(clp->cl_hostname); + kfree(clp->cl_acceptor); ++ nfs_free_multi_path_client(clp); + kfree(clp); + } + EXPORT_SYMBOL_GPL(nfs_free_client); +@@ -330,6 +331,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat + sap)) + continue; + ++ if (!nfs_multipath_client_match(clp, data)) ++ continue; ++ + refcount_inc(&clp->cl_count); + return clp; + } +@@ -512,6 +516,9 @@ int nfs_create_rpc_client(struct nfs_client *clp, + .program = &nfs_program, + .version = clp->rpc_ops->version, + .authflavor = flavor, ++#if IS_ENABLED(CONFIG_ENFS) ++ .multipath_option = cl_init->enfs_option, ++#endif + }; + + if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) +@@ -634,6 +641,13 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp, + /* the client is already initialised */ + if (clp->cl_cons_state == NFS_CS_READY) + return clp; ++ error = nfs_create_multi_path_client(clp, cl_init); ++ if (error < 0) { ++ dprintk("%s: create failed.%d!\n", __func__, error); ++ nfs_put_client(clp); ++ clp = ERR_PTR(error); ++ return clp; ++ } + + /* + * Create a client RPC handle for doing FSSTAT with UNIX auth only +@@ -666,6 +680,9 @@ static int nfs_init_server(struct nfs_server *server, + .net = data->net, + .timeparms = &timeparms, + .init_flags = (1UL << NFS_CS_REUSEPORT), ++#if IS_ENABLED(CONFIG_ENFS) ++ .enfs_option = data->enfs_option, ++#endif + }; + struct nfs_client *clp; + int error; +diff --git a/fs/nfs/enfs_adapter.c b/fs/nfs/enfs_adapter.c +new file mode 100644 +index 000000000000..7f471f2072c4 +--- /dev/null ++++ b/fs/nfs/enfs_adapter.c +@@ -0,0 +1,230 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs3.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/sunrpc/sched.h> ++#include <linux/nfs_iostat.h> ++#include "enfs_adapter.h" ++#include "iostat.h" ++ ++struct enfs_adapter_ops __rcu *enfs_adapter; ++ ++int enfs_adapter_register(struct enfs_adapter_ops *ops) ++{ ++ struct enfs_adapter_ops *old; ++ ++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, NULL, ops); ++ if (old == NULL || old == ops) ++ return 0; ++ pr_err("regist %s ops %p failed. old %p\n", __func__, ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(enfs_adapter_register); ++ ++int enfs_adapter_unregister(struct enfs_adapter_ops *ops) ++{ ++ struct enfs_adapter_ops *old; ++ ++ old = cmpxchg((struct enfs_adapter_ops **)&enfs_adapter, ops, NULL); ++ if (old == ops || old == NULL) ++ return 0; ++ pr_err("unregist %s ops %p failed. old %p\n", __func__, ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(enfs_adapter_unregister); ++ ++struct enfs_adapter_ops *nfs_multipath_router_get(void) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ rcu_read_lock(); ++ ops = rcu_dereference(enfs_adapter); ++ if (ops == NULL) { ++ rcu_read_unlock(); ++ return NULL; ++ } ++ if (!try_module_get(ops->owner)) ++ ops = NULL; ++ rcu_read_unlock(); ++ return ops; ++} ++ ++void nfs_multipath_router_put(struct enfs_adapter_ops *ops) ++{ ++ if (ops) ++ module_put(ops->owner); ++} ++ ++bool is_valid_option(enum nfsmultipathoptions option) ++{ ++ if (option < REMOTEADDR || option >= INVALID_OPTION) { ++ pr_warn("%s: ENFS invalid option %d\n", __func__, option); ++ return false; ++ } ++ ++ return true; ++} ++ ++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, ++ struct nfs_parsed_mount_data *mnt) ++{ ++ ++ //parseMultiPathOptions(getNfsMultiPathOpt(token), string, mnt); ++ ++ int rc; ++ struct enfs_adapter_ops *ops; ++ ++ ops = nfs_multipath_router_get(); ++ if ((ops == NULL) || (ops->parse_mount_options == NULL) || ++ !is_valid_option(option)) { ++ nfs_multipath_router_put(ops); ++ dfprintk(MOUNT, ++ "NFS: parsing nfs mount option enfs not load[%s]\n" ++ , __func__); ++ return -EOPNOTSUPP; ++ } ++ // nfs_multipath_parse_options ++ dfprintk(MOUNT, "NFS: parsing nfs mount option '%s' type: %d[%s]\n" ++ , str, option, __func__); ++ rc = ops->parse_mount_options(option, str, &mnt->enfs_option, mnt->net); ++ nfs_multipath_router_put(ops); ++ return rc; ++} ++ ++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ if (data->enfs_option == NULL) ++ return; ++ ++ ops = nfs_multipath_router_get(); ++ if ((ops == NULL) || (ops->free_mount_options == NULL)) { ++ nfs_multipath_router_put(ops); ++ return; ++ } ++ ops->free_mount_options((void *)&data->enfs_option); ++ nfs_multipath_router_put(ops); ++} ++ ++int nfs_create_multi_path_client(struct nfs_client *client, ++ const struct nfs_client_initdata *cl_init) ++{ ++ int ret = 0; ++ struct enfs_adapter_ops *ops; ++ ++ if (cl_init->enfs_option == NULL) ++ return 0; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_init != NULL) ++ ret = ops->client_info_init( ++ (void *)&client->cl_multipath_data, cl_init); ++ nfs_multipath_router_put(ops); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(nfs_create_multi_path_client); ++ ++void nfs_free_multi_path_client(struct nfs_client *clp) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ if (clp->cl_multipath_data == NULL) ++ return; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_free != NULL) ++ ops->client_info_free(clp->cl_multipath_data); ++ nfs_multipath_router_put(ops); ++} ++ ++int nfs_multipath_client_match(struct nfs_client *clp, ++ const struct nfs_client_initdata *sap) ++{ ++ int ret = true; ++ struct enfs_adapter_ops *ops; ++ ++ pr_info("%s src %p dst %p\n.", __func__, ++ clp->cl_multipath_data, sap->enfs_option); ++ ++ if (clp->cl_multipath_data == NULL && sap->enfs_option == NULL) ++ return true; ++ ++ if ((clp->cl_multipath_data == NULL && sap->enfs_option) || ++ (clp->cl_multipath_data && sap->enfs_option == NULL)) { ++ pr_err("not match client src %p dst %p\n.", ++ clp->cl_multipath_data, sap->enfs_option); ++ return false; ++ } ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_match != NULL) ++ ret = ops->client_info_match(clp->cl_multipath_data, ++ sap->enfs_option); ++ nfs_multipath_router_put(ops); ++ ++ return ret; ++} ++ ++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst) ++{ ++ int ret = true; ++ struct enfs_adapter_ops *ops; ++ ++ if (src->cl_multipath_data == NULL && dst->cl_multipath_data == NULL) ++ return true; ++ ++ if (src->cl_multipath_data == NULL || dst->cl_multipath_data == NULL) ++ return false; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->nfs4_client_info_match != NULL) ++ ret = ops->nfs4_client_info_match(src->cl_multipath_data, ++ src->cl_multipath_data); ++ nfs_multipath_router_put(ops); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(nfs4_multipath_client_match); ++ ++void nfs_multipath_show_client_info(struct seq_file *mount_option, ++ struct nfs_server *server) ++{ ++ struct enfs_adapter_ops *ops; ++ ++ if (mount_option == NULL || server == NULL || ++ server->client == NULL || ++ server->nfs_client->cl_multipath_data == NULL) ++ return; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->client_info_show != NULL) ++ ops->client_info_show(mount_option, server); ++ nfs_multipath_router_put(ops); ++} ++ ++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) ++{ ++ int ret = 0; ++ struct enfs_adapter_ops *ops; ++ ++ if (nfs_client == NULL || nfs_client->cl_rpcclient == NULL) ++ return 0; ++ ++ ops = nfs_multipath_router_get(); ++ if (ops != NULL && ops->remount_ip_list != NULL) ++ ret = ops->remount_ip_list(nfs_client, enfs_option); ++ nfs_multipath_router_put(ops); ++ return ret; ++} ++EXPORT_SYMBOL_GPL(nfs_remount_iplist); +diff --git a/fs/nfs/enfs_adapter.h b/fs/nfs/enfs_adapter.h +new file mode 100644 +index 000000000000..752544e18056 +--- /dev/null ++++ b/fs/nfs/enfs_adapter.h +@@ -0,0 +1,101 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapt header. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _NFS_MULTIPATH_H_ ++#define _NFS_MULTIPATH_H_ ++ ++#include "internal.h" ++ ++#if IS_ENABLED(CONFIG_ENFS) ++enum nfsmultipathoptions { ++ REMOTEADDR, ++ LOCALADDR, ++ REMOTEDNSNAME, ++ REMOUNTREMOTEADDR, ++ REMOUNTLOCALADDR, ++ INVALID_OPTION ++}; ++ ++ ++struct enfs_adapter_ops { ++ const char *name; ++ struct module *owner; ++ int (*parse_mount_options)(enum nfsmultipathoptions option, ++ char *str, void **enfs_option, struct net *net_ns); ++ ++ void (*free_mount_options)(void **data); ++ ++ int (*client_info_init)(void **data, ++ const struct nfs_client_initdata *cl_init); ++ void (*client_info_free)(void *data); ++ int (*client_info_match)(void *src, void *dst); ++ int (*nfs4_client_info_match)(void *src, void *dst); ++ void (*client_info_show)(struct seq_file *mount_option, void *data); ++ int (*remount_ip_list)(struct nfs_client *nfs_client, ++ void *enfs_option); ++}; ++ ++int enfs_parse_mount_options(enum nfsmultipathoptions option, char *str, ++ struct nfs_parsed_mount_data *mnt); ++void enfs_free_mount_options(struct nfs_parsed_mount_data *data); ++int nfs_create_multi_path_client(struct nfs_client *client, ++ const struct nfs_client_initdata *cl_init); ++void nfs_free_multi_path_client(struct nfs_client *clp); ++int nfs_multipath_client_match(struct nfs_client *clp, ++ const struct nfs_client_initdata *sap); ++int nfs4_multipath_client_match(struct nfs_client *src, struct nfs_client *dst); ++void nfs_multipath_show_client_info(struct seq_file *mount_option, ++ struct nfs_server *server); ++int enfs_adapter_register(struct enfs_adapter_ops *ops); ++int enfs_adapter_unregister(struct enfs_adapter_ops *ops); ++int nfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); ++int nfs4_create_multi_path(struct nfs_server *server, ++ struct nfs_parsed_mount_data *data, ++ const struct rpc_timeout *timeparms); ++ ++#else ++static inline ++void nfs_free_multi_path_client(struct nfs_client *clp) ++{ ++ ++} ++ ++static inline ++int nfs_multipath_client_match(struct nfs_client *clp, ++ const struct nfs_client_initdata *sap) ++{ ++ return 1; ++} ++ ++static inline ++int nfs_create_multi_path_client(struct nfs_client *client, ++ const struct nfs_client_initdata *cl_init) ++{ ++ return 0; ++} ++ ++static inline ++void nfs_multipath_show_client_info(struct seq_file *mount_option, ++ struct nfs_server *server) ++{ ++ ++} ++ ++static inline ++int nfs4_multipath_client_match(struct nfs_client *src, ++ struct nfs_client *dst) ++{ ++ return 1; ++} ++ ++static inline ++void enfs_free_mount_options(struct nfs_parsed_mount_data *data) ++{ ++ ++} ++ ++#endif // CONFIG_ENFS ++#endif // _NFS_MULTIPATH_H_ +diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h +index 0ce5a90640c4..c696693edc7b 100644 +--- a/fs/nfs/internal.h ++++ b/fs/nfs/internal.h +@@ -93,6 +93,9 @@ struct nfs_client_initdata { + u32 minorversion; + struct net *net; + const struct rpc_timeout *timeparms; ++#if IS_ENABLED(CONFIG_ENFS) ++ void *enfs_option; /* struct multipath_mount_options * */ ++#endif + }; + + /* +@@ -135,6 +138,9 @@ struct nfs_parsed_mount_data { + + struct security_mnt_opts lsm_opts; + struct net *net; ++#if IS_ENABLED(CONFIG_ENFS) ++ void *enfs_option; /* struct multipath_mount_options * */ ++#endif + }; + + /* mount_clnt.c */ +diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c +index 1350ea673672..4aa6e1f961f7 100644 +--- a/fs/nfs/nfs4client.c ++++ b/fs/nfs/nfs4client.c +@@ -10,7 +10,7 @@ + #include <linux/sunrpc/xprt.h> + #include <linux/sunrpc/bc_xprt.h> + #include <linux/sunrpc/rpc_pipe_fs.h> +-#include "internal.h" ++#include "enfs_adapter.h" + #include "callback.h" + #include "delegation.h" + #include "nfs4session.h" +@@ -225,6 +225,16 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); + ++#if IS_ENABLED(CONFIG_ENFS) ++ err = nfs_create_multi_path_client(clp, cl_init); ++ if (err < 0) { ++ dprintk("%s: create failed.%d\n", __func__, err); ++ nfs_put_client(clp); ++ clp = ERR_PTR(err); ++ return clp; ++ } ++#endif ++ + /* + * Set up the connection to the server before we add add to the + * global list. +@@ -529,6 +539,9 @@ static int nfs4_match_client(struct nfs_client *pos, struct nfs_client *new, + if (!nfs4_match_client_owner_id(pos, new)) + return 1; + ++ if (!nfs4_multipath_client_match(pos, new)) ++ return 1; ++ + return 0; + } + +@@ -860,7 +873,7 @@ static int nfs4_set_client(struct nfs_server *server, + const size_t addrlen, + const char *ip_addr, + int proto, const struct rpc_timeout *timeparms, +- u32 minorversion, struct net *net) ++ u32 minorversion, struct net *net, void *enfs_option) + { + struct nfs_client_initdata cl_init = { + .hostname = hostname, +@@ -872,6 +885,9 @@ static int nfs4_set_client(struct nfs_server *server, + .minorversion = minorversion, + .net = net, + .timeparms = timeparms, ++#if IS_ENABLED(CONFIG_ENFS) ++ .enfs_option = enfs_option, ++#endif + }; + struct nfs_client *clp; + +@@ -1042,6 +1058,30 @@ static int nfs4_server_common_setup(struct nfs_server *server, + return error; + } + ++int nfs4_create_multi_path(struct nfs_server *server, ++ struct nfs_parsed_mount_data *data, ++ const struct rpc_timeout *timeparms) ++{ ++ struct nfs_client_initdata cl_init = { ++ .hostname = data->nfs_server.hostname, ++ .addr = (const struct sockaddr *)&data->nfs_server.address, ++ .addrlen = data->nfs_server.addrlen, ++ .ip_addr = data->client_address, ++ .nfs_mod = &nfs_v4, ++ .proto = data->nfs_server.protocol, ++ .minorversion = data->minorversion, ++ .net = data->net, ++ .timeparms = timeparms, ++#if IS_ENABLED(CONFIG_ENFS) ++ .enfs_option = data->enfs_option, ++#endif // CONFIG_ENFS ++ }; ++ ++ return nfs_create_multi_path_client(server->nfs_client, &cl_init); ++ ++} ++EXPORT_SYMBOL_GPL(nfs4_create_multi_path); ++ + /* + * Create a version 4 volume record + */ +@@ -1050,6 +1090,7 @@ static int nfs4_init_server(struct nfs_server *server, + { + struct rpc_timeout timeparms; + int error; ++ void *enfs_option = NULL; + + nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, + data->timeo, data->retrans); +@@ -1067,6 +1108,10 @@ static int nfs4_init_server(struct nfs_server *server, + else + data->selected_flavor = RPC_AUTH_UNIX; + ++#if IS_ENABLED(CONFIG_ENFS) ++ enfs_option = data->enfs_option; ++#endif ++ + /* Get a client record */ + error = nfs4_set_client(server, + data->nfs_server.hostname, +@@ -1076,7 +1121,7 @@ static int nfs4_init_server(struct nfs_server *server, + data->nfs_server.protocol, + &timeparms, + data->minorversion, +- data->net); ++ data->net, enfs_option); + if (error < 0) + return error; + +@@ -1161,7 +1206,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, + XPRT_TRANSPORT_RDMA, + parent_server->client->cl_timeout, + parent_client->cl_mvops->minor_version, +- parent_client->cl_net); ++ parent_client->cl_net, NULL); + if (!error) + goto init_server; + #endif /* IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) */ +@@ -1174,7 +1219,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, + XPRT_TRANSPORT_TCP, + parent_server->client->cl_timeout, + parent_client->cl_mvops->minor_version, +- parent_client->cl_net); ++ parent_client->cl_net, NULL); + if (error < 0) + goto error; + +@@ -1269,7 +1314,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, + set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); + error = nfs4_set_client(server, hostname, sap, salen, buf, + clp->cl_proto, clnt->cl_timeout, +- clp->cl_minorversion, net); ++ clp->cl_minorversion, net, NULL); + clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); + if (error != 0) { + nfs_server_insert_lists(server); +diff --git a/fs/nfs/super.c b/fs/nfs/super.c +index a05e1eb2c3fd..83cd294aca15 100644 +--- a/fs/nfs/super.c ++++ b/fs/nfs/super.c +@@ -61,7 +61,7 @@ + #include "callback.h" + #include "delegation.h" + #include "iostat.h" +-#include "internal.h" ++#include "enfs_adapter.h" + #include "fscache.h" + #include "nfs4session.h" + #include "pnfs.h" +@@ -113,6 +113,12 @@ enum { + + /* Special mount options */ + Opt_userspace, Opt_deprecated, Opt_sloppy, ++#if IS_ENABLED(CONFIG_ENFS) ++ Opt_remote_iplist, ++ Opt_local_iplist, ++ Opt_remote_dnslist, ++ Opt_enfs_info, ++#endif + + Opt_err + }; +@@ -183,6 +189,13 @@ static const match_table_t nfs_mount_option_tokens = { + { Opt_fscache_uniq, "fsc=%s" }, + { Opt_local_lock, "local_lock=%s" }, + ++#if IS_ENABLED(CONFIG_ENFS) ++ { Opt_remote_iplist, "remoteaddrs=%s" }, ++ { Opt_local_iplist, "localaddrs=%s" }, ++ { Opt_remote_dnslist, "remotednsname=%s" }, ++ { Opt_enfs_info, "enfs_info=%s" }, ++#endif ++ + /* The following needs to be listed after all other options */ + { Opt_nfsvers, "v%s" }, + +@@ -365,6 +378,21 @@ static struct shrinker acl_shrinker = { + .seeks = DEFAULT_SEEKS, + }; + ++#if IS_ENABLED(CONFIG_ENFS) ++enum nfsmultipathoptions getNfsMultiPathOpt(int token) ++{ ++ switch (token) { ++ case Opt_remote_iplist: ++ return REMOUNTREMOTEADDR; ++ case Opt_local_iplist: ++ return REMOUNTLOCALADDR; ++ case Opt_remote_dnslist: ++ return REMOTEDNSNAME; ++ } ++ return INVALID_OPTION; ++} ++#endif ++ + /* + * Register the NFS filesystems + */ +@@ -758,6 +786,9 @@ int nfs_show_options(struct seq_file *m, struct dentry *root) + seq_printf(m, ",addr=%s", + rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient, + RPC_DISPLAY_ADDR)); ++ ++ nfs_multipath_show_client_info(m, nfss); ++ + rcu_read_unlock(); + + return 0; +@@ -853,6 +884,8 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) + seq_puts(m, root->d_sb->s_flags & SB_NODIRATIME ? ",nodiratime" : ""); + nfs_show_mount_options(m, nfss, 1); + ++ nfs_multipath_show_client_info(m, nfss); ++ + seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); + + show_implementation_id(m, nfss); +@@ -977,6 +1010,7 @@ static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data) + kfree(data->nfs_server.export_path); + kfree(data->nfs_server.hostname); + kfree(data->fscache_uniq); ++ enfs_free_mount_options(data); + security_free_mnt_opts(&data->lsm_opts); + kfree(data); + } +@@ -1641,7 +1675,34 @@ static int nfs_parse_mount_options(char *raw, + return 0; + }; + break; +- ++#if IS_ENABLED(CONFIG_ENFS) ++ case Opt_remote_iplist: ++ case Opt_local_iplist: ++ case Opt_remote_dnslist: ++ string = match_strdup(args); ++ if (string == NULL) ++ goto out_nomem; ++ rc = enfs_parse_mount_options(getNfsMultiPathOpt(token), ++ string, mnt); ++ kfree(string); ++ switch (rc) { ++ case 0: ++ break; ++ case -ENOMEM: ++ goto out_nomem; ++ case -ENOSPC: ++ goto out_limit; ++ case -EINVAL: ++ goto out_invalid_address; ++ case -ENOTSUPP: ++ goto out_invalid_address; ++ case -EOPNOTSUPP: ++ goto out_invalid_address; ++ } ++ break; ++ case Opt_enfs_info: ++ break; ++#endif + /* + * Special options + */ +@@ -1720,6 +1781,11 @@ static int nfs_parse_mount_options(char *raw, + free_secdata(secdata); + printk(KERN_INFO "NFS: security options invalid: %d\n", rc); + return 0; ++#if IS_ENABLED(CONFIG_ENFS) ++out_limit: ++ dprintk("NFS: param is more than supported limit: %d\n", rc); ++ return 0; ++#endif + } + + /* +@@ -2335,6 +2401,14 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) + if (!nfs_parse_mount_options((char *)options, data)) + goto out; + ++#if IS_ENABLED(CONFIG_ENFS) ++ if (data->enfs_option) { ++ error = nfs_remount_iplist(nfss->nfs_client, data->enfs_option); ++ if (error) ++ goto out; ++ } ++#endif ++ + /* + * noac is a special case. It implies -o sync, but that's not + * necessarily reflected in the mtab options. do_remount_sb +@@ -2347,6 +2421,11 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) + /* compare new mount options with old ones */ + error = nfs_compare_remount_data(nfss, data); + out: ++#if IS_ENABLED(CONFIG_ENFS) ++ /* release remount option member */ ++ if (data->enfs_option) ++ enfs_free_mount_options(data); ++#endif + nfs_free_parsed_mount_data(data); + return error; + } +diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h +index 7023ae64e3d7..2c19678afe8d 100644 +--- a/include/linux/nfs_fs_sb.h ++++ b/include/linux/nfs_fs_sb.h +@@ -123,6 +123,11 @@ struct nfs_client { + + struct net *cl_net; + struct list_head pending_cb_stateids; ++ ++#if IS_ENABLED(CONFIG_ENFS) ++ /* multi path private structure (struct multipath_client_info *) */ ++ void *cl_multipath_data; ++#endif + }; + + /* diff --git a/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch new file mode 100644 index 0000000..540a2ce --- /dev/null +++ b/0002-sunrpc_add_api_to_support_enfs_registe_and_create_multipath_then_dispatch_IO.patch @@ -0,0 +1,805 @@ +diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h +index 8aa865bce4f6..89178f78de8c 100644 +--- a/include/linux/sunrpc/clnt.h ++++ b/include/linux/sunrpc/clnt.h +@@ -70,6 +70,10 @@ struct rpc_clnt { + struct dentry *cl_debugfs; /* debugfs directory */ + #endif + struct rpc_xprt_iter cl_xpi; ++ ++#if IS_ENABLED(CONFIG_ENFS) ++ bool cl_enfs; ++#endif + }; + + /* +@@ -124,6 +128,9 @@ struct rpc_create_args { + unsigned long flags; + char *client_name; + struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ ++#if IS_ENABLED(CONFIG_ENFS) ++ void *multipath_option; ++#endif + }; + + struct rpc_add_xprt_test { +@@ -221,6 +228,12 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, + const struct sockaddr *sap); + void rpc_cleanup_clids(void); + ++#if IS_ENABLED(CONFIG_ENFS) ++int ++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, ++ const struct rpc_call_ops *ops, void *data, int flags); ++#endif /* CONFIG_ENFS */ ++ + static inline int rpc_reply_expected(struct rpc_task *task) + { + return (task->tk_msg.rpc_proc != NULL) && +diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h +index ad2e243f3f03..124f5a0faf3e 100644 +--- a/include/linux/sunrpc/sched.h ++++ b/include/linux/sunrpc/sched.h +@@ -90,6 +90,9 @@ struct rpc_task { + tk_garb_retry : 2, + tk_cred_retry : 2, + tk_rebind_retry : 2; ++#if IS_ENABLED(CONFIG_ENFS) ++ unsigned long tk_major_timeo; /* major timeout ticks */ ++#endif + }; + + typedef void (*rpc_action)(struct rpc_task *); +@@ -118,6 +121,9 @@ struct rpc_task_setup { + */ + #define RPC_TASK_ASYNC 0x0001 /* is an async task */ + #define RPC_TASK_SWAPPER 0x0002 /* is swapping in/out */ ++#if IS_ENABLED(CONFIG_ENFS) ++#define RPC_TASK_FIXED 0x0004 /* detect xprt status task */ ++#endif + #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ + #define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ + #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ +@@ -257,6 +263,9 @@ void rpc_destroy_mempool(void); + extern struct workqueue_struct *rpciod_workqueue; + extern struct workqueue_struct *xprtiod_workqueue; + void rpc_prepare_task(struct rpc_task *task); ++#if IS_ENABLED(CONFIG_ENFS) ++void rpc_init_task_retry_counters(struct rpc_task *task); ++#endif + + static inline int rpc_wait_for_completion_task(struct rpc_task *task) + { +diff --git a/include/linux/sunrpc/sunrpc_enfs_adapter.h b/include/linux/sunrpc/sunrpc_enfs_adapter.h +new file mode 100644 +index 000000000000..28abedcf5cf6 +--- /dev/null ++++ b/include/linux/sunrpc/sunrpc_enfs_adapter.h +@@ -0,0 +1,128 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* Client-side SUNRPC ENFS adapter header. ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _SUNRPC_ENFS_ADAPTER_H_ ++#define _SUNRPC_ENFS_ADAPTER_H_ ++#include <linux/sunrpc/clnt.h> ++ ++#if IS_ENABLED(CONFIG_ENFS) ++ ++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) ++{ ++ xps->xps_nactive--; ++} ++ ++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) ++{ ++ xps->xps_nactive--; ++} ++ ++struct rpc_xprt *rpc_task_get_xprt ++(struct rpc_clnt *clnt, struct rpc_xprt *xprt); ++ ++struct rpc_multipath_ops { ++ struct module *owner; ++ void (*create_clnt)(struct rpc_create_args *args, ++ struct rpc_clnt *clnt); ++ void (*releas_clnt)(struct rpc_clnt *clnt); ++ void (*create_xprt)(struct rpc_xprt *xprt); ++ void (*destroy_xprt)(struct rpc_xprt *xprt); ++ void (*xprt_iostat)(struct rpc_task *task); ++ void (*failover_handle)(struct rpc_task *task); ++ bool (*task_need_call_start_again)(struct rpc_task *task); ++ void (*adjust_task_timeout)(struct rpc_task *task, void *condition); ++ void (*init_task_req)(struct rpc_task *task, struct rpc_rqst *req); ++ bool (*prepare_transmit)(struct rpc_task *task); ++}; ++ ++extern struct rpc_multipath_ops __rcu *multipath_ops; ++void rpc_init_task_retry_counters(struct rpc_task *task); ++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops); ++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops); ++struct rpc_multipath_ops *rpc_multipath_ops_get(void); ++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops); ++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); ++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, ++ struct rpc_clnt *clnt); ++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt); ++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt); ++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt); ++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task); ++void rpc_multipath_ops_failover_handle(struct rpc_task *task); ++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task); ++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, ++ void *condition); ++void rpc_multipath_ops_init_task_req(struct rpc_task *task, ++ struct rpc_rqst *req); ++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task); ++ ++#else ++static inline struct rpc_xprt *rpc_task_get_xprt(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt) ++{ ++ return NULL; ++} ++ ++static inline void rpc_task_release_xprt(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt) ++{ ++} ++ ++static inline void rpc_xps_nactive_add_one(struct rpc_xprt_switch *xps) ++{ ++} ++ ++static inline void rpc_xps_nactive_sub_one(struct rpc_xprt_switch *xps) ++{ ++} ++ ++static inline void rpc_multipath_ops_create_clnt ++(struct rpc_create_args *args, struct rpc_clnt *clnt) ++{ ++} ++ ++static inline void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) ++{ ++} ++ ++static inline bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) ++{ ++ return false; ++} ++ ++static inline void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) ++{ ++} ++ ++static inline void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) ++{ ++} ++ ++static inline void rpc_multipath_ops_failover_handle(struct rpc_task *task) ++{ ++} ++ ++static inline ++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) ++{ ++ return false; ++} ++ ++static inline void ++rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, void *condition) ++{ ++} ++ ++static inline void ++rpc_multipath_ops_init_task_req(struct rpc_task *task, struct rpc_rqst *req) ++{ ++} ++ ++static inline bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) ++{ ++ return false; ++} ++ ++#endif ++#endif // _SUNRPC_ENFS_ADAPTER_H_ +diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h +index ccfacca1eba9..2e47b3577947 100644 +--- a/include/linux/sunrpc/xprt.h ++++ b/include/linux/sunrpc/xprt.h +@@ -279,6 +279,10 @@ struct rpc_xprt { + atomic_t inject_disconnect; + #endif + struct rcu_head rcu; ++#if IS_ENABLED(CONFIG_ENFS) ++ atomic_long_t queuelen; ++ void *multipath_context; ++#endif + }; + + #if defined(CONFIG_SUNRPC_BACKCHANNEL) +diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h +index af1257c030d2..d54e4dbbbf34 100644 +--- a/include/linux/sunrpc/xprtmultipath.h ++++ b/include/linux/sunrpc/xprtmultipath.h +@@ -22,6 +22,10 @@ struct rpc_xprt_switch { + const struct rpc_xprt_iter_ops *xps_iter_ops; + + struct rcu_head xps_rcu; ++#if IS_ENABLED(CONFIG_ENFS) ++ unsigned int xps_nactive; ++ atomic_long_t xps_queuelen; ++#endif + }; + + struct rpc_xprt_iter { +@@ -69,4 +73,8 @@ extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); + + extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap); ++#if IS_ENABLED(CONFIG_ENFS) ++extern void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++ struct rpc_xprt *xprt); ++#endif + #endif +diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c +index 0fc540b0d183..d7ffee637148 100644 +--- a/net/sunrpc/clnt.c ++++ b/net/sunrpc/clnt.c +@@ -37,6 +37,7 @@ + #include <linux/sunrpc/rpc_pipe_fs.h> + #include <linux/sunrpc/metrics.h> + #include <linux/sunrpc/bc_xprt.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + #include <trace/events/sunrpc.h> + + #include "sunrpc.h" +@@ -490,6 +491,8 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, + } + } + ++ rpc_multipath_ops_create_clnt(args, clnt); ++ + clnt->cl_softrtry = 1; + if (args->flags & RPC_CLNT_CREATE_HARDRTRY) + clnt->cl_softrtry = 0; +@@ -869,6 +872,8 @@ void rpc_shutdown_client(struct rpc_clnt *clnt) + list_empty(&clnt->cl_tasks), 1*HZ); + } + ++ rpc_multipath_ops_releas_clnt(clnt); ++ + rpc_release_client(clnt); + } + EXPORT_SYMBOL_GPL(rpc_shutdown_client); +@@ -981,7 +986,13 @@ void rpc_task_release_transport(struct rpc_task *task) + + if (xprt) { + task->tk_xprt = NULL; +- xprt_put(xprt); ++#if IS_ENABLED(CONFIG_ENFS) ++ if (task->tk_client) { ++ rpc_task_release_xprt(task->tk_client, xprt); ++ return; ++ } ++#endif ++ xprt_put(xprt); + } + } + EXPORT_SYMBOL_GPL(rpc_task_release_transport); +@@ -990,6 +1001,10 @@ void rpc_task_release_client(struct rpc_task *task) + { + struct rpc_clnt *clnt = task->tk_client; + ++#if IS_ENABLED(CONFIG_ENFS) ++ rpc_task_release_transport(task); ++#endif ++ + if (clnt != NULL) { + /* Remove from client task list */ + spin_lock(&clnt->cl_lock); +@@ -999,14 +1014,29 @@ void rpc_task_release_client(struct rpc_task *task) + + rpc_release_client(clnt); + } ++#if IS_ENABLED(CONFIG_ENFS) ++#else + rpc_task_release_transport(task); ++#endif + } + ++#if IS_ENABLED(CONFIG_ENFS) ++static struct rpc_xprt * ++rpc_task_get_next_xprt(struct rpc_clnt *clnt) ++{ ++ return rpc_task_get_xprt(clnt, xprt_iter_get_next(&clnt->cl_xpi)); ++} ++#endif ++ + static + void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) + { + if (!task->tk_xprt) ++#if IS_ENABLED(CONFIG_ENFS) ++ task->tk_xprt = rpc_task_get_next_xprt(clnt); ++#else + task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); ++#endif + } + + static +@@ -1597,6 +1627,14 @@ call_reserveresult(struct rpc_task *task) + return; + case -EIO: /* probably a shutdown */ + break; ++#if IS_ENABLED(CONFIG_ENFS) ++ case -ETIMEDOUT: /* woken up; restart */ ++ if (rpc_multipath_ops_task_need_call_start_again(task)) { ++ rpc_task_release_transport(task); ++ task->tk_action = call_start; ++ return; ++ } ++#endif + default: + printk(KERN_ERR "%s: unrecognized error %d, exiting\n", + __func__, status); +@@ -1962,6 +2000,10 @@ call_transmit(struct rpc_task *task) + return; + if (!xprt_prepare_transmit(task)) + return; ++ ++ if (rpc_multipath_ops_prepare_transmit(task)) ++ return; ++ + task->tk_action = call_transmit_status; + /* Encode here so that rpcsec_gss can use correct sequence number. */ + if (rpc_task_need_encode(task)) { +@@ -2277,6 +2319,9 @@ call_timeout(struct rpc_task *task) + + retry: + task->tk_action = call_bind; ++#if IS_ENABLED(CONFIG_ENFS) ++ rpc_multipath_ops_failover_handle(task); ++#endif + task->tk_status = 0; + } + +@@ -2961,3 +3006,30 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) + } + EXPORT_SYMBOL_GPL(rpc_clnt_swap_deactivate); + #endif /* CONFIG_SUNRPC_SWAP */ ++ ++#if IS_ENABLED(CONFIG_ENFS) ++/* rpc_clnt_test_xprt - Test and add a new transport to a rpc_clnt ++ * @clnt: pointer to struct rpc_clnt ++ * @xprt: pointer struct rpc_xprt ++ * @ops: async operation ++ */ ++int ++rpc_clnt_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, ++ const struct rpc_call_ops *ops, void *data, int flags) ++{ ++ struct rpc_cred *cred; ++ struct rpc_task *task; ++ ++ cred = authnull_ops.lookup_cred(NULL, NULL, 0); ++ task = rpc_call_null_helper(clnt, xprt, cred, ++ RPC_TASK_SOFT | RPC_TASK_SOFTCONN | flags, ++ ops, data); ++ put_rpccred(cred); ++ if (IS_ERR(task)) ++ return PTR_ERR(task); ++ ++ rpc_put_task(task); ++ return 1; ++} ++EXPORT_SYMBOL_GPL(rpc_clnt_test_xprt); ++#endif +diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c +index a873c92a4898..2254fea0e863 100644 +--- a/net/sunrpc/sched.c ++++ b/net/sunrpc/sched.c +@@ -20,7 +20,7 @@ + #include <linux/mutex.h> + #include <linux/freezer.h> + +-#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + + #include "sunrpc.h" + +@@ -962,7 +962,12 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta + /* Initialize workqueue for async tasks */ + task->tk_workqueue = task_setup_data->workqueue; + ++#if IS_ENABLED(CONFIG_ENFS) ++ task->tk_xprt = rpc_task_get_xprt(task_setup_data->rpc_client, ++ xprt_get(task_setup_data->rpc_xprt)); ++#else + task->tk_xprt = xprt_get(task_setup_data->rpc_xprt); ++#endif + + if (task->tk_ops->rpc_call_prepare != NULL) + task->tk_action = rpc_prepare_task; +diff --git a/net/sunrpc/sunrpc_enfs_adapter.c b/net/sunrpc/sunrpc_enfs_adapter.c +new file mode 100644 +index 000000000000..c1543545c6de +--- /dev/null ++++ b/net/sunrpc/sunrpc_enfs_adapter.c +@@ -0,0 +1,214 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* Client-side SUNRPC ENFS adapter header. ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> ++ ++struct rpc_multipath_ops __rcu *multipath_ops; ++ ++void rpc_init_task_retry_counters(struct rpc_task *task) ++{ ++ /* Initialize retry counters */ ++ task->tk_garb_retry = 2; ++ task->tk_cred_retry = 2; ++ task->tk_rebind_retry = 2; ++} ++EXPORT_SYMBOL_GPL(rpc_init_task_retry_counters); ++ ++struct rpc_xprt * ++rpc_task_get_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) ++{ ++ struct rpc_xprt_switch *xps; ++ ++ if (!xprt) ++ return NULL; ++ rcu_read_lock(); ++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ++ atomic_long_inc(&xps->xps_queuelen); ++ rcu_read_unlock(); ++ atomic_long_inc(&xprt->queuelen); ++ ++ return xprt; ++} ++ ++int rpc_multipath_ops_register(struct rpc_multipath_ops *ops) ++{ ++ struct rpc_multipath_ops *old; ++ ++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, NULL, ops); ++ if (!old || old == ops) ++ return 0; ++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_register); ++ ++int rpc_multipath_ops_unregister(struct rpc_multipath_ops *ops) ++{ ++ struct rpc_multipath_ops *old; ++ ++ old = cmpxchg((struct rpc_multipath_ops **)&multipath_ops, ops, NULL); ++ if (!old || old == ops) ++ return 0; ++ pr_err("regist rpc_multipath ops %p fail. old %p\n", ops, old); ++ return -EPERM; ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_unregister); ++ ++struct rpc_multipath_ops *rpc_multipath_ops_get(void) ++{ ++ struct rpc_multipath_ops *ops; ++ ++ rcu_read_lock(); ++ ops = rcu_dereference(multipath_ops); ++ if (!ops) { ++ rcu_read_unlock(); ++ return NULL; ++ } ++ if (!try_module_get(ops->owner)) ++ ops = NULL; ++ rcu_read_unlock(); ++ return ops; ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_get); ++ ++void rpc_multipath_ops_put(struct rpc_multipath_ops *ops) ++{ ++ if (ops) ++ module_put(ops->owner); ++} ++EXPORT_SYMBOL_GPL(rpc_multipath_ops_put); ++ ++void rpc_task_release_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) ++{ ++ struct rpc_xprt_switch *xps; ++ ++ atomic_long_dec(&xprt->queuelen); ++ rcu_read_lock(); ++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ++ atomic_long_dec(&xps->xps_queuelen); ++ rcu_read_unlock(); ++ ++ xprt_put(xprt); ++} ++ ++void rpc_multipath_ops_create_clnt(struct rpc_create_args *args, ++ struct rpc_clnt *clnt) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ if (args->multipath_option) { ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->create_clnt) ++ mops->create_clnt(args, clnt); ++ rpc_multipath_ops_put(mops); ++ } ++} ++ ++void rpc_multipath_ops_releas_clnt(struct rpc_clnt *clnt) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->releas_clnt) ++ mops->releas_clnt(clnt); ++ ++ rpc_multipath_ops_put(mops); ++} ++ ++bool rpc_multipath_ops_create_xprt(struct rpc_xprt *xprt) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->create_xprt) { ++ mops->create_xprt(xprt); ++ if (!xprt->multipath_context) { ++ rpc_multipath_ops_put(mops); ++ return true; ++ } ++ } ++ rpc_multipath_ops_put(mops); ++ return false; ++} ++ ++void rpc_multipath_ops_destroy_xprt(struct rpc_xprt *xprt) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ if (xprt->multipath_context) { ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->destroy_xprt) ++ mops->destroy_xprt(xprt); ++ rpc_multipath_ops_put(mops); ++ } ++} ++ ++void rpc_multipath_ops_xprt_iostat(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mops; ++ ++ mops = rpc_multipath_ops_get(); ++ if (task->tk_client && mops && mops->xprt_iostat) ++ mops->xprt_iostat(task); ++ rpc_multipath_ops_put(mops); ++} ++ ++void rpc_multipath_ops_failover_handle(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mpath_ops = NULL; ++ ++ mpath_ops = rpc_multipath_ops_get(); ++ if (mpath_ops && mpath_ops->failover_handle) ++ mpath_ops->failover_handle(task); ++ rpc_multipath_ops_put(mpath_ops); ++} ++ ++bool rpc_multipath_ops_task_need_call_start_again(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mpath_ops = NULL; ++ bool ret = false; ++ ++ mpath_ops = rpc_multipath_ops_get(); ++ if (mpath_ops && mpath_ops->task_need_call_start_again) ++ ret = mpath_ops->task_need_call_start_again(task); ++ rpc_multipath_ops_put(mpath_ops); ++ return ret; ++} ++ ++void rpc_multipath_ops_adjust_task_timeout(struct rpc_task *task, ++ void *condition) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->adjust_task_timeout) ++ mops->adjust_task_timeout(task, NULL); ++ rpc_multipath_ops_put(mops); ++} ++ ++void rpc_multipath_ops_init_task_req(struct rpc_task *task, ++ struct rpc_rqst *req) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->init_task_req) ++ mops->init_task_req(task, req); ++ rpc_multipath_ops_put(mops); ++} ++ ++bool rpc_multipath_ops_prepare_transmit(struct rpc_task *task) ++{ ++ struct rpc_multipath_ops *mops = NULL; ++ ++ mops = rpc_multipath_ops_get(); ++ if (mops && mops->prepare_transmit) { ++ if (!(mops->prepare_transmit(task))) { ++ rpc_multipath_ops_put(mops); ++ return true; ++ } ++ } ++ rpc_multipath_ops_put(mops); ++ return false; ++} +diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c +index c912bf20faa2..c2b63b3d5217 100644 +--- a/net/sunrpc/xprt.c ++++ b/net/sunrpc/xprt.c +@@ -48,6 +48,7 @@ + #include <linux/sunrpc/clnt.h> + #include <linux/sunrpc/metrics.h> + #include <linux/sunrpc/bc_xprt.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + #include <linux/rcupdate.h> + + #include <trace/events/sunrpc.h> +@@ -259,6 +260,9 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) + dprintk("RPC: %5u failed to lock transport %p\n", + task->tk_pid, xprt); + task->tk_timeout = 0; ++ ++ rpc_multipath_ops_adjust_task_timeout(task, NULL); ++ + task->tk_status = -EAGAIN; + if (req == NULL) + priority = RPC_PRIORITY_LOW; +@@ -560,6 +564,9 @@ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action) + struct rpc_xprt *xprt = req->rq_xprt; + + task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0; ++ ++ rpc_multipath_ops_adjust_task_timeout(task, NULL); ++ + rpc_sleep_on(&xprt->pending, task, action); + } + EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space); +@@ -1347,6 +1354,9 @@ xprt_request_init(struct rpc_task *task) + req->rq_rcv_buf.buflen = 0; + req->rq_release_snd_buf = NULL; + xprt_reset_majortimeo(req); ++ ++ rpc_multipath_ops_init_task_req(task, req); ++ + dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, + req, ntohl(req->rq_xid)); + } +@@ -1427,6 +1437,9 @@ void xprt_release(struct rpc_task *task) + task->tk_ops->rpc_count_stats(task, task->tk_calldata); + else if (task->tk_client) + rpc_count_iostats(task, task->tk_client->cl_metrics); ++ ++ rpc_multipath_ops_xprt_iostat(task); ++ + spin_lock(&xprt->recv_lock); + if (!list_empty(&req->rq_list)) { + list_del_init(&req->rq_list); +@@ -1455,6 +1468,7 @@ void xprt_release(struct rpc_task *task) + else + xprt_free_bc_request(req); + } ++EXPORT_SYMBOL_GPL(xprt_release); + + static void xprt_init(struct rpc_xprt *xprt, struct net *net) + { +@@ -1528,6 +1542,10 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) + return ERR_PTR(-ENOMEM); + } + ++if (rpc_multipath_ops_create_xprt(xprt)) { ++ xprt_destroy(xprt); ++ return ERR_PTR(-ENOMEM); ++} + rpc_xprt_debugfs_register(xprt); + + dprintk("RPC: created transport %p with %u slots\n", xprt, +@@ -1547,6 +1565,9 @@ static void xprt_destroy_cb(struct work_struct *work) + rpc_destroy_wait_queue(&xprt->sending); + rpc_destroy_wait_queue(&xprt->backlog); + kfree(xprt->servername); ++ ++ rpc_multipath_ops_destroy_xprt(xprt); ++ + /* + * Tear down transport state and free the rpc_xprt + */ +diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c +index 6ebaa58b4eff..6202a0be1327 100644 +--- a/net/sunrpc/xprtmultipath.c ++++ b/net/sunrpc/xprtmultipath.c +@@ -18,6 +18,7 @@ + #include <linux/sunrpc/xprt.h> + #include <linux/sunrpc/addr.h> + #include <linux/sunrpc/xprtmultipath.h> ++#include <linux/sunrpc/sunrpc_enfs_adapter.h> + + typedef struct rpc_xprt *(*xprt_switch_find_xprt_t)(struct list_head *head, + const struct rpc_xprt *cur); +@@ -26,8 +27,8 @@ static const struct rpc_xprt_iter_ops rpc_xprt_iter_singular; + static const struct rpc_xprt_iter_ops rpc_xprt_iter_roundrobin; + static const struct rpc_xprt_iter_ops rpc_xprt_iter_listall; + +-static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, +- struct rpc_xprt *xprt) ++void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, ++ struct rpc_xprt *xprt) + { + if (unlikely(xprt_get(xprt) == NULL)) + return; +@@ -36,7 +37,9 @@ static void xprt_switch_add_xprt_locked(struct rpc_xprt_switch *xps, + if (xps->xps_nxprts == 0) + xps->xps_net = xprt->xprt_net; + xps->xps_nxprts++; ++ rpc_xps_nactive_add_one(xps); + } ++EXPORT_SYMBOL(xprt_switch_add_xprt_locked); + + /** + * rpc_xprt_switch_add_xprt - Add a new rpc_xprt to an rpc_xprt_switch +@@ -63,6 +66,7 @@ static void xprt_switch_remove_xprt_locked(struct rpc_xprt_switch *xps, + if (unlikely(xprt == NULL)) + return; + xps->xps_nxprts--; ++ rpc_xps_nactive_sub_one(xps); + if (xps->xps_nxprts == 0) + xps->xps_net = NULL; + smp_wmb(); +@@ -84,7 +88,7 @@ void rpc_xprt_switch_remove_xprt(struct rpc_xprt_switch *xps, + spin_unlock(&xps->xps_lock); + xprt_put(xprt); + } +- ++EXPORT_SYMBOL(rpc_xprt_switch_remove_xprt); + /** + * xprt_switch_alloc - Allocate a new struct rpc_xprt_switch + * @xprt: pointer to struct rpc_xprt +@@ -102,7 +106,13 @@ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, + if (xps != NULL) { + spin_lock_init(&xps->xps_lock); + kref_init(&xps->xps_kref); ++#if IS_ENABLED(CONFIG_ENFS) ++ xps->xps_nxprts = 0; ++ xps->xps_nactive = 0; ++ atomic_long_set(&xps->xps_queuelen, 0); ++#else + xps->xps_nxprts = 0; ++#endif + INIT_LIST_HEAD(&xps->xps_xprt_list); + xps->xps_iter_ops = &rpc_xprt_iter_singular; + xprt_switch_add_xprt_locked(xps, xprt); +@@ -148,6 +158,7 @@ struct rpc_xprt_switch *xprt_switch_get(struct rpc_xprt_switch *xps) + return xps; + return NULL; + } ++EXPORT_SYMBOL(xprt_switch_get); + + /** + * xprt_switch_put - Release a reference to a rpc_xprt_switch +@@ -160,6 +171,7 @@ void xprt_switch_put(struct rpc_xprt_switch *xps) + if (xps != NULL) + kref_put(&xps->xps_kref, xprt_switch_free); + } ++EXPORT_SYMBOL(xprt_switch_put); + + /** + * rpc_xprt_switch_set_roundrobin - Set a round-robin policy on rpc_xprt_switch diff --git a/0003-add_enfs_module_for_nfs_mount_option.patch b/0003-add_enfs_module_for_nfs_mount_option.patch new file mode 100644 index 0000000..70753b5 --- /dev/null +++ b/0003-add_enfs_module_for_nfs_mount_option.patch @@ -0,0 +1,1209 @@ +diff --git a/fs/nfs/enfs/Makefile b/fs/nfs/enfs/Makefile +new file mode 100644 +index 000000000000..6e83eb23c668 +--- /dev/null ++++ b/fs/nfs/enfs/Makefile +@@ -0,0 +1,18 @@ ++obj-m += enfs.o ++ ++#EXTRA_CFLAGS += -I$(PWD)/.. ++ ++enfs-y := enfs_init.o ++enfs-y += enfs_config.o ++enfs-y += mgmt_init.o ++enfs-y += enfs_multipath_client.o ++enfs-y += enfs_multipath_parse.o ++enfs-y += failover_path.o ++enfs-y += failover_time.o ++enfs-y += enfs_roundrobin.o ++enfs-y += enfs_multipath.o ++enfs-y += enfs_path.o ++enfs-y += enfs_proc.o ++enfs-y += enfs_remount.o ++enfs-y += pm_ping.o ++enfs-y += pm_state.o +diff --git a/fs/nfs/enfs/enfs.h b/fs/nfs/enfs/enfs.h +new file mode 100644 +index 000000000000..be3d95220088 +--- /dev/null ++++ b/fs/nfs/enfs/enfs.h +@@ -0,0 +1,62 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS multipath adapt header. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++ ++#ifndef _ENFS_H_ ++#define _ENFS_H_ ++#include <linux/atomic.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs3.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include "../enfs_adapter.h" ++ ++#define IP_ADDRESS_LEN_MAX 64 ++#define MAX_IP_PAIR_PER_MOUNT 8 ++#define MAX_IP_INDEX (MAX_IP_PAIR_PER_MOUNT) ++#define MAX_SUPPORTED_LOCAL_IP_COUNT 8 ++#define MAX_SUPPORTED_REMOTE_IP_COUNT 32 ++#define MAX_DNS_NAME_LEN 512 ++#define MAX_DNS_SUPPORTED 2 ++#define EXTEND_CMD_MAX_BUF_LEN 65356 ++ ++ ++struct nfs_ip_list { ++ int count; ++ struct sockaddr_storage address[MAX_SUPPORTED_REMOTE_IP_COUNT]; ++ size_t addrlen[MAX_SUPPORTED_REMOTE_IP_COUNT]; ++}; ++ ++struct NFS_ROUTE_DNS_S { ++ char dnsname[MAX_DNS_NAME_LEN]; // valid only if dnsExist is true ++}; ++ ++struct NFS_ROUTE_DNS_INFO_S { ++ int dnsNameCount; // Count of DNS name in the list ++ // valid only if dnsExist is true ++ struct NFS_ROUTE_DNS_S routeRemoteDnsList[MAX_DNS_SUPPORTED]; ++}; ++ ++struct rpc_iostats; ++struct enfs_xprt_context { ++ struct sockaddr_storage srcaddr; ++ struct rpc_iostats *stats; ++ bool main; ++ atomic_t path_state; ++ atomic_t path_check_state; ++}; ++ ++static inline bool enfs_is_main_xprt(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = xprt->multipath_context; ++ ++ if (!ctx) ++ return false; ++ return ctx->main; ++} ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_init.c b/fs/nfs/enfs/enfs_init.c +new file mode 100644 +index 000000000000..4b55608191a7 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_init.c +@@ -0,0 +1,98 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/module.h> ++#include <linux/sunrpc/sched.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs3.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include "enfs.h" ++#include "enfs_multipath_parse.h" ++#include "enfs_multipath_client.h" ++#include "enfs_remount.h" ++#include "init.h" ++#include "enfs_log.h" ++#include "enfs_multipath.h" ++#include "mgmt_init.h" ++ ++struct enfs_adapter_ops enfs_adapter = { ++ .name = "enfs", ++ .owner = THIS_MODULE, ++ .parse_mount_options = nfs_multipath_parse_options, ++ .free_mount_options = nfs_multipath_free_options, ++ .client_info_init = nfs_multipath_client_info_init, ++ .client_info_free = nfs_multipath_client_info_free, ++ .client_info_match = nfs_multipath_client_info_match, ++ .client_info_show = nfs_multipath_client_info_show, ++ .remount_ip_list = enfs_remount_iplist, ++}; ++ ++int32_t enfs_init(void) ++{ ++ int err; ++ ++ err = enfs_multipath_init(); ++ if (err) { ++ enfs_log_error("init multipath failed.\n"); ++ goto out; ++ } ++ ++ err = mgmt_init(); ++ if (err != 0) { ++ enfs_log_error("init mgmt failed.\n"); ++ goto out_tp_exit; ++ } ++ ++ return 0; ++ ++out_tp_exit: ++ enfs_multipath_exit(); ++out: ++ return err; ++} ++ ++void enfs_fini(void) ++{ ++ mgmt_fini(); ++ ++ enfs_multipath_exit(); ++} ++ ++static int __init init_enfs(void) ++{ ++ int ret; ++ ++ ret = enfs_adapter_register(&enfs_adapter); ++ if (ret) { ++ pr_err("regist enfs_adapter fail. ret %d\n", ret); ++ return -1; ++ } ++ ++ ret = enfs_init(); ++ if (ret) { ++ enfs_adapter_unregister(&enfs_adapter); ++ return -1; ++ } ++ ++ return 0; ++} ++ ++static void __exit exit_enfs(void) ++{ ++ enfs_fini(); ++ enfs_adapter_unregister(&enfs_adapter); ++} ++ ++MODULE_LICENSE("GPL"); ++MODULE_AUTHOR("Huawei Tech. Co., Ltd."); ++MODULE_DESCRIPTION("Nfs client router"); ++MODULE_VERSION("1.0"); ++ ++module_init(init_enfs); ++module_exit(exit_enfs); +diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c +new file mode 100644 +index 000000000000..63c02898a42c +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.c +@@ -0,0 +1,340 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/proc_fs.h> ++#include <linux/seq_file.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/addr.h> ++#include "enfs_multipath_client.h" ++#include "enfs_multipath_parse.h" ++ ++int ++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, ++ const struct nfs_client_initdata *client_init_data) ++{ ++ struct multipath_mount_options *mount_options = ++ (struct multipath_mount_options *)client_init_data->enfs_option; ++ ++ if (mount_options->local_ip_list) { ++ client_info->local_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->local_ip_list) ++ return -ENOMEM; ++ ++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->remote_ip_list) { ++ ++ client_info->remote_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->remote_ip_list) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->remote_ip_list, ++ mount_options->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->pRemoteDnsInfo) { ++ client_info->pRemoteDnsInfo = ++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); ++ ++ if (!client_info->pRemoteDnsInfo) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ kfree(client_info->remote_ip_list); ++ client_info->remote_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->pRemoteDnsInfo, ++ mount_options->pRemoteDnsInfo, ++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); ++ } ++ return 0; ++} ++ ++void nfs_multipath_client_info_free_work(struct work_struct *work) ++{ ++ ++ struct multipath_client_info *clp_info; ++ ++ if (work == NULL) ++ return; ++ ++ clp_info = container_of(work, struct multipath_client_info, work); ++ ++ if (clp_info->local_ip_list != NULL) { ++ kfree(clp_info->local_ip_list); ++ clp_info->local_ip_list = NULL; ++ } ++ if (clp_info->remote_ip_list != NULL) { ++ kfree(clp_info->remote_ip_list); ++ clp_info->remote_ip_list = NULL; ++ } ++ kfree(clp_info); ++} ++ ++void nfs_multipath_client_info_free(void *data) ++{ ++ struct multipath_client_info *clp_info = ++ (struct multipath_client_info *)data; ++ ++ if (clp_info == NULL) ++ return; ++ pr_info("free client info %p.\n", clp_info); ++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); ++ schedule_work(&clp_info->work); ++} ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init) ++{ ++ int rc; ++ struct multipath_client_info *info; ++ struct multipath_client_info **enfs_info; ++ /* no multi path info, no need do multipath init */ ++ if (cl_init->enfs_option == NULL) ++ return 0; ++ enfs_info = (struct multipath_client_info **)data; ++ if (enfs_info == NULL) ++ return -EINVAL; ++ ++ if (*enfs_info == NULL) ++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), ++ GFP_KERNEL); ++ ++ if (*enfs_info == NULL) ++ return -ENOMEM; ++ ++ info = (struct multipath_client_info *)*enfs_info; ++ pr_info("init client info %p.\n", info); ++ rc = nfs_multipath_client_mount_info_init(info, cl_init); ++ if (rc) { ++ nfs_multipath_client_info_free((void *)info); ++ return rc; ++ } ++ return rc; ++} ++ ++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, ++ const struct nfs_ip_list *ip_list_dst) ++{ ++ int i; ++ int j; ++ bool is_find; ++ /* if both are equal or NULL, then return true. */ ++ if (ip_list_src == ip_list_dst) ++ return true; ++ ++ if ((ip_list_src == NULL || ip_list_dst == NULL)) ++ return false; ++ ++ if (ip_list_src->count != ip_list_dst->count) ++ return false; ++ ++ for (i = 0; i < ip_list_src->count; i++) { ++ is_find = false; ++ for (j = 0; j < ip_list_src->count; j++) { ++ if (rpc_cmp_addr_port( ++ (const struct sockaddr *) ++ &ip_list_src->address[i], ++ (const struct sockaddr *) ++ &ip_list_dst->address[j]) ++ ) { ++ is_find = true; ++ break; ++ } ++ } ++ if (is_find == false) ++ return false; ++ } ++ return true; ++} ++ ++int ++nfs_multipath_dns_list_info_match( ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) ++{ ++ int i; ++ ++ /* if both are equal or NULL, then return true. */ ++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) ++ return true; ++ ++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) ++ return false; ++ ++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) ++ return false; ++ ++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { ++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, ++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) ++ return false; ++ } ++ return true; ++} ++ ++int nfs_multipath_client_info_match(void *src, void *dst) ++{ ++ int ret = true; ++ ++ struct multipath_client_info *src_info; ++ struct multipath_mount_options *dst_info; ++ ++ src_info = (struct multipath_client_info *)src; ++ dst_info = (struct multipath_mount_options *)dst; ++ pr_info("try match client .\n"); ++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, ++ dst_info->local_ip_list); ++ if (ret == false) { ++ pr_err("local_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, ++ dst_info->remote_ip_list); ++ if (ret == false) { ++ pr_err("remote_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, ++ dst_info->pRemoteDnsInfo); ++ if (ret == false) { ++ pr_err("dns not match.\n"); ++ return ret; ++ } ++ pr_info("try match client ret %d.\n", ret); ++ return ret; ++} ++ ++void nfs_multipath_print_ip_info(struct seq_file *mount_option, ++ struct nfs_ip_list *ip_list, ++ const char *type) ++{ ++ char buf[IP_ADDRESS_LEN_MAX + 1]; ++ int len = 0; ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < ip_list->count; i++) { ++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], ++ buf, IP_ADDRESS_LEN_MAX); ++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) ++ buf[len] = '\0'; ++ ++ if (i == 0) ++ seq_printf(mount_option, "%s", buf); ++ else ++ seq_printf(mount_option, "~%s", buf); ++ dfprintk(MOUNT, ++ "NFS: show nfs mount option type:%s %s [%s]\n", ++ type, buf, __func__); ++ } ++} ++ ++void nfs_multipath_print_dns_info(struct seq_file *mount_option, ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, ++ const char *type) ++{ ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { ++ if (i == 0) ++ seq_printf(mount_option, ++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) ++ seq_printf(mount_option, ",%s]", ++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else ++ seq_printf(mount_option, ++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ } ++} ++ ++ ++static void multipath_print_sockaddr(struct seq_file *seq, ++ struct sockaddr *addr) ++{ ++ switch (addr->sa_family) { ++ case AF_INET: { ++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; ++ ++ seq_printf(seq, "%pI4", &sin->sin_addr); ++ return; ++ } ++ case AF_INET6: { ++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; ++ ++ seq_printf(seq, "%pI6", &sin6->sin6_addr); ++ return; ++ } ++ default: ++ break; ++ } ++ pr_err("unsupport family:%d\n", addr->sa_family); ++} ++ ++static void multipath_print_enfs_info(struct seq_file *seq, ++ struct nfs_server *server) ++{ ++ struct sockaddr_storage peeraddr; ++ struct rpc_clnt *next = server->client; ++ ++ rpc_peeraddr(server->client, ++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); ++ seq_puts(seq, ",enfs_info="); ++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); ++ ++ while (next->cl_parent) { ++ if (next == next->cl_parent) ++ break; ++ next = next->cl_parent; ++ } ++ seq_printf(seq, "_%u", next->cl_clid); ++} ++ ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) ++{ ++ struct nfs_server *server = data; ++ struct multipath_client_info *client_info = ++ server->nfs_client->cl_multipath_data; ++ ++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); ++ if ((client_info->remote_ip_list) && ++ (client_info->remote_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->remote_ip_list, ++ "remoteaddrs"); ++ ++ if ((client_info->local_ip_list) && ++ (client_info->local_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->local_ip_list, ++ "localaddrs"); ++ ++ if ((client_info->pRemoteDnsInfo) && ++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) ++ nfs_multipath_print_dns_info(mount_option, ++ client_info->pRemoteDnsInfo, ++ "remotednsname"); ++ ++ multipath_print_enfs_info(mount_option, server); ++} +diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h +new file mode 100644 +index 000000000000..208f7260690d +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.h +@@ -0,0 +1,26 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _ENFS_MULTIPATH_CLIENT_H_ ++#define _ENFS_MULTIPATH_CLIENT_H_ ++ ++#include "enfs.h" ++ ++struct multipath_client_info { ++ struct work_struct work; ++ struct nfs_ip_list *remote_ip_list; ++ struct nfs_ip_list *local_ip_list; ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; ++ s64 client_id; ++}; ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init); ++void nfs_multipath_client_info_free(void *data); ++int nfs_multipath_client_info_match(void *src, void *dst); ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_multipath_parse.c b/fs/nfs/enfs/enfs_multipath_parse.c +new file mode 100644 +index 000000000000..9c4c6c1880b6 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_parse.c +@@ -0,0 +1,601 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/parser.h> ++#include <linux/kern_levels.h> ++#include <linux/sunrpc/addr.h> ++#include "enfs_multipath_parse.h" ++#include "enfs_log.h" ++ ++#define NFSDBG_FACILITY NFSDBG_CLIENT ++ ++void nfs_multipath_parse_ip_ipv6_add(struct sockaddr_in6 *sin6, int add_num) ++{ ++ int i; ++ ++ pr_info("NFS: before %08x%08x%08x%08x add_num: %d[%s]\n", ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), ++ add_num, __func__); ++ for (i = 0; i < add_num; i++) { ++ sin6->sin6_addr.in6_u.u6_addr32[3] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[3] != 0) ++ continue; ++ ++ sin6->sin6_addr.in6_u.u6_addr32[2] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[2] != 0) ++ continue; ++ ++ sin6->sin6_addr.in6_u.u6_addr32[1] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[1] != 0) ++ continue; ++ ++ sin6->sin6_addr.in6_u.u6_addr32[0] = ++ htonl(ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]) + 1); ++ ++ if (sin6->sin6_addr.in6_u.u6_addr32[0] != 0) ++ continue; ++ } ++ ++ return; ++ ++} ++ ++static int nfs_multipath_parse_ip_range(struct net *net_ns, const char *cursor, ++ struct nfs_ip_list *ip_list, enum nfsmultipathoptions type) ++{ ++ struct sockaddr_storage addr; ++ struct sockaddr_storage tmp_addr; ++ int i; ++ size_t len; ++ int add_num = 1; ++ bool duplicate_flag = false; ++ bool is_complete = false; ++ struct sockaddr_in *sin4; ++ struct sockaddr_in6 *sin6; ++ ++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", ++ cursor, type, __func__); ++ len = rpc_pton(net_ns, cursor, strlen(cursor), ++ (struct sockaddr *)&addr, sizeof(addr)); ++ if (!len) ++ return -EINVAL; ++ ++ if (addr.ss_family != ip_list->address[ip_list->count - 1].ss_family) { ++ pr_info("NFS: %s parsing nfs mount option type: %d fail.\n", ++ __func__, type); ++ return -EINVAL; ++ } ++ ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &ip_list->address[ip_list->count - 1], ++ (const struct sockaddr *)&addr)) { ++ ++ pr_info("range ip is same ip.\n"); ++ return 0; ++ ++ } ++ ++ while (true) { ++ ++ tmp_addr = ip_list->address[ip_list->count - 1]; ++ ++ switch (addr.ss_family) { ++ case AF_INET: ++ sin4 = (struct sockaddr_in *)&tmp_addr; ++ ++ sin4->sin_addr.s_addr = ++ htonl(ntohl(sin4->sin_addr.s_addr) + add_num); ++ ++ pr_info("NFS: mount option ip%08x type: %d ipcont %d [%s]\n", ++ ntohl(sin4->sin_addr.s_addr), ++ type, ip_list->count, __func__); ++ break; ++ case AF_INET6: ++ sin6 = (struct sockaddr_in6 *)&tmp_addr; ++ nfs_multipath_parse_ip_ipv6_add(sin6, add_num); ++ pr_info("NFS: mount option ip %08x%08x%08x%08x type: %d ipcont %d [%s]\n", ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[0]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[1]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[2]), ++ ntohl(sin6->sin6_addr.in6_u.u6_addr32[3]), ++ type, ip_list->count, __func__); ++ break; ++ // return -EOPNOTSUPP; ++ default: ++ return -EOPNOTSUPP; ++ } ++ ++ if (rpc_cmp_addr((const struct sockaddr *)&tmp_addr, ++ (const struct sockaddr *)&addr)) { ++ is_complete = true; ++ } ++ // delete duplicate ip, continuosly repeat, skip it ++ for (i = 0; i < ip_list->count; i++) { ++ duplicate_flag = false; ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &ip_list->address[i], ++ (const struct sockaddr *)&tmp_addr)) { ++ add_num++; ++ duplicate_flag = true; ++ break; ++ } ++ } ++ ++ if (duplicate_flag == false) { ++ pr_info("this ip not duplicate;"); ++ add_num = 1; ++ // if not repeat but omit limit return false ++ if ((type == LOCALADDR && ++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || ++ (type == REMOTEADDR && ++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { ++ ++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", ++ __func__, type, ip_list->count, ++ type == LOCALADDR ? ++ MAX_SUPPORTED_LOCAL_IP_COUNT : ++ MAX_SUPPORTED_REMOTE_IP_COUNT); ++ ip_list->count = 0; ++ return -ENOSPC; ++ } ++ ip_list->address[ip_list->count] = tmp_addr; ++ ++ ip_list->addrlen[ip_list->count] = ++ ip_list->addrlen[ip_list->count - 1]; ++ ++ ip_list->count += 1; ++ } ++ if (is_complete == true) ++ break; ++ } ++ return 0; ++} ++ ++int nfs_multipath_parse_ip_list_inter(struct nfs_ip_list *ip_list, ++ struct net *net_ns, ++ char *cursor, enum nfsmultipathoptions type) ++{ ++ int i = 0; ++ struct sockaddr_storage addr; ++ struct sockaddr_storage swap; ++ int len; ++ ++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", ++ cursor, type, __func__); ++ ++ len = rpc_pton(net_ns, cursor, ++ strlen(cursor), ++ (struct sockaddr *)&addr, sizeof(addr)); ++ if (!len) ++ return -EINVAL; ++ ++ // check repeated ip ++ for (i = 0; i < ip_list->count; i++) { ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &ip_list->address[i], ++ (const struct sockaddr *)&addr)) { ++ ++ pr_info("NFS: mount option '%s' type:%d index %d same as before index %d [%s]\n", ++ cursor, type, ip_list->count, i, __func__); ++ // prevent this ip is beginning ++ // if repeated take it to the end of list ++ swap = ip_list->address[i]; ++ ++ ip_list->address[i] = ++ ip_list->address[ip_list->count-1]; ++ ++ ip_list->address[ip_list->count-1] = swap; ++ return 0; ++ } ++ } ++ // if not repeated, check exceed limit ++ if ((type == LOCALADDR && ++ ip_list->count >= MAX_SUPPORTED_LOCAL_IP_COUNT) || ++ (type == REMOTEADDR && ++ ip_list->count >= MAX_SUPPORTED_REMOTE_IP_COUNT)) { ++ ++ pr_info("[MULTIPATH:%s] iplist for type %d reached %d, more than supported limit %d\n", ++ __func__, type, ip_list->count, ++ type == LOCALADDR ? ++ MAX_SUPPORTED_LOCAL_IP_COUNT : ++ MAX_SUPPORTED_REMOTE_IP_COUNT); ++ ++ ip_list->count = 0; ++ return -ENOSPC; ++ } ++ ip_list->address[ip_list->count] = addr; ++ ip_list->addrlen[ip_list->count] = len; ++ ip_list->count++; ++ ++ return 0; ++} ++ ++char *nfs_multipath_parse_ip_list_get_cursor(char **buf_to_parse, bool *single) ++{ ++ char *cursor = NULL; ++ const char *single_sep = strchr(*buf_to_parse, '~'); ++ const char *range_sep = strchr(*buf_to_parse, '-'); ++ ++ *single = true; ++ if (range_sep) { ++ if (range_sep > single_sep) { // A-B or A~B-C ++ if (single_sep == NULL) { // A-B ++ cursor = strsep(buf_to_parse, "-"); ++ if (cursor) ++ *single = false; ++ } else// A~B-C ++ cursor = strsep(buf_to_parse, "~"); ++ } else { // A-B~C ++ cursor = strsep(buf_to_parse, "-"); ++ if (cursor) ++ *single = false; ++ } ++ } else { // A~B~C ++ cursor = strsep(buf_to_parse, "~"); ++ } ++ return cursor; ++} ++ ++bool nfs_multipath_parse_param_check(enum nfsmultipathoptions type, ++ struct multipath_mount_options *options) ++{ ++ if (type == REMOUNTREMOTEADDR && options->remote_ip_list->count != 0) { ++ memset(options->remote_ip_list, 0, sizeof(struct nfs_ip_list)); ++ return true; ++ } ++ if (type == REMOUNTLOCALADDR && options->local_ip_list->count != 0) { ++ memset(options->local_ip_list, 0, sizeof(struct nfs_ip_list)); ++ return true; ++ } ++ if ((type == REMOTEADDR || type == REMOTEDNSNAME) && ++ options->pRemoteDnsInfo->dnsNameCount != 0) { ++ ++ pr_info("[MULTIPATH:%s] parse for %d ,already have dns\n", ++ __func__, type); ++ return false; ++ } else if ((type == REMOTEADDR || type == REMOTEDNSNAME) && ++ options->remote_ip_list->count != 0) { ++ ++ pr_info("[MULTIPATH:%s] parse for %d ,already have iplist\n", ++ __func__, type); ++ return false; ++ } ++ return true; ++} ++ ++int nfs_multipath_parse_ip_list(char *buffer, struct net *net_ns, ++ struct multipath_mount_options *options, ++ enum nfsmultipathoptions type) ++{ ++ char *buf_to_parse = NULL; ++ bool prev_range = false; ++ int ret = 0; ++ char *cursor = NULL; ++ bool single = true; ++ struct nfs_ip_list *ip_list_tmp = NULL; ++ ++ if (!nfs_multipath_parse_param_check(type, options)) ++ return -ENOTSUPP; ++ ++ if (type == REMOUNTREMOTEADDR) ++ type = REMOTEADDR; ++ ++ if (type == REMOUNTLOCALADDR) ++ type = LOCALADDR; ++ ++ if (type == LOCALADDR) ++ ip_list_tmp = options->local_ip_list; ++ else ++ ip_list_tmp = options->remote_ip_list; ++ ++ pr_info("NFS: parsing nfs mount option '%s' type: %d[%s]\n", ++ buffer, type, __func__); ++ ++ buf_to_parse = buffer; ++ while (buf_to_parse != NULL) { ++ cursor = ++ nfs_multipath_parse_ip_list_get_cursor(&buf_to_parse, &single); ++ if (!cursor) ++ break; ++ ++ if (single == false && prev_range == true) { ++ pr_info("NFS: mount option type: %d fail. Multiple Range.[%s]\n", ++ type, __func__); ++ ++ ret = -EINVAL; ++ goto out; ++ } ++ ++ if (prev_range == false) { ++ ret = nfs_multipath_parse_ip_list_inter(ip_list_tmp, ++ net_ns, cursor, type); ++ if (ret) ++ goto out; ++ if (single == false) ++ prev_range = true; ++ } else { ++ ret = nfs_multipath_parse_ip_range(net_ns, cursor, ++ ip_list_tmp, type); ++ if (ret != 0) ++ goto out; ++ prev_range = false; ++ } ++ } ++ ++out: ++ if (ret) ++ memset(ip_list_tmp, 0, sizeof(struct nfs_ip_list)); ++ ++ return ret; ++} ++ ++int nfs_multipath_parse_dns_list(char *buffer, struct net *net_ns, ++ struct multipath_mount_options *options) ++{ ++ struct NFS_ROUTE_DNS_INFO_S *dns_name_list_tmp = NULL; ++ char *cursor = NULL; ++ char *bufToParse; ++ ++ if (!nfs_multipath_parse_param_check(REMOTEDNSNAME, options)) ++ return -ENOTSUPP; ++ ++ pr_info("[MULTIPATH:%s] buffer %s\n", __func__, buffer); ++ // freed in nfs_free_parsed_mount_data ++ dns_name_list_tmp = kmalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), ++ GFP_KERNEL); ++ if (!dns_name_list_tmp) ++ return -ENOMEM; ++ ++ dns_name_list_tmp->dnsNameCount = 0; ++ bufToParse = buffer; ++ while (bufToParse) { ++ if (dns_name_list_tmp->dnsNameCount >= MAX_DNS_SUPPORTED) { ++ pr_err("%s: dnsname for %s reached %d,more than supported limit %d\n", ++ __func__, cursor, ++ dns_name_list_tmp->dnsNameCount, ++ MAX_DNS_SUPPORTED); ++ dns_name_list_tmp->dnsNameCount = 0; ++ return -ENOSPC; ++ } ++ cursor = strsep(&bufToParse, "~"); ++ if (!cursor) ++ break; ++ ++ strcpy(dns_name_list_tmp->routeRemoteDnsList ++ [dns_name_list_tmp->dnsNameCount].dnsname, ++ cursor); ++ dns_name_list_tmp->dnsNameCount++; ++ } ++ if (dns_name_list_tmp->dnsNameCount == 0) ++ return -EINVAL; ++ options->pRemoteDnsInfo = dns_name_list_tmp; ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check_ipv4_valid(struct sockaddr_in *addr) ++{ ++ if (addr->sin_addr.s_addr == 0 || addr->sin_addr.s_addr == 0xffffffff) ++ return -EINVAL; ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check_ipv6_valid(struct sockaddr_in6 *addr) ++{ ++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0 && ++ addr->sin6_addr.in6_u.u6_addr32[1] == 0 && ++ addr->sin6_addr.in6_u.u6_addr32[2] == 0 && ++ addr->sin6_addr.in6_u.u6_addr32[3] == 0) ++ return -EINVAL; ++ ++ if (addr->sin6_addr.in6_u.u6_addr32[0] == 0xffffffff && ++ addr->sin6_addr.in6_u.u6_addr32[1] == 0xffffffff && ++ addr->sin6_addr.in6_u.u6_addr32[2] == 0xffffffff && ++ addr->sin6_addr.in6_u.u6_addr32[3] == 0xffffffff) ++ return -EINVAL; ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check_ip_valid(struct sockaddr_storage *address) ++{ ++ int rc = 0; ++ ++ if (address->ss_family == AF_INET) ++ rc = nfs_multipath_parse_options_check_ipv4_valid( ++ (struct sockaddr_in *)address); ++ else if (address->ss_family == AF_INET6) ++ rc = nfs_multipath_parse_options_check_ipv6_valid( ++ (struct sockaddr_in6 *)address); ++ else ++ rc = -EINVAL; ++ ++ return rc; ++} ++ ++int nfs_multipath_parse_options_check_valid( ++ struct multipath_mount_options *options) ++{ ++ int rc; ++ int i; ++ ++ if (options == NULL) ++ return 0; ++ ++ for (i = 0; i < options->local_ip_list->count; i++) { ++ rc = nfs_multipath_parse_options_check_ip_valid( ++ &options->local_ip_list->address[i]); ++ if (rc != 0) ++ return rc; ++ } ++ ++ for (i = 0; i < options->remote_ip_list->count; i++) { ++ rc = nfs_multipath_parse_options_check_ip_valid( ++ &options->remote_ip_list->address[i]); ++ if (rc != 0) ++ return rc; ++ } ++ ++ return 0; ++} ++int nfs_multipath_parse_options_check_duplicate( ++ struct multipath_mount_options *options) ++{ ++ int i; ++ int j; ++ ++ if (options == NULL || ++ options->local_ip_list->count == 0 || ++ options->remote_ip_list->count == 0) ++ ++ return 0; ++ ++ for (i = 0; i < options->local_ip_list->count; i++) { ++ for (j = 0; j < options->remote_ip_list->count; j++) { ++ if (rpc_cmp_addr((const struct sockaddr *) ++ &options->local_ip_list->address[i], ++ (const struct sockaddr *) ++ &options->remote_ip_list->address[j])) ++ return -ENOTSUPP; ++ } ++ } ++ return 0; ++} ++ ++int nfs_multipath_parse_options_check(struct multipath_mount_options *options) ++{ ++ int rc = 0; ++ ++ rc = nfs_multipath_parse_options_check_valid(options); ++ ++ if (rc != 0) { ++ pr_err("has invaild ip.\n"); ++ return rc; ++ } ++ ++ rc = nfs_multipath_parse_options_check_duplicate(options); ++ if (rc != 0) ++ return rc; ++ return rc; ++} ++ ++int nfs_multipath_alloc_options(void **enfs_option) ++{ ++ struct multipath_mount_options *options = NULL; ++ ++ options = kzalloc(sizeof(struct multipath_mount_options), GFP_KERNEL); ++ ++ if (options == NULL) ++ return -ENOMEM; ++ ++ options->local_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ if (options->local_ip_list == NULL) { ++ kfree(options); ++ return -ENOMEM; ++ } ++ ++ options->remote_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ if (options->remote_ip_list == NULL) { ++ kfree(options->local_ip_list); ++ kfree(options); ++ return -ENOMEM; ++ } ++ ++ options->pRemoteDnsInfo = kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), ++ GFP_KERNEL); ++ if (options->pRemoteDnsInfo == NULL) { ++ kfree(options->remote_ip_list); ++ kfree(options->local_ip_list); ++ kfree(options); ++ return -ENOMEM; ++ } ++ ++ *enfs_option = options; ++ return 0; ++} ++ ++int nfs_multipath_parse_options(enum nfsmultipathoptions type, ++ char *str, void **enfs_option, struct net *net_ns) ++{ ++ int rc; ++ struct multipath_mount_options *options = NULL; ++ ++ if ((str == NULL) || (enfs_option == NULL) || (net_ns == NULL)) ++ return -EINVAL; ++ ++ if (*enfs_option == NULL) { ++ rc = nfs_multipath_alloc_options(enfs_option); ++ if (rc != 0) { ++ enfs_log_error( ++ "alloc enfs_options failed! errno:%d\n", rc); ++ return rc; ++ } ++ } ++ ++ options = (struct multipath_mount_options *)*enfs_option; ++ ++ if (type == LOCALADDR || type == REMOUNTLOCALADDR || ++ type == REMOTEADDR || type == REMOUNTREMOTEADDR) { ++ rc = nfs_multipath_parse_ip_list(str, net_ns, options, type); ++ } else if (type == REMOTEDNSNAME) { ++ /* alloc and release need to modify */ ++ rc = nfs_multipath_parse_dns_list(str, net_ns, options); ++ } else { ++ rc = -EOPNOTSUPP; ++ } ++ ++ // after parsing cmd, need checking local and remote ++ // IP is same. if not means illegal cmd ++ if (rc == 0) ++ rc = nfs_multipath_parse_options_check_duplicate(options); ++ ++ if (rc == 0) ++ rc = nfs_multipath_parse_options_check(options); ++ ++ return rc; ++} ++ ++void nfs_multipath_free_options(void **enfs_option) ++{ ++ struct multipath_mount_options *options; ++ ++ if (enfs_option == NULL || *enfs_option == NULL) ++ return; ++ ++ options = (struct multipath_mount_options *)*enfs_option; ++ ++ if (options->remote_ip_list != NULL) { ++ kfree(options->remote_ip_list); ++ options->remote_ip_list = NULL; ++ } ++ ++ if (options->local_ip_list != NULL) { ++ kfree(options->local_ip_list); ++ options->local_ip_list = NULL; ++ } ++ ++ if (options->pRemoteDnsInfo != NULL) { ++ kfree(options->pRemoteDnsInfo); ++ options->pRemoteDnsInfo = NULL; ++ } ++ ++ kfree(options); ++ *enfs_option = NULL; ++} +diff --git a/fs/nfs/enfs/enfs_multipath_parse.h b/fs/nfs/enfs/enfs_multipath_parse.h +new file mode 100644 +index 000000000000..6f3e8703e3e2 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_parse.h +@@ -0,0 +1,22 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _ENFS_MULTIPATH_PARSE_H_ ++#define _ENFS_MULTIPATH_PARSE_H_ ++ ++#include "enfs.h" ++ ++struct multipath_mount_options { ++ struct nfs_ip_list *remote_ip_list; ++ struct nfs_ip_list *local_ip_list; ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; ++}; ++ ++int nfs_multipath_parse_options(enum nfsmultipathoptions type, ++ char *str, void **enfs_option, struct net *net_ns); ++void nfs_multipath_free_options(void **enfs_option); ++ ++#endif diff --git a/0004-add_enfs_module_for_sunrpc_multipatch.patch b/0004-add_enfs_module_for_sunrpc_multipatch.patch new file mode 100644 index 0000000..2c0fcc7 --- /dev/null +++ b/0004-add_enfs_module_for_sunrpc_multipatch.patch @@ -0,0 +1,1581 @@ +diff --git a/fs/nfs/enfs/enfs_multipath.h b/fs/nfs/enfs/enfs_multipath.h +new file mode 100644 +index 000000000000..e064c2929ced +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath.h +@@ -0,0 +1,24 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: enfs multipath ++ * Author: ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef ENFS_MULTIPATH_H ++#define ENFS_MULTIPATH_H ++#include <linux/sunrpc/clnt.h> ++ ++#define MAX_XPRT_NUM_PER_CLIENT 32 ++ ++int enfs_multipath_init(void); ++void enfs_multipath_exit(void); ++void enfs_xprt_ippair_create(struct xprt_create *xprtargs, ++ struct rpc_clnt *clnt, void *data); ++int enfs_config_xprt_create_args(struct xprt_create *xprtargs, ++ struct rpc_create_args *args, ++ char *servername, size_t length); ++void print_enfs_multipath_addr(struct sockaddr *local, struct sockaddr *remote); ++ ++#endif // ENFS_MULTIPATH_H +diff --git a/fs/nfs/enfs/enfs_multipath_client.c b/fs/nfs/enfs/enfs_multipath_client.c +new file mode 100644 +index 000000000000..63c02898a42c +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.c +@@ -0,0 +1,340 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#include <linux/types.h> ++#include <linux/nfs.h> ++#include <linux/nfs4.h> ++#include <linux/nfs_fs.h> ++#include <linux/nfs_fs_sb.h> ++#include <linux/proc_fs.h> ++#include <linux/seq_file.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/addr.h> ++#include "enfs_multipath_client.h" ++#include "enfs_multipath_parse.h" ++ ++int ++nfs_multipath_client_mount_info_init(struct multipath_client_info *client_info, ++ const struct nfs_client_initdata *client_init_data) ++{ ++ struct multipath_mount_options *mount_options = ++ (struct multipath_mount_options *)client_init_data->enfs_option; ++ ++ if (mount_options->local_ip_list) { ++ client_info->local_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->local_ip_list) ++ return -ENOMEM; ++ ++ memcpy(client_info->local_ip_list, mount_options->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->remote_ip_list) { ++ ++ client_info->remote_ip_list = ++ kzalloc(sizeof(struct nfs_ip_list), GFP_KERNEL); ++ ++ if (!client_info->remote_ip_list) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->remote_ip_list, ++ mount_options->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (mount_options->pRemoteDnsInfo) { ++ client_info->pRemoteDnsInfo = ++ kzalloc(sizeof(struct NFS_ROUTE_DNS_INFO_S), GFP_KERNEL); ++ ++ if (!client_info->pRemoteDnsInfo) { ++ kfree(client_info->local_ip_list); ++ client_info->local_ip_list = NULL; ++ kfree(client_info->remote_ip_list); ++ client_info->remote_ip_list = NULL; ++ return -ENOMEM; ++ } ++ memcpy(client_info->pRemoteDnsInfo, ++ mount_options->pRemoteDnsInfo, ++ sizeof(struct NFS_ROUTE_DNS_INFO_S)); ++ } ++ return 0; ++} ++ ++void nfs_multipath_client_info_free_work(struct work_struct *work) ++{ ++ ++ struct multipath_client_info *clp_info; ++ ++ if (work == NULL) ++ return; ++ ++ clp_info = container_of(work, struct multipath_client_info, work); ++ ++ if (clp_info->local_ip_list != NULL) { ++ kfree(clp_info->local_ip_list); ++ clp_info->local_ip_list = NULL; ++ } ++ if (clp_info->remote_ip_list != NULL) { ++ kfree(clp_info->remote_ip_list); ++ clp_info->remote_ip_list = NULL; ++ } ++ kfree(clp_info); ++} ++ ++void nfs_multipath_client_info_free(void *data) ++{ ++ struct multipath_client_info *clp_info = ++ (struct multipath_client_info *)data; ++ ++ if (clp_info == NULL) ++ return; ++ pr_info("free client info %p.\n", clp_info); ++ INIT_WORK(&clp_info->work, nfs_multipath_client_info_free_work); ++ schedule_work(&clp_info->work); ++} ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init) ++{ ++ int rc; ++ struct multipath_client_info *info; ++ struct multipath_client_info **enfs_info; ++ /* no multi path info, no need do multipath init */ ++ if (cl_init->enfs_option == NULL) ++ return 0; ++ enfs_info = (struct multipath_client_info **)data; ++ if (enfs_info == NULL) ++ return -EINVAL; ++ ++ if (*enfs_info == NULL) ++ *enfs_info = kzalloc(sizeof(struct multipath_client_info), ++ GFP_KERNEL); ++ ++ if (*enfs_info == NULL) ++ return -ENOMEM; ++ ++ info = (struct multipath_client_info *)*enfs_info; ++ pr_info("init client info %p.\n", info); ++ rc = nfs_multipath_client_mount_info_init(info, cl_init); ++ if (rc) { ++ nfs_multipath_client_info_free((void *)info); ++ return rc; ++ } ++ return rc; ++} ++ ++bool nfs_multipath_ip_list_info_match(const struct nfs_ip_list *ip_list_src, ++ const struct nfs_ip_list *ip_list_dst) ++{ ++ int i; ++ int j; ++ bool is_find; ++ /* if both are equal or NULL, then return true. */ ++ if (ip_list_src == ip_list_dst) ++ return true; ++ ++ if ((ip_list_src == NULL || ip_list_dst == NULL)) ++ return false; ++ ++ if (ip_list_src->count != ip_list_dst->count) ++ return false; ++ ++ for (i = 0; i < ip_list_src->count; i++) { ++ is_find = false; ++ for (j = 0; j < ip_list_src->count; j++) { ++ if (rpc_cmp_addr_port( ++ (const struct sockaddr *) ++ &ip_list_src->address[i], ++ (const struct sockaddr *) ++ &ip_list_dst->address[j]) ++ ) { ++ is_find = true; ++ break; ++ } ++ } ++ if (is_find == false) ++ return false; ++ } ++ return true; ++} ++ ++int ++nfs_multipath_dns_list_info_match( ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoSrc, ++ const struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfoDst) ++{ ++ int i; ++ ++ /* if both are equal or NULL, then return true. */ ++ if (pRemoteDnsInfoSrc == pRemoteDnsInfoDst) ++ return true; ++ ++ if ((pRemoteDnsInfoSrc == NULL || pRemoteDnsInfoDst == NULL)) ++ return false; ++ ++ if (pRemoteDnsInfoSrc->dnsNameCount != pRemoteDnsInfoDst->dnsNameCount) ++ return false; ++ ++ for (i = 0; i < pRemoteDnsInfoSrc->dnsNameCount; i++) { ++ if (!strcmp(pRemoteDnsInfoSrc->routeRemoteDnsList[i].dnsname, ++ pRemoteDnsInfoDst->routeRemoteDnsList[i].dnsname)) ++ return false; ++ } ++ return true; ++} ++ ++int nfs_multipath_client_info_match(void *src, void *dst) ++{ ++ int ret = true; ++ ++ struct multipath_client_info *src_info; ++ struct multipath_mount_options *dst_info; ++ ++ src_info = (struct multipath_client_info *)src; ++ dst_info = (struct multipath_mount_options *)dst; ++ pr_info("try match client .\n"); ++ ret = nfs_multipath_ip_list_info_match(src_info->local_ip_list, ++ dst_info->local_ip_list); ++ if (ret == false) { ++ pr_err("local_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_ip_list_info_match(src_info->remote_ip_list, ++ dst_info->remote_ip_list); ++ if (ret == false) { ++ pr_err("remote_ip not match.\n"); ++ return ret; ++ } ++ ++ ret = nfs_multipath_dns_list_info_match(src_info->pRemoteDnsInfo, ++ dst_info->pRemoteDnsInfo); ++ if (ret == false) { ++ pr_err("dns not match.\n"); ++ return ret; ++ } ++ pr_info("try match client ret %d.\n", ret); ++ return ret; ++} ++ ++void nfs_multipath_print_ip_info(struct seq_file *mount_option, ++ struct nfs_ip_list *ip_list, ++ const char *type) ++{ ++ char buf[IP_ADDRESS_LEN_MAX + 1]; ++ int len = 0; ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < ip_list->count; i++) { ++ len = rpc_ntop((struct sockaddr *)&ip_list->address[i], ++ buf, IP_ADDRESS_LEN_MAX); ++ if (len > 0 && len < IP_ADDRESS_LEN_MAX) ++ buf[len] = '\0'; ++ ++ if (i == 0) ++ seq_printf(mount_option, "%s", buf); ++ else ++ seq_printf(mount_option, "~%s", buf); ++ dfprintk(MOUNT, ++ "NFS: show nfs mount option type:%s %s [%s]\n", ++ type, buf, __func__); ++ } ++} ++ ++void nfs_multipath_print_dns_info(struct seq_file *mount_option, ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo, ++ const char *type) ++{ ++ int i = 0; ++ ++ seq_printf(mount_option, ",%s=", type); ++ for (i = 0; i < pRemoteDnsInfo->dnsNameCount; i++) { ++ if (i == 0) ++ seq_printf(mount_option, ++ "[%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else if (i == pRemoteDnsInfo->dnsNameCount - 1) ++ seq_printf(mount_option, ",%s]", ++ pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ else ++ seq_printf(mount_option, ++ ",%s", pRemoteDnsInfo->routeRemoteDnsList[i].dnsname); ++ } ++} ++ ++ ++static void multipath_print_sockaddr(struct seq_file *seq, ++ struct sockaddr *addr) ++{ ++ switch (addr->sa_family) { ++ case AF_INET: { ++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; ++ ++ seq_printf(seq, "%pI4", &sin->sin_addr); ++ return; ++ } ++ case AF_INET6: { ++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; ++ ++ seq_printf(seq, "%pI6", &sin6->sin6_addr); ++ return; ++ } ++ default: ++ break; ++ } ++ pr_err("unsupport family:%d\n", addr->sa_family); ++} ++ ++static void multipath_print_enfs_info(struct seq_file *seq, ++ struct nfs_server *server) ++{ ++ struct sockaddr_storage peeraddr; ++ struct rpc_clnt *next = server->client; ++ ++ rpc_peeraddr(server->client, ++ (struct sockaddr *)&peeraddr, sizeof(peeraddr)); ++ seq_puts(seq, ",enfs_info="); ++ multipath_print_sockaddr(seq, (struct sockaddr *)&peeraddr); ++ ++ while (next->cl_parent) { ++ if (next == next->cl_parent) ++ break; ++ next = next->cl_parent; ++ } ++ seq_printf(seq, "_%u", next->cl_clid); ++} ++ ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data) ++{ ++ struct nfs_server *server = data; ++ struct multipath_client_info *client_info = ++ server->nfs_client->cl_multipath_data; ++ ++ dfprintk(MOUNT, "NFS: show nfs mount option[%s]\n", __func__); ++ if ((client_info->remote_ip_list) && ++ (client_info->remote_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->remote_ip_list, ++ "remoteaddrs"); ++ ++ if ((client_info->local_ip_list) && ++ (client_info->local_ip_list->count > 0)) ++ nfs_multipath_print_ip_info(mount_option, ++ client_info->local_ip_list, ++ "localaddrs"); ++ ++ if ((client_info->pRemoteDnsInfo) && ++ (client_info->pRemoteDnsInfo->dnsNameCount > 0)) ++ nfs_multipath_print_dns_info(mount_option, ++ client_info->pRemoteDnsInfo, ++ "remotednsname"); ++ ++ multipath_print_enfs_info(mount_option, server); ++} +diff --git a/fs/nfs/enfs/enfs_multipath_client.h b/fs/nfs/enfs/enfs_multipath_client.h +new file mode 100644 +index 000000000000..208f7260690d +--- /dev/null ++++ b/fs/nfs/enfs/enfs_multipath_client.h +@@ -0,0 +1,26 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS adapter. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef _ENFS_MULTIPATH_CLIENT_H_ ++#define _ENFS_MULTIPATH_CLIENT_H_ ++ ++#include "enfs.h" ++ ++struct multipath_client_info { ++ struct work_struct work; ++ struct nfs_ip_list *remote_ip_list; ++ struct nfs_ip_list *local_ip_list; ++ struct NFS_ROUTE_DNS_INFO_S *pRemoteDnsInfo; ++ s64 client_id; ++}; ++ ++int nfs_multipath_client_info_init(void **data, ++ const struct nfs_client_initdata *cl_init); ++void nfs_multipath_client_info_free(void *data); ++int nfs_multipath_client_info_match(void *src, void *dst); ++void nfs_multipath_client_info_show(struct seq_file *mount_option, void *data); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_path.c b/fs/nfs/enfs/enfs_path.c +new file mode 100644 +index 000000000000..7355f8c2f672 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_path.c +@@ -0,0 +1,47 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++ ++#include <linux/sunrpc/metrics.h> ++#include <linux/sunrpc/xprt.h> ++ ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_path.h" ++ ++// only create ctx in this function ++// alloc iostat memory in create_clnt ++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx; ++ ++ if (!xprt) { ++ enfs_log_error("invalid xprt pointer.\n"); ++ return -EINVAL; ++ } ++ ++ ctx = kzalloc(sizeof(struct enfs_xprt_context), GFP_KERNEL); ++ if (!ctx) { ++ enfs_log_error("add xprt test failed.\n"); ++ return -ENOMEM; ++ } ++ ++ xprt->multipath_context = (void *)ctx; ++ return 0; ++} ++ ++// free multi_context and iostat memory ++void enfs_free_xprt_ctx(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = xprt->multipath_context; ++ ++ if (ctx) { ++ if (ctx->stats) { ++ rpc_free_iostats(ctx->stats); ++ ctx->stats = NULL; ++ } ++ kfree(xprt->multipath_context); ++ xprt->multipath_context = NULL; ++ } ++} +diff --git a/fs/nfs/enfs/enfs_path.h b/fs/nfs/enfs/enfs_path.h +new file mode 100644 +index 000000000000..97b1ef3730b8 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_path.h +@@ -0,0 +1,12 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++ ++#ifndef ENFS_PATH_H ++#define ENFS_PATH_H ++ ++int enfs_alloc_xprt_ctx(struct rpc_xprt *xprt); ++void enfs_free_xprt_ctx(struct rpc_xprt *xprt); ++ ++#endif // ENFS_PATH_H +diff --git a/fs/nfs/enfs/enfs_proc.c b/fs/nfs/enfs/enfs_proc.c +new file mode 100644 +index 000000000000..53fa1a07642f +--- /dev/null ++++ b/fs/nfs/enfs/enfs_proc.c +@@ -0,0 +1,545 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#include <linux/module.h> ++#include <linux/proc_fs.h> ++#include <linux/seq_file.h> ++#include <linux/spinlock.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/metrics.h> ++#include <linux/sunrpc/xprtsock.h> ++#include <net/netns/generic.h> ++ ++#include "../../../net/sunrpc/netns.h" ++ ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_proc.h" ++#include "enfs_multipath.h" ++#include "pm_state.h" ++ ++#define ENFS_PROC_DIR "enfs" ++#define ENFS_PROC_PATH_STATUS_LEN 256 ++ ++static struct proc_dir_entry *enfs_proc_parent; ++ ++void ++enfs_iterate_each_rpc_clnt(int (*fn)(struct rpc_clnt *clnt, void *data), ++ void *data) ++{ ++ struct net *net; ++ struct sunrpc_net *sn; ++ struct rpc_clnt *clnt; ++ ++ rcu_read_lock(); ++ for_each_net_rcu(net) { ++ sn = net_generic(net, sunrpc_net_id); ++ if (sn == NULL) ++ continue; ++ spin_lock(&sn->rpc_client_lock); ++ list_for_each_entry(clnt, &sn->all_clients, cl_clients) { ++ fn(clnt, data); ++ } ++ spin_unlock(&sn->rpc_client_lock); ++ } ++ rcu_read_unlock(); ++} ++ ++struct proc_dir_entry *enfs_get_proc_parent(void) ++{ ++ return enfs_proc_parent; ++} ++ ++static int sockaddr_ip_to_str(struct sockaddr *addr, char *buf, int len) ++{ ++ switch (addr->sa_family) { ++ case AF_INET: { ++ struct sockaddr_in *sin = (struct sockaddr_in *)addr; ++ ++ snprintf(buf, len, "%pI4", &sin->sin_addr); ++ return 0; ++ } ++ case AF_INET6: { ++ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; ++ ++ snprintf(buf, len, "%pI6", &sin6->sin6_addr); ++ return 0; ++ } ++ default: ++ break; ++ } ++ return 1; ++} ++ ++static bool should_print(const char *name) ++{ ++ int i; ++ static const char * const proc_names[] = { ++ "READ", ++ "WRITE", ++ }; ++ ++ if (name == NULL) ++ return false; ++ ++ for (i = 0; i < ARRAY_SIZE(proc_names); i++) { ++ if (strcmp(name, proc_names[i]) == 0) ++ return true; ++ } ++ return false; ++} ++ ++struct enfs_xprt_iter { ++ unsigned int id; ++ struct seq_file *seq; ++ unsigned int max_addrs_length; ++}; ++ ++static int debug_show_xprt(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ ++ if (xprt->multipath_context) ++ ctx = xprt->multipath_context; ++ ++ pr_info(" xprt:%p ctx:%p main:%d queue_len:%lu.\n", xprt, ++ xprt->multipath_context, ++ ctx ? ctx->main : false, ++ atomic_long_read(&xprt->queuelen)); ++ return 0; ++} ++ ++static int debug_show_clnt(struct rpc_clnt *clnt, void *data) ++{ ++ pr_info(" clnt %d addr:%p enfs:%d\n", ++ clnt->cl_clid, clnt, ++ clnt->cl_enfs); ++ rpc_clnt_iterate_for_each_xprt(clnt, debug_show_xprt, NULL); ++ return 0; ++} ++ ++static void debug_print_all_xprt(void) ++{ ++ enfs_iterate_each_rpc_clnt(debug_show_clnt, NULL); ++} ++ ++static ++void enfs_proc_format_xprt_addr_display(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ char *local_name_buf, ++ int local_name_buf_len, ++ char *remote_name_buf, ++ int remote_name_buf_len) ++{ ++ int err; ++ struct sockaddr_storage srcaddr; ++ struct enfs_xprt_context *ctx; ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ sockaddr_ip_to_str((struct sockaddr *)&xprt->addr, ++ remote_name_buf, remote_name_buf_len); ++ ++ // get local address depend one main or not ++ if (enfs_is_main_xprt(xprt)) { ++ err = rpc_localaddr(clnt, (struct sockaddr *)&srcaddr, ++ sizeof(srcaddr)); ++ if (err != 0) ++ (void)snprintf(local_name_buf, ++ local_name_buf_len, "Unknown"); ++ else ++ sockaddr_ip_to_str((struct sockaddr *)&srcaddr, ++ local_name_buf, ++ local_name_buf_len); ++ } else { ++ sockaddr_ip_to_str((struct sockaddr *)&ctx->srcaddr, ++ local_name_buf, ++ local_name_buf_len); ++ } ++} ++ ++static int enfs_show_xprt_stats(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ unsigned int op; ++ unsigned int maxproc = clnt->cl_maxproc; ++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; ++ struct enfs_xprt_context *ctx; ++ char local_name[INET6_ADDRSTRLEN]; ++ char remote_name[INET6_ADDRSTRLEN]; ++ ++ if (!xprt->multipath_context) ++ return 0; ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ enfs_proc_format_xprt_addr_display(clnt, xprt, local_name, ++ sizeof(local_name), ++ remote_name, sizeof(remote_name)); ++ ++ seq_printf(iter->seq, "%-6u%-*s%-*s", iter->id, ++ iter->max_addrs_length + 4, ++ local_name, ++ iter->max_addrs_length + 4, ++ remote_name); ++ ++ iter->id++; ++ ++ for (op = 0; op < maxproc; op++) { ++ if (!should_print(clnt->cl_procinfo[op].p_name)) ++ continue; ++ ++ seq_printf(iter->seq, "%-22lu%-22Lu%-22Lu", ++ ctx->stats[op].om_ops, ++ ctx->stats[op].om_ops == 0 ? 0 : ++ ktime_to_ms(ctx->stats[op].om_rtt) / ++ ctx->stats[op].om_ops, ++ ctx->stats[op].om_ops == 0 ? 0 : ++ ktime_to_ms(ctx->stats[op].om_execute) / ++ ctx->stats[op].om_ops); ++ } ++ seq_puts(iter->seq, "\n"); ++ return 0; ++} ++ ++static int rpc_proc_show_path_status(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; ++ struct enfs_xprt_context *ctx = NULL; ++ char local_name[INET6_ADDRSTRLEN] = {0}; ++ char remote_name[INET6_ADDRSTRLEN] = {0}; ++ char multiapth_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; ++ char xprt_status[ENFS_PROC_PATH_STATUS_LEN] = {0}; ++ ++ if (!xprt->multipath_context) { ++ enfs_log_debug("multipath_context is null.\n"); ++ return 0; ++ } ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ enfs_proc_format_xprt_addr_display(clnt, xprt, ++ local_name, ++ sizeof(local_name), ++ remote_name, sizeof(remote_name)); ++ ++ pm_get_path_state_desc(xprt, ++ multiapth_status, ++ ENFS_PROC_PATH_STATUS_LEN); ++ ++ pm_get_xprt_state_desc(xprt, ++ xprt_status, ++ ENFS_PROC_PATH_STATUS_LEN); ++ ++ seq_printf(iter->seq, "%-6u%-*s%-*s%-12s%-12s\n", ++ iter->id, iter->max_addrs_length + 4, ++ local_name, iter->max_addrs_length + 4, ++ remote_name, multiapth_status, ++ xprt_status); ++ iter->id++; ++ return 0; ++} ++ ++static int enfs_get_max_addrs_length(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ struct enfs_xprt_iter *iter = (struct enfs_xprt_iter *)data; ++ char local_name[INET6_ADDRSTRLEN]; ++ char remote_name[INET6_ADDRSTRLEN]; ++ ++ enfs_proc_format_xprt_addr_display(clnt, xprt, ++ local_name, sizeof(local_name), ++ remote_name, sizeof(remote_name)); ++ ++ if (iter->max_addrs_length < strlen(local_name)) ++ iter->max_addrs_length = strlen(local_name); ++ ++ if (iter->max_addrs_length < strlen(remote_name)) ++ iter->max_addrs_length = strlen(remote_name); ++ ++ return 0; ++} ++ ++static int rpc_proc_clnt_showpath(struct seq_file *seq, void *v) ++{ ++ struct rpc_clnt *clnt = seq->private; ++ struct enfs_xprt_iter iter; ++ ++ iter.seq = seq; ++ iter.id = 0; ++ iter.max_addrs_length = 0; ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ enfs_get_max_addrs_length, ++ (void *)&iter); ++ ++ seq_printf(seq, "%-6s%-*s%-*s%-12s%-12s\n", "id", ++ iter.max_addrs_length + 4, ++ "local_addr", ++ iter.max_addrs_length + 4, ++ "remote_addr", ++ "path_state", ++ "xprt_state"); ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ rpc_proc_show_path_status, ++ (void *)&iter); ++ return 0; ++} ++ ++static int enfs_rpc_proc_show(struct seq_file *seq, void *v) ++{ ++ struct rpc_clnt *clnt = seq->private; ++ struct enfs_xprt_iter iter; ++ ++ iter.seq = seq; ++ iter.id = 0; ++ iter.max_addrs_length = 0; ++ ++ debug_print_all_xprt(); ++ pr_info("enfs proc clnt:%p\n", clnt); ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ enfs_get_max_addrs_length, ++ (void *)&iter); ++ ++ seq_printf(seq, "%-6s%-*s%-*s%-22s%-22s%-22s%-22s%-22s%-22s\n", "id", ++ iter.max_addrs_length + 4, "local_addr", ++ iter.max_addrs_length + 4, ++ "remote_addr", "r_count", ++ "r_rtt", "r_exec", "w_count", "w_rtt", "w_exec"); ++ ++ // rpc_clnt_show_stats(seq, clnt); ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ enfs_show_xprt_stats, ++ (void *)&iter); ++ return 0; ++} ++ ++static int rpc_proc_open(struct inode *inode, struct file *file) ++{ ++ struct rpc_clnt *clnt = PDE_DATA(inode); ++ ++ pr_info("%s %p\n", __func__, clnt); ++ return single_open(file, enfs_rpc_proc_show, clnt); ++} ++ ++static int enfs_reset_xprt_stats(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void *data) ++{ ++ unsigned int op; ++ struct enfs_xprt_context *ctx; ++ unsigned int maxproc = clnt->cl_maxproc; ++ struct rpc_iostats stats = {0}; ++ ++ if (!xprt->multipath_context) ++ return 0; ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ ++ for (op = 0; op < maxproc; op++) { ++ spin_lock(&ctx->stats[op].om_lock); ++ ctx->stats[op] = stats; ++ spin_unlock(&ctx->stats[op].om_lock); ++ } ++ return 0; ++} ++ ++static void trim_newline_ch(char *str, int len) ++{ ++ int i; ++ ++ for (i = 0; str[i] != '\0' && i < len; i++) { ++ if (str[i] == '\n') ++ str[i] = '\0'; ++ } ++} ++ ++static ssize_t enfs_proc_write(struct file *file, ++ const char __user *user_buf, ++ size_t len, ++ loff_t *offset) ++{ ++ char buffer[128]; ++ struct rpc_clnt *clnt = ++ ((struct seq_file *)file->private_data)->private; ++ ++ if (len >= sizeof(buffer)) ++ return -E2BIG; ++ ++ if (copy_from_user(buffer, user_buf, len) != 0) ++ return -EFAULT; ++ ++ buffer[len] = '\0'; ++ trim_newline_ch(buffer, len); ++ if (strcmp(buffer, "reset") != 0) ++ return -EINVAL; ++ ++ rpc_clnt_iterate_for_each_xprt(clnt, enfs_reset_xprt_stats, NULL); ++ return len; ++} ++ ++static int rpc_proc_show_path(struct inode *inode, struct file *file) ++{ ++ struct rpc_clnt *clnt = PDE_DATA(inode); ++ ++ return single_open(file, rpc_proc_clnt_showpath, clnt); ++} ++ ++static const struct file_operations rpc_proc_fops = { ++ .owner = THIS_MODULE, ++ .open = rpc_proc_open, ++ .read = seq_read, ++ .llseek = seq_lseek, ++ .release = single_release, ++ .write = enfs_proc_write, ++}; ++ ++static const struct file_operations rpc_show_path_fops = { ++ .owner = THIS_MODULE, ++ .open = rpc_proc_show_path, ++ .read = seq_read, ++ .llseek = seq_lseek, ++ .release = single_release, ++}; ++ ++static int clnt_proc_name(struct rpc_clnt *clnt, char *buf, int len) ++{ ++ int ret; ++ ++ ret = snprintf(buf, len, "%s_%u", ++ rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR), ++ clnt->cl_clid); ++ if (ret > len) ++ return -E2BIG; ++ return 0; ++} ++ ++static int enfs_proc_create_file(struct rpc_clnt *clnt) ++{ ++ int err; ++ char buf[128]; ++ ++ struct proc_dir_entry *clnt_entry; ++ struct proc_dir_entry *stat_entry; ++ ++ err = clnt_proc_name(clnt, buf, sizeof(buf)); ++ if (err) ++ return err; ++ ++ clnt_entry = proc_mkdir(buf, enfs_proc_parent); ++ if (clnt_entry == NULL) ++ return -EINVAL; ++ ++ stat_entry = proc_create_data("stat", ++ 0, clnt_entry, ++ &rpc_proc_fops, clnt); ++ ++ if (stat_entry == NULL) ++ return -EINVAL; ++ ++ stat_entry = proc_create_data("path", ++ 0, clnt_entry, ++ &rpc_show_path_fops, clnt); ++ ++ if (stat_entry == NULL) ++ return -EINVAL; ++ ++ return 0; ++} ++ ++void enfs_count_iostat(struct rpc_task *task) ++{ ++ struct enfs_xprt_context *ctx = task->tk_xprt->multipath_context; ++ ++ if (!ctx || !ctx->stats) ++ return; ++ rpc_count_iostats(task, ctx->stats); ++} ++ ++static void enfs_proc_delete_file(struct rpc_clnt *clnt) ++{ ++ int err; ++ char buf[128]; ++ ++ err = clnt_proc_name(clnt, buf, sizeof(buf)); ++ if (err) { ++ pr_err("gen clnt name failed.\n"); ++ return; ++ } ++ remove_proc_subtree(buf, enfs_proc_parent); ++} ++ ++// create proc file "/porc/enfs/[mount_ip]_[id]/stat" ++int enfs_proc_create_clnt(struct rpc_clnt *clnt) ++{ ++ int err; ++ ++ err = enfs_proc_create_file(clnt); ++ if (err) { ++ pr_err("create client %d\n", err); ++ return err; ++ } ++ ++ return 0; ++} ++ ++void enfs_proc_delete_clnt(struct rpc_clnt *clnt) ++{ ++ if (clnt->cl_enfs) ++ enfs_proc_delete_file(clnt); ++} ++ ++static int enfs_proc_create_parent(void) ++{ ++ enfs_proc_parent = proc_mkdir(ENFS_PROC_DIR, NULL); ++ ++ if (enfs_proc_parent == NULL) { ++ pr_err("Enfs create proc dir err\n"); ++ return -ENOMEM; ++ } ++ return 0; ++} ++ ++static void enfs_proc_delete_parent(void) ++{ ++ remove_proc_entry(ENFS_PROC_DIR, NULL); ++} ++ ++static int enfs_proc_init_create_clnt(struct rpc_clnt *clnt, void *data) ++{ ++ if (clnt->cl_enfs) ++ enfs_proc_create_file(clnt); ++ return 0; ++} ++ ++static int enfs_proc_destroy_clnt(struct rpc_clnt *clnt, void *data) ++{ ++ if (clnt->cl_enfs) ++ enfs_proc_delete_file(clnt); ++ return 0; ++} ++ ++int enfs_proc_init(void) ++{ ++ int err; ++ ++ err = enfs_proc_create_parent(); ++ if (err) ++ return err; ++ ++ enfs_iterate_each_rpc_clnt(enfs_proc_init_create_clnt, NULL); ++ return 0; ++} ++ ++void enfs_proc_exit(void) ++{ ++ enfs_iterate_each_rpc_clnt(enfs_proc_destroy_clnt, NULL); ++ enfs_proc_delete_parent(); ++} +diff --git a/fs/nfs/enfs/enfs_proc.h b/fs/nfs/enfs/enfs_proc.h +new file mode 100644 +index 000000000000..321951031c2e +--- /dev/null ++++ b/fs/nfs/enfs/enfs_proc.h +@@ -0,0 +1,21 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Client-side ENFS PROC. ++ * ++ * Copyright (c) 2023. Huawei Technologies Co., Ltd. All rights reserved. ++ */ ++#ifndef ENFS_PROC_H ++#define ENFS_PROC_H ++ ++struct rpc_clnt; ++struct rpc_task; ++struct proc_dir_entry; ++ ++int enfs_proc_init(void); ++void enfs_proc_exit(void); ++struct proc_dir_entry *enfs_get_proc_parent(void); ++int enfs_proc_create_clnt(struct rpc_clnt *clnt); ++void enfs_proc_delete_clnt(struct rpc_clnt *clnt); ++void enfs_count_iostat(struct rpc_task *task); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_remount.c b/fs/nfs/enfs/enfs_remount.c +new file mode 100644 +index 000000000000..2c3fe125c735 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_remount.c +@@ -0,0 +1,221 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: remount ip source file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++#include "enfs_remount.h" ++ ++#include <linux/string.h> ++#include <linux/in.h> ++#include <linux/in6.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/spinlock.h> ++#include <linux/sunrpc/addr.h> ++#include <linux/sunrpc/metrics.h> ++#include <linux/sunrpc/xprtmultipath.h> ++#include <linux/sunrpc/xprtsock.h> ++#include <linux/sunrpc/xprt.h> ++#include <linux/smp.h> ++#include <linux/delay.h> ++ ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_multipath.h" ++#include "enfs_multipath_parse.h" ++#include "enfs_path.h" ++#include "enfs_proc.h" ++#include "enfs_multipath_client.h" ++ ++static bool enfs_rpc_xprt_switch_need_delete_addr( ++ struct multipath_mount_options *enfs_option, ++ struct sockaddr *dstaddr, struct sockaddr *srcaddr) ++{ ++ int i; ++ bool find_same_ip = false; ++ int32_t local_total; ++ int32_t remote_total; ++ ++ local_total = enfs_option->local_ip_list->count; ++ remote_total = enfs_option->remote_ip_list->count; ++ if (local_total == 0 || remote_total == 0) { ++ pr_err("no ip list is present.\n"); ++ return false; ++ } ++ ++ for (i = 0; i < local_total; i++) { ++ find_same_ip = ++ rpc_cmp_addr((struct sockaddr *) ++ &enfs_option->local_ip_list->address[i], ++ srcaddr); ++ if (find_same_ip) ++ break; ++ } ++ ++ if (find_same_ip == false) ++ return true; ++ ++ find_same_ip = false; ++ for (i = 0; i < remote_total; i++) { ++ find_same_ip = ++ rpc_cmp_addr((struct sockaddr *) ++ &enfs_option->remote_ip_list->address[i], ++ dstaddr); ++ if (find_same_ip) ++ break; ++ } ++ ++ if (find_same_ip == false) ++ return true; ++ ++ return false; ++} ++ ++// Used in rcu_lock ++static bool enfs_delete_xprt_from_switch(struct rpc_xprt *xprt, ++ void *enfs_option, ++ struct rpc_xprt_switch *xps) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ struct multipath_mount_options *mopt = ++ (struct multipath_mount_options *)enfs_option; ++ ++ if (enfs_is_main_xprt(xprt)) ++ return true; ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (enfs_rpc_xprt_switch_need_delete_addr(mopt, ++ (struct sockaddr *)&xprt->addr, ++ (struct sockaddr *)&ctx->srcaddr)) { ++ ++ print_enfs_multipath_addr((struct sockaddr *)&ctx->srcaddr, ++ (struct sockaddr *)&xprt->addr); ++ rpc_xprt_switch_remove_xprt(xps, xprt); ++ return true; ++ } ++ ++ return false; ++} ++ ++void enfs_clnt_delete_obsolete_xprts(struct nfs_client *nfs_client, ++ void *enfs_option) ++{ ++ int xprt_count = 0; ++ struct rpc_xprt *pos = NULL; ++ struct rpc_xprt_switch *xps = NULL; ++ ++ rcu_read_lock(); ++ xps = xprt_switch_get( ++ rcu_dereference( ++ nfs_client->cl_rpcclient->cl_xpi.xpi_xpswitch)); ++ if (xps == NULL) { ++ rcu_read_unlock(); ++ xprt_switch_put(xps); ++ return; ++ } ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (xprt_count < MAX_XPRT_NUM_PER_CLIENT) { ++ if (enfs_delete_xprt_from_switch( ++ pos, enfs_option, xps) == false) ++ xprt_count++; ++ } else ++ rpc_xprt_switch_remove_xprt(xps, pos); ++ } ++ rcu_read_unlock(); ++ xprt_switch_put(xps); ++} ++ ++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option) ++{ ++ int errno = 0; ++ char servername[48]; ++ struct multipath_mount_options *remount_lists = ++ (struct multipath_mount_options *)enfs_option; ++ struct multipath_client_info *client_info = ++ (struct multipath_client_info *)nfs_client->cl_multipath_data; ++ struct xprt_create xprtargs; ++ struct rpc_create_args args = { ++ .protocol = nfs_client->cl_proto, ++ .net = nfs_client->cl_net, ++ .addrsize = nfs_client->cl_addrlen, ++ .servername = nfs_client->cl_hostname, ++ }; ++ ++ memset(&xprtargs, 0, sizeof(struct xprt_create)); ++ ++ //mount is not use multipath ++ if (client_info == NULL || enfs_option == NULL) { ++ enfs_log_error( ++ "mount information or remount information is empty.\n"); ++ return -EINVAL; ++ } ++ ++ //remount : localaddrs and remoteaddrs are empty ++ if (remount_lists->local_ip_list->count == 0 && ++ remount_lists->remote_ip_list->count == 0) { ++ enfs_log_info("remount local_ip_list and remote_ip_list are NULL\n"); ++ return 0; ++ } ++ ++ errno = enfs_config_xprt_create_args(&xprtargs, ++ &args, servername, sizeof(servername)); ++ ++ if (errno) { ++ enfs_log_error("config_xprt_create failed! errno:%d\n", errno); ++ return errno; ++ } ++ ++ if (remount_lists->local_ip_list->count == 0) { ++ if (client_info->local_ip_list->count == 0) { ++ errno = rpc_localaddr(nfs_client->cl_rpcclient, ++ (struct sockaddr *) ++ &remount_lists->local_ip_list->address[0], ++ sizeof(struct sockaddr_storage)); ++ if (errno) { ++ enfs_log_error("get clnt srcaddr errno:%d\n", ++ errno); ++ return errno; ++ } ++ remount_lists->local_ip_list->count = 1; ++ } else ++ memcpy(remount_lists->local_ip_list, ++ client_info->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ if (remount_lists->remote_ip_list->count == 0) { ++ if (client_info->remote_ip_list->count == 0) { ++ errno = rpc_peeraddr(nfs_client->cl_rpcclient, ++ (struct sockaddr *) ++ &remount_lists->remote_ip_list->address[0], ++ sizeof(struct sockaddr_storage)); ++ if (errno == 0) { ++ enfs_log_error("get clnt dstaddr errno:%d\n", ++ errno); ++ return errno; ++ } ++ remount_lists->remote_ip_list->count = 1; ++ } else ++ memcpy(remount_lists->remote_ip_list, ++ client_info->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ } ++ ++ enfs_log_info("Remount creating new links...\n"); ++ enfs_xprt_ippair_create(&xprtargs, ++ nfs_client->cl_rpcclient, ++ remount_lists); ++ ++ enfs_log_info("Remount deleting obsolete links...\n"); ++ enfs_clnt_delete_obsolete_xprts(nfs_client, remount_lists); ++ ++ memcpy(client_info->local_ip_list, ++ remount_lists->local_ip_list, ++ sizeof(struct nfs_ip_list)); ++ memcpy(client_info->remote_ip_list, ++ remount_lists->remote_ip_list, ++ sizeof(struct nfs_ip_list)); ++ ++ return 0; ++} +diff --git a/fs/nfs/enfs/enfs_remount.h b/fs/nfs/enfs/enfs_remount.h +new file mode 100644 +index 000000000000..a663ed257004 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_remount.h +@@ -0,0 +1,15 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: remount ip header file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++#ifndef _ENFS_REMOUNT_ ++#define _ENFS_REMOUNT_ ++#include <linux/string.h> ++#include "enfs.h" ++ ++int enfs_remount_iplist(struct nfs_client *nfs_client, void *enfs_option); ++ ++#endif +diff --git a/fs/nfs/enfs/enfs_roundrobin.c b/fs/nfs/enfs/enfs_roundrobin.c +new file mode 100644 +index 000000000000..4e4eda784a3e +--- /dev/null ++++ b/fs/nfs/enfs/enfs_roundrobin.c +@@ -0,0 +1,255 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#include <linux/spinlock.h> ++#include <linux/module.h> ++#include <linux/printk.h> ++#include <linux/kref.h> ++#include <linux/rculist.h> ++#include <linux/types.h> ++#include <linux/sunrpc/xprt.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/xprtmultipath.h> ++#include "enfs_roundrobin.h" ++ ++#include "enfs.h" ++#include "enfs_config.h" ++#include "pm_state.h" ++ ++typedef struct rpc_xprt *(*enfs_xprt_switch_find_xprt_t)( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur); ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin; ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular; ++ ++static bool enfs_xprt_is_active(struct rpc_xprt *xprt) ++{ ++ enum pm_path_state state; ++ ++ if (kref_read(&xprt->kref) <= 0) ++ return false; ++ ++ state = pm_get_path_state(xprt); ++ if (state == PM_STATE_NORMAL) ++ return true; ++ ++ return false; ++} ++ ++static struct rpc_xprt *enfs_lb_set_cursor_xprt( ++ struct rpc_xprt_switch *xps, struct rpc_xprt **cursor, ++ enfs_xprt_switch_find_xprt_t find_next) ++{ ++ struct rpc_xprt *pos; ++ struct rpc_xprt *old; ++ ++ old = smp_load_acquire(cursor); /* read latest cursor */ ++ pos = find_next(xps, old); ++ smp_store_release(cursor, pos); /* let cursor point to pos */ ++ return pos; ++} ++ ++static ++struct rpc_xprt *enfs_lb_find_next_entry_roundrobin( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *pos; ++ struct rpc_xprt *prev = NULL; ++ bool found = false; ++ struct rpc_xprt *min_queuelen_xprt = NULL; ++ unsigned long pos_xprt_queuelen; ++ unsigned long min_xprt_queuelen = 0; ++ ++ unsigned long xps_queuelen = atomic_long_read(&xps->xps_queuelen); ++ // delete origin xprt ++ unsigned int multipath_nactive = READ_ONCE(xps->xps_nactive) - 1; ++ ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (enfs_is_main_xprt(pos) || !enfs_xprt_is_active(pos)) { ++ prev = pos; ++ continue; ++ } ++ ++ pos_xprt_queuelen = atomic_long_read(&pos->queuelen); ++ if (min_queuelen_xprt == NULL || ++ pos_xprt_queuelen < min_xprt_queuelen) { ++ ++ min_queuelen_xprt = pos; ++ min_xprt_queuelen = pos_xprt_queuelen; ++ } ++ ++ if (cur == prev) ++ found = true; ++ ++ if (found && pos_xprt_queuelen * ++ multipath_nactive <= xps_queuelen) ++ return pos; ++ prev = pos; ++ }; ++ ++ return min_queuelen_xprt; ++} ++ ++struct rpc_xprt *enfs_lb_switch_find_first_active_xprt( ++ struct rpc_xprt_switch *xps) ++{ ++ struct rpc_xprt *pos; ++ ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (enfs_xprt_is_active(pos)) ++ return pos; ++ }; ++ return NULL; ++} ++ ++struct rpc_xprt *enfs_lb_switch_get_main_xprt(struct rpc_xprt_switch *xps) ++{ ++ return list_first_or_null_rcu(&xps->xps_xprt_list, ++ struct rpc_xprt, xprt_switch); ++} ++ ++static struct rpc_xprt *enfs_lb_switch_get_next_xprt_roundrobin( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *xprt; ++ ++ // disable multipath ++ if (enfs_get_config_multipath_state()) ++ return enfs_lb_switch_get_main_xprt(xps); ++ ++ xprt = enfs_lb_find_next_entry_roundrobin(xps, cur); ++ if (xprt != NULL) ++ return xprt; ++ ++ return enfs_lb_switch_get_main_xprt(xps); ++} ++ ++static ++struct rpc_xprt *enfs_lb_iter_next_entry_roundrobin(struct rpc_xprt_iter *xpi) ++{ ++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); ++ ++ if (xps == NULL) ++ return NULL; ++ ++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, ++ enfs_lb_switch_get_next_xprt_roundrobin); ++} ++ ++static ++struct rpc_xprt *enfs_lb_switch_find_singular_entry( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *pos; ++ bool found = false; ++ ++ list_for_each_entry_rcu(pos, &xps->xps_xprt_list, xprt_switch) { ++ if (cur == pos) ++ found = true; ++ ++ if (found && enfs_xprt_is_active(pos)) ++ return pos; ++ } ++ return NULL; ++} ++ ++struct rpc_xprt *enfs_lb_get_singular_xprt( ++ struct rpc_xprt_switch *xps, const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *xprt; ++ ++ if (xps == NULL) ++ return NULL; ++ ++ // disable multipath ++ if (enfs_get_config_multipath_state()) ++ return enfs_lb_switch_get_main_xprt(xps); ++ ++ if (cur == NULL || xps->xps_nxprts < 2) ++ return enfs_lb_switch_find_first_active_xprt(xps); ++ ++ xprt = enfs_lb_switch_find_singular_entry(xps, cur); ++ if (!xprt) ++ return enfs_lb_switch_get_main_xprt(xps); ++ ++ return xprt; ++} ++ ++static ++struct rpc_xprt *enfs_lb_iter_next_entry_sigular(struct rpc_xprt_iter *xpi) ++{ ++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); ++ ++ if (xps == NULL) ++ return NULL; ++ ++ return enfs_lb_set_cursor_xprt(xps, &xpi->xpi_cursor, ++ enfs_lb_get_singular_xprt); ++} ++ ++static void enfs_lb_iter_default_rewind(struct rpc_xprt_iter *xpi) ++{ ++ WRITE_ONCE(xpi->xpi_cursor, NULL); ++} ++ ++static void enfs_lb_switch_set_roundrobin(struct rpc_clnt *clnt) ++{ ++ struct rpc_xprt_switch *xps; ++ ++ rcu_read_lock(); ++ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ++ rcu_read_unlock(); ++ if (clnt->cl_vers == 3) { ++ ++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_roundrobin) ++ WRITE_ONCE(xps->xps_iter_ops, ++ &enfs_xprt_iter_roundrobin); ++ ++ return; ++ } ++ if (READ_ONCE(xps->xps_iter_ops) != &enfs_xprt_iter_singular) ++ WRITE_ONCE(xps->xps_iter_ops, &enfs_xprt_iter_singular); ++} ++ ++static ++struct rpc_xprt *enfs_lb_switch_find_current(struct list_head *head, ++ const struct rpc_xprt *cur) ++{ ++ struct rpc_xprt *pos; ++ ++ list_for_each_entry_rcu(pos, head, xprt_switch) { ++ if (cur == pos) ++ return pos; ++ } ++ return NULL; ++} ++ ++static struct rpc_xprt *enfs_lb_iter_current_entry(struct rpc_xprt_iter *xpi) ++{ ++ struct rpc_xprt_switch *xps = rcu_dereference(xpi->xpi_xpswitch); ++ struct list_head *head; ++ ++ if (xps == NULL) ++ return NULL; ++ head = &xps->xps_xprt_list; ++ if (xpi->xpi_cursor == NULL || xps->xps_nxprts < 2) ++ return enfs_lb_switch_get_main_xprt(xps); ++ return enfs_lb_switch_find_current(head, xpi->xpi_cursor); ++} ++ ++void enfs_lb_set_policy(struct rpc_clnt *clnt) ++{ ++ enfs_lb_switch_set_roundrobin(clnt); ++} ++ ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_roundrobin = { ++ .xpi_rewind = enfs_lb_iter_default_rewind, ++ .xpi_xprt = enfs_lb_iter_current_entry, ++ .xpi_next = enfs_lb_iter_next_entry_roundrobin, ++}; ++ ++static const struct rpc_xprt_iter_ops enfs_xprt_iter_singular = { ++ .xpi_rewind = enfs_lb_iter_default_rewind, ++ .xpi_xprt = enfs_lb_iter_current_entry, ++ .xpi_next = enfs_lb_iter_next_entry_sigular, ++}; +diff --git a/fs/nfs/enfs/enfs_roundrobin.h b/fs/nfs/enfs/enfs_roundrobin.h +new file mode 100644 +index 000000000000..b72b088a6258 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_roundrobin.h +@@ -0,0 +1,9 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#ifndef ENFS_ROUNDROBIN_H ++#define ENFS_ROUNDROBIN_H ++ ++void enfs_lb_set_policy(struct rpc_clnt *clnt); ++#endif diff --git a/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch new file mode 100644 index 0000000..cc6b677 --- /dev/null +++ b/0005-add_enfs_module_for_sunrpc_failover_and_configure.patch @@ -0,0 +1,1607 @@ +diff --git a/fs/nfs/enfs/enfs_config.c b/fs/nfs/enfs/enfs_config.c +new file mode 100644 +index 000000000000..11aa7a00385b +--- /dev/null ++++ b/fs/nfs/enfs/enfs_config.c +@@ -0,0 +1,378 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ */ ++#include <linux/cdev.h> ++#include <linux/errno.h> ++#include <linux/fcntl.h> ++#include <linux/fs.h> ++#include <linux/kernel.h> ++#include <linux/kthread.h> ++#include <linux/slab.h> ++#include <linux/string.h> ++#include <linux/uaccess.h> ++#include <linux/delay.h> ++ ++#include "enfs_errcode.h" ++#include "enfs_log.h" ++#include "enfs_config.h" ++ ++#define MAX_FILE_SIZE 8192 ++#define STRING_BUF_SIZE 128 ++#define CONFIG_FILE_PATH "/etc/enfs/config.ini" ++#define ENFS_NOTIFY_FILE_PERIOD 1000UL ++ ++#define MAX_PATH_DETECT_INTERVAL 300 ++#define MIN_PATH_DETECT_INTERVAL 5 ++#define MAX_PATH_DETECT_TIMEOUT 60 ++#define MIN_PATH_DETECT_TIMEOUT 1 ++#define MAX_MULTIPATH_TIMEOUT 60 ++#define MIN_MULTIPATH_TIMEOUT 0 ++#define MAX_MULTIPATH_STATE ENFS_MULTIPATH_DISABLE ++#define MIN_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE ++ ++#define DEFAULT_PATH_DETECT_INTERVAL 10 ++#define DEFAULT_PATH_DETECT_TIMEOUT 5 ++#define DEFAULT_MULTIPATH_TIMEOUT 0 ++#define DEFAULT_MULTIPATH_STATE ENFS_MULTIPATH_ENABLE ++#define DEFAULT_LOADBALANCE_MODE ENFS_LOADBALANCE_RR ++ ++typedef int (*check_and_assign_func)(char *, char *, int, int); ++ ++struct enfs_config_info { ++ int32_t path_detect_interval; ++ int32_t path_detect_timeout; ++ int32_t multipath_timeout; ++ int32_t loadbalance_mode; ++ int32_t multipath_state; ++}; ++ ++struct check_and_assign_value { ++ char *field_name; ++ check_and_assign_func func; ++ int min_value; ++ int max_value; ++}; ++ ++static struct enfs_config_info g_enfs_config_info; ++static struct timespec64 modify_time; ++static struct task_struct *thread; ++ ++static int enfs_check_config_value(char *value, int min_value, int max_value) ++{ ++ unsigned long num_value; ++ int ret; ++ ++ ret = kstrtol(value, 10, &num_value); ++ if (ret != 0) { ++ enfs_log_error("Failed to convert string to int\n"); ++ return -EINVAL; ++ } ++ ++ if (num_value < min_value || num_value > max_value) ++ return -EINVAL; ++ ++ return num_value; ++} ++ ++static int32_t enfs_check_and_assign_int_value(char *field_name, char *value, ++ int min_value, int max_value) ++{ ++ int int_value = enfs_check_config_value(value, min_value, max_value); ++ ++ if (int_value < 0) ++ return -EINVAL; ++ ++ if (strcmp(field_name, "path_detect_interval") == 0) { ++ g_enfs_config_info.path_detect_interval = int_value; ++ return ENFS_RET_OK; ++ } ++ if (strcmp(field_name, "path_detect_timeout") == 0) { ++ g_enfs_config_info.path_detect_timeout = int_value; ++ return ENFS_RET_OK; ++ } ++ if (strcmp(field_name, "multipath_timeout") == 0) { ++ g_enfs_config_info.multipath_timeout = int_value; ++ return ENFS_RET_OK; ++ } ++ if (strcmp(field_name, "multipath_disable") == 0) { ++ g_enfs_config_info.multipath_state = int_value; ++ return ENFS_RET_OK; ++ } ++ return -EINVAL; ++} ++ ++static int32_t enfs_check_and_assign_loadbalance_mode(char *field_name, ++ char *value, ++ int min_value, ++ int max_value) ++{ ++ if (value == NULL) ++ return -EINVAL; ++ ++ if (strcmp(field_name, "multipath_select_policy") == 0) { ++ if (strcmp(value, "roundrobin") == 0) { ++ g_enfs_config_info.loadbalance_mode ++ = ENFS_LOADBALANCE_RR; ++ return ENFS_RET_OK; ++ } ++ } ++ return -EINVAL; ++} ++ ++static const struct check_and_assign_value g_check_and_assign_value[] = { ++ {"path_detect_interval", enfs_check_and_assign_int_value, ++ MIN_PATH_DETECT_INTERVAL, MAX_PATH_DETECT_INTERVAL}, ++ {"path_detect_timeout", enfs_check_and_assign_int_value, ++ MIN_PATH_DETECT_TIMEOUT, MAX_PATH_DETECT_TIMEOUT}, ++ {"multipath_timeout", enfs_check_and_assign_int_value, ++ MIN_MULTIPATH_TIMEOUT, MAX_MULTIPATH_TIMEOUT}, ++ {"multipath_disable", enfs_check_and_assign_int_value, ++ MIN_MULTIPATH_STATE, MAX_MULTIPATH_STATE}, ++ {"multipath_select_policy", enfs_check_and_assign_loadbalance_mode, ++ 0, 0}, ++}; ++ ++static int32_t enfs_read_config_file(char *buffer, char *file_path) ++{ ++ int ret; ++ struct file *filp = NULL; ++ loff_t f_pos = 0; ++ mm_segment_t fs; ++ ++ ++ filp = filp_open(file_path, O_RDONLY, 0); ++ ++ if (IS_ERR(filp)) { ++ enfs_log_error("Failed to open file %s\n", CONFIG_FILE_PATH); ++ ret = -ENOENT; ++ return ret; ++ } ++ ++ fs = get_fs(); ++ set_fs(get_ds()); ++ kernel_read(filp, buffer, MAX_FILE_SIZE, &f_pos); ++ set_fs(fs); ++ ++ ret = filp_close(filp, NULL); ++ if (ret) { ++ enfs_log_error("Close File:%s failed:%d.\n", ++ CONFIG_FILE_PATH, ret); ++ return -EINVAL; ++ } ++ return ENFS_RET_OK; ++} ++ ++static int32_t enfs_deal_with_comment_line(char *buffer) ++{ ++ int ret; ++ char *pos = strchr(buffer, '\n'); ++ ++ if (pos != NULL) ++ ret = strlen(buffer) - strlen(pos); ++ else ++ ret = strlen(buffer); ++ ++ return ret; ++} ++ ++static int32_t enfs_parse_key_value_from_config(char *buffer, char *key, ++ char *value, int keyLen, ++ int valueLen) ++{ ++ char *line; ++ char *tokenPtr; ++ int len; ++ char *tem; ++ char *pos = strchr(buffer, '\n'); ++ ++ if (pos != NULL) ++ len = strlen(buffer) - strlen(pos); ++ else ++ len = strlen(buffer); ++ ++ line = kmalloc(len + 1, GFP_KERNEL); ++ if (!line) { ++ enfs_log_error("Failed to allocate memory.\n"); ++ return -ENOMEM; ++ } ++ line[len] = '\0'; ++ strncpy(line, buffer, len); ++ ++ tem = line; ++ tokenPtr = strsep(&tem, "="); ++ if (tokenPtr == NULL || tem == NULL) { ++ kfree(line); ++ return len; ++ } ++ strncpy(key, strim(tokenPtr), keyLen); ++ strncpy(value, strim(tem), valueLen); ++ ++ kfree(line); ++ return len; ++} ++ ++static int32_t enfs_get_value_from_config_file(char *buffer, char *field_name, ++ char *value, int valueLen) ++{ ++ int ret; ++ char key[STRING_BUF_SIZE + 1] = {0}; ++ char val[STRING_BUF_SIZE + 1] = {0}; ++ ++ while (buffer[0] != '\0') { ++ if (buffer[0] == '\n') { ++ buffer++; ++ } else if (buffer[0] == '#') { ++ ret = enfs_deal_with_comment_line(buffer); ++ if (ret > 0) ++ buffer += ret; ++ } else { ++ ret = enfs_parse_key_value_from_config(buffer, key, val, ++ STRING_BUF_SIZE, ++ STRING_BUF_SIZE); ++ if (ret < 0) { ++ enfs_log_error("failed parse key value, %d\n" ++ , ret); ++ return ret; ++ } ++ key[STRING_BUF_SIZE] = '\0'; ++ val[STRING_BUF_SIZE] = '\0'; ++ ++ buffer += ret; ++ ++ if (strcmp(field_name, key) == 0) { ++ strncpy(value, val, valueLen); ++ return ENFS_RET_OK; ++ } ++ } ++ } ++ enfs_log_error("can not find value which matched field_name: %s.\n", ++ field_name); ++ return -EINVAL; ++} ++ ++int32_t enfs_config_load(void) ++{ ++ char value[STRING_BUF_SIZE + 1]; ++ int ret; ++ int table_len; ++ int min; ++ int max; ++ int i; ++ char *buffer; ++ ++ buffer = kmalloc(MAX_FILE_SIZE, GFP_KERNEL); ++ if (!buffer) { ++ enfs_log_error("Failed to allocate memory.\n"); ++ return -ENOMEM; ++ } ++ memset(buffer, 0, MAX_FILE_SIZE); ++ ++ g_enfs_config_info.path_detect_interval = DEFAULT_PATH_DETECT_INTERVAL; ++ g_enfs_config_info.path_detect_timeout = DEFAULT_PATH_DETECT_TIMEOUT; ++ g_enfs_config_info.multipath_timeout = DEFAULT_MULTIPATH_TIMEOUT; ++ g_enfs_config_info.multipath_state = DEFAULT_MULTIPATH_STATE; ++ g_enfs_config_info.loadbalance_mode = DEFAULT_LOADBALANCE_MODE; ++ ++ table_len = sizeof(g_check_and_assign_value) / ++ sizeof(g_check_and_assign_value[0]); ++ ++ ret = enfs_read_config_file(buffer, CONFIG_FILE_PATH); ++ if (ret != 0) { ++ kfree(buffer); ++ return ret; ++ } ++ ++ for (i = 0; i < table_len; i++) { ++ ret = enfs_get_value_from_config_file(buffer, ++ g_check_and_assign_value[i].field_name, ++ value, STRING_BUF_SIZE); ++ if (ret < 0) ++ continue; ++ ++ value[STRING_BUF_SIZE] = '\0'; ++ min = g_check_and_assign_value[i].min_value; ++ max = g_check_and_assign_value[i].max_value; ++ if (g_check_and_assign_value[i].func != NULL) ++ (*g_check_and_assign_value[i].func)( ++ g_check_and_assign_value[i].field_name, ++ value, min, max); ++ } ++ ++ kfree(buffer); ++ return ENFS_RET_OK; ++} ++ ++int32_t enfs_get_config_path_detect_interval(void) ++{ ++ return g_enfs_config_info.path_detect_interval; ++} ++ ++int32_t enfs_get_config_path_detect_timeout(void) ++{ ++ return g_enfs_config_info.path_detect_timeout; ++} ++ ++int32_t enfs_get_config_multipath_timeout(void) ++{ ++ return g_enfs_config_info.multipath_timeout; ++} ++ ++int32_t enfs_get_config_multipath_state(void) ++{ ++ return g_enfs_config_info.multipath_state; ++} ++ ++int32_t enfs_get_config_loadbalance_mode(void) ++{ ++ return g_enfs_config_info.loadbalance_mode; ++} ++ ++static bool enfs_file_changed(const char *filename) ++{ ++ int err; ++ struct kstat file_stat; ++ ++ err = vfs_stat(filename, &file_stat); ++ if (err) { ++ pr_err("failed to open file:%s err:%d\n", filename, err); ++ return false; ++ } ++ ++ if (timespec64_compare(&modify_time, &file_stat.mtime) == -1) { ++ modify_time = file_stat.mtime; ++ pr_info("file change: %lld %lld\n", modify_time.tv_sec, ++ file_stat.mtime.tv_sec); ++ return true; ++ } ++ ++ return false; ++} ++ ++static int enfs_thread_func(void *data) ++{ ++ while (!kthread_should_stop()) { ++ if (enfs_file_changed(CONFIG_FILE_PATH)) ++ enfs_config_load(); ++ ++ msleep(ENFS_NOTIFY_FILE_PERIOD); ++ } ++ return 0; ++} ++ ++int enfs_config_timer_init(void) ++{ ++ thread = kthread_run(enfs_thread_func, NULL, "enfs_notiy_file_thread"); ++ if (IS_ERR(thread)) { ++ pr_err("Failed to create kernel thread\n"); ++ return PTR_ERR(thread); ++ } ++ return 0; ++} ++ ++void enfs_config_timer_exit(void) ++{ ++ pr_info("enfs_notify_file_exit\n"); ++ if (thread) ++ kthread_stop(thread); ++} +diff --git a/fs/nfs/enfs/enfs_config.h b/fs/nfs/enfs/enfs_config.h +new file mode 100644 +index 000000000000..752710129170 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_config.h +@@ -0,0 +1,32 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs configuration ++ * Author: y00583252 ++ * Create: 2023-07-27 ++ */ ++ ++#ifndef ENFS_CONFIG_H ++#define ENFS_CONFIG_H ++ ++#include <linux/types.h> ++ ++enum enfs_multipath_state { ++ ENFS_MULTIPATH_ENABLE = 0, ++ ENFS_MULTIPATH_DISABLE = 1, ++}; ++ ++enum enfs_loadbalance_mode { ++ ENFS_LOADBALANCE_RR, ++}; ++ ++ ++int32_t enfs_get_config_path_detect_interval(void); ++int32_t enfs_get_config_path_detect_timeout(void); ++int32_t enfs_get_config_multipath_timeout(void); ++int32_t enfs_get_config_multipath_state(void); ++int32_t enfs_get_config_loadbalance_mode(void); ++int32_t enfs_config_load(void); ++int32_t enfs_config_timer_init(void); ++void enfs_config_timer_exit(void); ++#endif // ENFS_CONFIG_H +diff --git a/fs/nfs/enfs/enfs_errcode.h b/fs/nfs/enfs/enfs_errcode.h +new file mode 100644 +index 000000000000..cca47ab9a191 +--- /dev/null ++++ b/fs/nfs/enfs/enfs_errcode.h +@@ -0,0 +1,17 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs errocode ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef ENFS_ERRCODE_H ++#define ENFS_ERRCODE_H ++ ++enum { ++ ENFS_RET_OK = 0, ++ ENFS_RET_FAIL ++}; ++ ++#endif // ENFS_ERRCODE_H +diff --git a/fs/nfs/enfs/enfs_log.h b/fs/nfs/enfs/enfs_log.h +new file mode 100644 +index 000000000000..177b404f05df +--- /dev/null ++++ b/fs/nfs/enfs/enfs_log.h +@@ -0,0 +1,25 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: enfs log ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++#ifndef ENFS_LOG_H ++#define ENFS_LOG_H ++ ++#include <linux/printk.h> ++ ++#define enfs_log_info(fmt, ...) \ ++ pr_info("enfs:[%s]" pr_fmt(fmt), \ ++ __func__, ##__VA_ARGS__) ++ ++#define enfs_log_error(fmt, ...) \ ++ pr_err("enfs:[%s]" pr_fmt(fmt), \ ++ __func__, ##__VA_ARGS__) ++ ++#define enfs_log_debug(fmt, ...) \ ++ pr_debug("enfs:[%s]" pr_fmt(fmt), \ ++ __func__, ##__VA_ARGS__) ++ ++#endif // ENFS_ERRCODE_H +diff --git a/fs/nfs/enfs/failover_com.h b/fs/nfs/enfs/failover_com.h +new file mode 100644 +index 000000000000..c52940da232e +--- /dev/null ++++ b/fs/nfs/enfs/failover_com.h +@@ -0,0 +1,23 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: failover time commont header file ++ * Create: 2023-08-02 ++ */ ++#ifndef FAILOVER_COMMON_H ++#define FAILOVER_COMMON_H ++ ++static inline bool failover_is_enfs_clnt(struct rpc_clnt *clnt) ++{ ++ struct rpc_clnt *next = clnt->cl_parent; ++ ++ while (next) { ++ if (next == next->cl_parent) ++ break; ++ next = next->cl_parent; ++ } ++ ++ return next != NULL ? next->cl_enfs : clnt->cl_enfs; ++} ++ ++#endif // FAILOVER_COMMON_H +diff --git a/fs/nfs/enfs/failover_path.c b/fs/nfs/enfs/failover_path.c +new file mode 100644 +index 000000000000..93b454de29d1 +--- /dev/null ++++ b/fs/nfs/enfs/failover_path.c +@@ -0,0 +1,207 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs path failover file ++ * Author: y00583252 ++ * Create: 2023-08-02 ++ */ ++ ++#include "failover_path.h" ++#include <linux/nfs.h> ++#include <linux/nfs3.h> ++#include <linux/nfs4.h> ++#include <linux/sunrpc/clnt.h> ++#include <linux/sunrpc/sched.h> ++#include <linux/sunrpc/xprt.h> ++#include "enfs_config.h" ++#include "enfs_log.h" ++#include "failover_com.h" ++#include "pm_state.h" ++#include "pm_ping.h" ++ ++enum failover_policy_t { ++ FAILOVER_NOACTION = 1, ++ FAILOVER_RETRY, ++ FAILOVER_RETRY_DELAY, ++}; ++ ++static void failover_retry_path(struct rpc_task *task) ++{ ++ xprt_release(task); ++ rpc_init_task_retry_counters(task); ++ rpc_task_release_transport(task); ++ rpc_restart_call(task); ++} ++ ++static void failover_retry_path_delay(struct rpc_task *task, int32_t delay) ++{ ++ failover_retry_path(task); ++ rpc_delay(task, delay); ++} ++ ++static void failover_retry_path_by_policy(struct rpc_task *task, ++ enum failover_policy_t policy) ++{ ++ if (policy == FAILOVER_RETRY) ++ failover_retry_path(task); ++ else if (policy == FAILOVER_RETRY_DELAY) ++ failover_retry_path_delay(task, 3 * HZ); // delay 3s ++} ++ ++static ++enum failover_policy_t failover_get_nfs3_retry_policy(struct rpc_task *task) ++{ ++ enum failover_policy_t policy = FAILOVER_NOACTION; ++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; ++ u32 proc; ++ ++ if (unlikely(procinfo == NULL)) { ++ enfs_log_error("the task contains no valid proc.\n"); ++ return FAILOVER_NOACTION; ++ } ++ ++ proc = procinfo->p_proc; ++ ++ switch (proc) { ++ case NFS3PROC_CREATE: ++ case NFS3PROC_MKDIR: ++ case NFS3PROC_REMOVE: ++ case NFS3PROC_RMDIR: ++ case NFS3PROC_SYMLINK: ++ case NFS3PROC_LINK: ++ case NFS3PROC_SETATTR: ++ case NFS3PROC_WRITE: ++ policy = FAILOVER_RETRY_DELAY; ++ default: ++ policy = FAILOVER_RETRY; ++ } ++ return policy; ++} ++ ++static ++enum failover_policy_t failover_get_nfs4_retry_policy(struct rpc_task *task) ++{ ++ enum failover_policy_t policy = FAILOVER_NOACTION; ++ const struct rpc_procinfo *procinfo = task->tk_msg.rpc_proc; ++ u32 proc_idx; ++ ++ if (unlikely(procinfo == NULL)) { ++ enfs_log_error("the task contains no valid proc.\n"); ++ return FAILOVER_NOACTION; ++ } ++ ++ proc_idx = procinfo->p_statidx; ++ ++ switch (proc_idx) { ++ case NFSPROC4_CLNT_CREATE: ++ case NFSPROC4_CLNT_REMOVE: ++ case NFSPROC4_CLNT_LINK: ++ case NFSPROC4_CLNT_SYMLINK: ++ case NFSPROC4_CLNT_SETATTR: ++ case NFSPROC4_CLNT_WRITE: ++ case NFSPROC4_CLNT_RENAME: ++ case NFSPROC4_CLNT_SETACL: ++ policy = FAILOVER_RETRY_DELAY; ++ default: ++ policy = FAILOVER_RETRY; ++ } ++ return policy; ++} ++ ++static enum failover_policy_t failover_get_retry_policy(struct rpc_task *task) ++{ ++ struct rpc_clnt *clnt = task->tk_client; ++ u32 version = clnt->cl_vers; ++ enum failover_policy_t policy = FAILOVER_NOACTION; ++ ++ // 1. if the task meant to send to certain xprt, take no action ++ if (task->tk_flags & RPC_TASK_FIXED) ++ return FAILOVER_NOACTION; ++ ++ // 2. get policy by different version of nfs protocal ++ if (version == 3) // nfs v3 ++ policy = failover_get_nfs3_retry_policy(task); ++ else if (version == 4) // nfs v4 ++ policy = failover_get_nfs4_retry_policy(task); ++ else ++ return FAILOVER_NOACTION; ++ ++ // 3. if the task is not send to target, retry immediately ++ if (!RPC_WAS_SENT(task)) ++ policy = FAILOVER_RETRY; ++ ++ return policy; ++} ++ ++static int failover_check_task(struct rpc_task *task) ++{ ++ struct rpc_clnt *clnt = NULL; ++ int disable_mpath = enfs_get_config_multipath_state(); ++ ++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return -EINVAL; ++ } ++ ++ if (unlikely((task == NULL) || (task->tk_client == NULL))) { ++ enfs_log_error("The task is not valid.\n"); ++ return -EINVAL; ++ } ++ ++ clnt = task->tk_client; ++ ++ if (clnt->cl_prog != NFS_PROGRAM) { ++ enfs_log_debug("The clnt is not prog{%u} type.\n", ++ clnt->cl_prog); ++ return -EINVAL; ++ } ++ ++ if (!failover_is_enfs_clnt(clnt)) { ++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); ++ return -EINVAL; ++ } ++ return 0; ++} ++ ++void failover_handle(struct rpc_task *task) ++{ ++ enum failover_policy_t policy; ++ int ret; ++ ++ ret = failover_check_task(task); ++ if (ret != 0) ++ return; ++ ++ pm_set_path_state(task->tk_xprt, PM_STATE_FAULT); ++ ++ policy = failover_get_retry_policy(task); ++ ++ failover_retry_path_by_policy(task, policy); ++} ++ ++bool failover_task_need_call_start_again(struct rpc_task *task) ++{ ++ int ret; ++ ++ ret = failover_check_task(task); ++ if (ret != 0) ++ return false; ++ ++ return true; ++} ++ ++bool failover_prepare_transmit(struct rpc_task *task) ++{ ++ if (task->tk_flags & RPC_TASK_FIXED) ++ return true; ++ ++ if (pm_ping_is_test_xprt_task(task)) ++ return true; ++ ++ if (pm_get_path_state(task->tk_xprt) == PM_STATE_FAULT) { ++ task->tk_status = -ETIMEDOUT; ++ return false; ++ } ++ ++ return true; ++} +diff --git a/fs/nfs/enfs/failover_path.h b/fs/nfs/enfs/failover_path.h +new file mode 100644 +index 000000000000..6f1294829a6e +--- /dev/null ++++ b/fs/nfs/enfs/failover_path.h +@@ -0,0 +1,17 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs path failover header file ++ * Author: y00583252 ++ * Create: 2023-08-02 ++ */ ++ ++#ifndef FAILOVER_PATH_H ++#define FAILOVER_PATH_H ++ ++#include <linux/sunrpc/sched.h> ++ ++void failover_handle(struct rpc_task *task); ++bool failover_prepare_transmit(struct rpc_task *task); ++ ++#endif // FAILOVER_PATH_H +diff --git a/fs/nfs/enfs/failover_time.c b/fs/nfs/enfs/failover_time.c +new file mode 100644 +index 000000000000..866ea82d13fc +--- /dev/null ++++ b/fs/nfs/enfs/failover_time.c +@@ -0,0 +1,99 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: failover time file ++ * Create: 2023-08-02 ++ */ ++ ++#include "failover_time.h" ++#include <linux/jiffies.h> ++#include <linux/sunrpc/clnt.h> ++#include "enfs_config.h" ++#include "enfs_log.h" ++#include "failover_com.h" ++#include "pm_ping.h" ++ ++static unsigned long failover_get_mulitipath_timeout(struct rpc_clnt *clnt) ++{ ++ unsigned long config_tmo = enfs_get_config_multipath_timeout() * HZ; ++ unsigned long clnt_tmo = clnt->cl_timeout->to_initval; ++ ++ if (config_tmo == 0) ++ return clnt_tmo; ++ ++ return config_tmo > clnt_tmo ? clnt_tmo : config_tmo; ++} ++ ++void failover_adjust_task_timeout(struct rpc_task *task, void *condition) ++{ ++ struct rpc_clnt *clnt = NULL; ++ unsigned long tmo; ++ int disable_mpath = enfs_get_config_multipath_state(); ++ ++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return; ++ } ++ ++ clnt = task->tk_client; ++ if (unlikely(clnt == NULL)) { ++ enfs_log_error("task associate client is NULL.\n"); ++ return; ++ } ++ ++ if (!failover_is_enfs_clnt(clnt)) { ++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); ++ return; ++ } ++ ++ tmo = failover_get_mulitipath_timeout(clnt); ++ if (tmo == 0) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return; ++ } ++ ++ if (task->tk_timeout != 0) ++ task->tk_timeout = ++ task->tk_timeout < tmo ? task->tk_timeout : tmo; ++ else ++ task->tk_timeout = tmo; ++} ++ ++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req) ++{ ++ struct rpc_clnt *clnt = NULL; ++ int disable_mpath = enfs_get_config_multipath_state(); ++ ++ if (disable_mpath != ENFS_MULTIPATH_ENABLE) { ++ enfs_log_debug("Multipath is not enabled.\n"); ++ return; ++ } ++ ++ clnt = task->tk_client; ++ if (unlikely(clnt == NULL)) { ++ enfs_log_error("task associate client is NULL.\n"); ++ return; ++ } ++ ++ if (!failover_is_enfs_clnt(clnt)) { ++ enfs_log_debug("The clnt is not a enfs-managed type.\n"); ++ return; ++ } ++ ++ if (!pm_ping_is_test_xprt_task(task)) ++ req->rq_timeout = failover_get_mulitipath_timeout(clnt); ++ else { ++ req->rq_timeout = enfs_get_config_path_detect_timeout() * HZ; ++ req->rq_majortimeo = req->rq_timeout + jiffies; ++ } ++ ++ /* ++ * when task is retried, the req is new, we lost major-timeout times, ++ * so we have to restore req major ++ * timeouts from the task, if it is stored. ++ */ ++ if (task->tk_major_timeo != 0) ++ req->rq_majortimeo = task->tk_major_timeo; ++ else ++ task->tk_major_timeo = req->rq_majortimeo; ++} +diff --git a/fs/nfs/enfs/failover_time.h b/fs/nfs/enfs/failover_time.h +new file mode 100644 +index 000000000000..ede25b577a2a +--- /dev/null ++++ b/fs/nfs/enfs/failover_time.h +@@ -0,0 +1,16 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: failover time header file ++ * Create: 2023-08-02 ++ */ ++ ++#ifndef FAILOVER_TIME_H ++#define FAILOVER_TIME_H ++ ++#include <linux/sunrpc/sched.h> ++ ++void failover_adjust_task_timeout(struct rpc_task *task, void *condition); ++void failover_init_task_req(struct rpc_task *task, struct rpc_rqst *req); ++ ++#endif // FAILOVER_TIME_H +diff --git a/fs/nfs/enfs/init.h b/fs/nfs/enfs/init.h +new file mode 100644 +index 000000000000..fdabb9084e19 +--- /dev/null ++++ b/fs/nfs/enfs/init.h +@@ -0,0 +1,17 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs client init ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef ENFS_INIT_H ++#define ENFS_INIT_H ++ ++#include <linux/types.h> ++ ++int32_t enfs_init(void); ++void enfs_fini(void); ++ ++#endif +diff --git a/fs/nfs/enfs/mgmt_init.c b/fs/nfs/enfs/mgmt_init.c +new file mode 100644 +index 000000000000..75a40c5e0f6c +--- /dev/null ++++ b/fs/nfs/enfs/mgmt_init.c +@@ -0,0 +1,22 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: mgmt component init ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#include "mgmt_init.h" ++#include <linux/printk.h> ++#include "enfs_errcode.h" ++#include "enfs_config.h" ++ ++int32_t mgmt_init(void) ++{ ++ return enfs_config_timer_init(); ++} ++ ++void mgmt_fini(void) ++{ ++ enfs_config_timer_exit(); ++} +diff --git a/fs/nfs/enfs/mgmt_init.h b/fs/nfs/enfs/mgmt_init.h +new file mode 100644 +index 000000000000..aa78303b9f01 +--- /dev/null ++++ b/fs/nfs/enfs/mgmt_init.h +@@ -0,0 +1,18 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: mgmt component init ++ * Author: y00583252 ++ * Create: 2023-07-31 ++ */ ++ ++#ifndef MGMT_INIT_H ++#define MGMT_INIT_H ++ ++#include <linux/types.h> ++ ++int32_t mgmt_init(void); ++void mgmt_fini(void); ++ ++ ++#endif // MGMT_INIT_H +diff --git a/fs/nfs/enfs/pm_ping.c b/fs/nfs/enfs/pm_ping.c +new file mode 100644 +index 000000000000..24153cd4c7f3 +--- /dev/null ++++ b/fs/nfs/enfs/pm_ping.c +@@ -0,0 +1,421 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: path state header file ++ * Author: x00833432 ++ * Create: 2023-08-21 ++ */ ++ ++#include "pm_ping.h" ++#include <linux/err.h> ++#include <linux/spinlock.h> ++#include <linux/slab.h> ++#include <linux/module.h> ++#include <linux/printk.h> ++#include <linux/kthread.h> ++#include <linux/nfs.h> ++#include <linux/errno.h> ++#include <linux/rcupdate.h> ++#include <linux/workqueue.h> ++#include <net/netns/generic.h> ++#include <linux/atomic.h> ++#include <linux/sunrpc/clnt.h> ++ ++#include "../../../net/sunrpc/netns.h" ++#include "pm_state.h" ++#include "enfs.h" ++#include "enfs_log.h" ++#include "enfs_config.h" ++ ++#define SLEEP_INTERVAL 2 ++extern unsigned int sunrpc_net_id; ++ ++static struct task_struct *pm_ping_timer_thread; ++//protect pint_execute_workq ++static spinlock_t ping_execute_workq_lock; ++// timer for test xprt workqueue ++static struct workqueue_struct *ping_execute_workq; ++// count the ping xprt work on flight ++static atomic_t check_xprt_count; ++ ++struct ping_xprt_work { ++ struct rpc_xprt *xprt; // use this specific xprt ++ struct rpc_clnt *clnt; // use this specific rpc_client ++ struct work_struct ping_work; ++}; ++ ++struct pm_ping_async_callback { ++ void *data; ++ void (*func)(void *data); ++}; ++ ++// set xprt's enum pm_check_state ++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, ++ enum pm_check_state state) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ ++ if (IS_ERR(xprt)) { ++ enfs_log_error("The xprt ptr is not exist.\n"); ++ return; ++ } ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ xprt_get(xprt); ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ xprt_put(xprt); ++ return; ++ } ++ ++ atomic_set(&ctx->path_check_state, state); ++ xprt_put(xprt); ++} ++ ++// get xprt's enum pm_check_state ++static enum pm_check_state pm_ping_get_path_check_state(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ enum pm_check_state state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return PM_CHECK_UNDEFINE; ++ } ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ return PM_CHECK_UNDEFINE; ++ } ++ ++ state = atomic_read(&ctx->path_check_state); ++ ++ return state; ++} ++ ++static void pm_ping_call_done_callback(void *data) ++{ ++ struct pm_ping_async_callback *callback_data = ++ (struct pm_ping_async_callback *)data; ++ ++ if (callback_data == NULL) ++ return; ++ ++ callback_data->func(callback_data->data); ++ ++ kfree(callback_data); ++} ++ ++// Default callback for async RPC calls ++static void pm_ping_call_done(struct rpc_task *task, void *data) ++{ ++ struct rpc_xprt *xprt = task->tk_xprt; ++ ++ atomic_dec(&check_xprt_count); ++ if (task->tk_status >= 0) ++ pm_set_path_state(xprt, PM_STATE_NORMAL); ++ else ++ pm_set_path_state(xprt, PM_STATE_FAULT); ++ ++ pm_ping_set_path_check_state(xprt, PM_CHECK_FINISH); ++ ++ pm_ping_call_done_callback(data); ++} ++ ++// register func to rpc_call_done ++static const struct rpc_call_ops pm_ping_set_status_ops = { ++ .rpc_call_done = pm_ping_call_done, ++}; ++ ++// execute work which in work_queue ++static void pm_ping_execute_work(struct work_struct *work) ++{ ++ int ret = 0; ++ ++ // get the work information ++ struct ping_xprt_work *work_info = ++ container_of(work, struct ping_xprt_work, ping_work); ++ ++ // if check state is pending ++ if (pm_ping_get_path_check_state(work_info->xprt) == PM_CHECK_WAITING) { ++ ++ pm_ping_set_path_check_state(work_info->xprt, ++ PM_CHECK_CHECKING); ++ ++ ret = rpc_clnt_test_xprt(work_info->clnt, ++ work_info->xprt, ++ &pm_ping_set_status_ops, ++ NULL, ++ RPC_TASK_ASYNC | RPC_TASK_FIXED); ++ ++ if (ret < 0) { ++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); ++ ++ pm_ping_set_path_check_state(work_info->xprt, ++ PM_CHECK_FINISH); ++ ++ } else ++ atomic_inc(&check_xprt_count); ++ ++ } ++ ++ atomic_dec(&work_info->clnt->cl_count); ++ xprt_put(work_info->xprt); ++ kfree(work_info); ++ work_info = NULL; ++} ++ ++static bool pm_ping_workqueue_queue_work(struct work_struct *work) ++{ ++ bool ret = false; ++ ++ spin_lock(&ping_execute_workq_lock); ++ ++ if (ping_execute_workq != NULL) ++ ret = queue_work(ping_execute_workq, work); ++ ++ spin_unlock(&ping_execute_workq_lock); ++ return ret; ++} ++ ++// init test work and add this work to workqueue ++static int pm_ping_add_work(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, void *data) ++{ ++ struct ping_xprt_work *work_info; ++ bool ret = false; ++ ++ if (IS_ERR(xprt) || xprt == NULL) { ++ enfs_log_error("The xprt ptr is not exist.\n"); ++ return -EINVAL; ++ } ++ ++ if (IS_ERR(clnt) || clnt == NULL) { ++ enfs_log_error("The clnt ptr is not exist.\n"); ++ return -EINVAL; ++ } ++ ++ if (!xprt->multipath_context) { ++ enfs_log_error("multipath_context is null.\n"); ++ return -EINVAL; ++ } ++ ++ // check xprt pending status, if pending status equals Finish ++ // means this xprt can inster to work queue ++ if (pm_ping_get_path_check_state(xprt) == ++ PM_CHECK_FINISH || ++ pm_ping_get_path_check_state(xprt) == ++ PM_CHECK_INIT) { ++ ++ enfs_log_debug("find xprt pointer. %p\n", xprt); ++ work_info = kzalloc(sizeof(struct ping_xprt_work), GFP_ATOMIC); ++ if (work_info == NULL) ++ return -ENOMEM; ++ work_info->clnt = clnt; ++ atomic_inc(&clnt->cl_count); ++ work_info->xprt = xprt; ++ xprt_get(xprt); ++ INIT_WORK(&work_info->ping_work, pm_ping_execute_work); ++ pm_ping_set_path_check_state(xprt, PM_CHECK_WAITING); ++ ++ ret = pm_ping_workqueue_queue_work(&work_info->ping_work); ++ if (!ret) { ++ atomic_dec(&work_info->clnt->cl_count); ++ xprt_put(work_info->xprt); ++ kfree(work_info); ++ return -EINVAL; ++ } ++ } ++ return 0; ++} ++ ++// encapsulate pm_ping_add_work() ++static int pm_ping_execute_xprt_test(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, void *data) ++{ ++ pm_ping_add_work(clnt, xprt, NULL); ++ // return 0 for rpc_clnt_iterate_for_each_xprt(); ++ // because negative value will stop iterate all xprt ++ // and we need return negative value for debug ++ // Therefore, we need this function to iterate all xprt ++ return 0; ++} ++ ++// export to other module add ping work to workqueue ++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) ++{ ++ int ret; ++ ++ ret = pm_ping_add_work(clnt, xprt, NULL); ++ return ret; ++} ++ ++// iterate xprt in the client ++static void pm_ping_loop_rpclnt(struct sunrpc_net *sn) ++{ ++ struct rpc_clnt *clnt; ++ ++ spin_lock(&sn->rpc_client_lock); ++ list_for_each_entry_rcu(clnt, &sn->all_clients, cl_clients) { ++ if (clnt->cl_enfs) { ++ enfs_log_debug("find rpc_clnt. %p\n", clnt); ++ rpc_clnt_iterate_for_each_xprt(clnt, ++ pm_ping_execute_xprt_test, NULL); ++ } ++ } ++ spin_unlock(&sn->rpc_client_lock); ++} ++ ++// iterate each clnt in the sunrpc_net ++static void pm_ping_loop_sunrpc_net(void) ++{ ++ struct net *net; ++ struct sunrpc_net *sn; ++ ++ rcu_read_lock(); ++ for_each_net_rcu(net) { ++ sn = net_generic(net, sunrpc_net_id); ++ if (sn == NULL) ++ continue; ++ pm_ping_loop_rpclnt(sn); ++ } ++ rcu_read_unlock(); ++} ++ ++static int pm_ping_routine(void *data) ++{ ++ while (!kthread_should_stop()) { ++ // equale 0 means open multipath ++ if (enfs_get_config_multipath_state() == ++ ENFS_MULTIPATH_ENABLE) ++ pm_ping_loop_sunrpc_net(); ++ ++ msleep((unsigned int) ++ enfs_get_config_path_detect_interval() * 1000); ++ } ++ return 0; ++} ++ ++// start thread to cycly ping ++static int pm_ping_start(void) ++{ ++ pm_ping_timer_thread = ++ kthread_run(pm_ping_routine, NULL, "pm_ping_routine"); ++ if (IS_ERR(pm_ping_timer_thread)) { ++ enfs_log_error("Failed to create kernel thread\n"); ++ return PTR_ERR(pm_ping_timer_thread); ++ } ++ return 0; ++} ++ ++// initialize workqueue ++static int pm_ping_workqueue_init(void) ++{ ++ struct workqueue_struct *queue = NULL; ++ ++ queue = create_workqueue("pm_ping_workqueue"); ++ ++ if (queue == NULL) { ++ enfs_log_error("create workqueue failed.\n"); ++ return -ENOMEM; ++ } ++ ++ spin_lock(&ping_execute_workq_lock); ++ ping_execute_workq = queue; ++ spin_unlock(&ping_execute_workq_lock); ++ enfs_log_info("create workqueue succeeeded.\n"); ++ return 0; ++} ++ ++static void pm_ping_workqueue_fini(void) ++{ ++ struct workqueue_struct *queue = NULL; ++ ++ spin_lock(&ping_execute_workq_lock); ++ queue = ping_execute_workq; ++ ping_execute_workq = NULL; ++ spin_unlock(&ping_execute_workq_lock); ++ ++ enfs_log_info("delete work queue\n"); ++ ++ if (queue != NULL) { ++ flush_workqueue(queue); ++ destroy_workqueue(queue); ++ } ++} ++ ++// module exit func ++void pm_ping_fini(void) ++{ ++ if (pm_ping_timer_thread) ++ kthread_stop(pm_ping_timer_thread); ++ ++ pm_ping_workqueue_fini(); ++ ++ while (atomic_read(&check_xprt_count) != 0) ++ msleep(SLEEP_INTERVAL); ++} ++ ++// module init func ++int pm_ping_init(void) ++{ ++ int ret; ++ ++ atomic_set(&check_xprt_count, 0); ++ ret = pm_ping_workqueue_init(); ++ if (ret != 0) { ++ enfs_log_error("PM_PING Module loading failed.\n"); ++ return ret; ++ } ++ ret = pm_ping_start(); ++ if (ret != 0) { ++ enfs_log_error("PM_PING Module loading failed.\n"); ++ pm_ping_workqueue_fini(); ++ return ret; ++ } ++ ++ return ret; ++} ++ ++bool pm_ping_is_test_xprt_task(struct rpc_task *task) ++{ ++ return task->tk_ops == &pm_ping_set_status_ops ? true : false; ++} ++ ++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void (*func)(void *data), ++ void *data) ++{ ++ int ret; ++ ++ struct pm_ping_async_callback *callback_data = ++ kzalloc(sizeof(struct pm_ping_async_callback), GFP_KERNEL); ++ ++ if (callback_data == NULL) { ++ enfs_log_error("failed to mzalloc mem\n"); ++ return -ENOMEM; ++ } ++ ++ callback_data->data = data; ++ callback_data->func = func; ++ atomic_inc(&check_xprt_count); ++ ret = rpc_clnt_test_xprt(clnt, xprt, ++ &pm_ping_set_status_ops, ++ callback_data, ++ RPC_TASK_ASYNC | RPC_TASK_FIXED); ++ ++ if (ret < 0) { ++ enfs_log_debug("ping xprt execute failed ,ret %d", ret); ++ atomic_dec(&check_xprt_count); ++ } ++ ++ return ret; ++} +diff --git a/fs/nfs/enfs/pm_ping.h b/fs/nfs/enfs/pm_ping.h +new file mode 100644 +index 000000000000..6bcb94bfc836 +--- /dev/null ++++ b/fs/nfs/enfs/pm_ping.h +@@ -0,0 +1,33 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: nfs configuration ++ * Author: x00833432 ++ * Create: 2023-07-27 ++ */ ++ ++#ifndef PM_PING_H ++#define PM_PING_H ++ ++#include <linux/sunrpc/clnt.h> ++ ++enum pm_check_state { ++ PM_CHECK_INIT, // this xprt never been queued ++ PM_CHECK_WAITING, // this xprt waiting in the queue ++ PM_CHECK_CHECKING, // this xprt is testing ++ PM_CHECK_FINISH, // this xprt has been finished ++ PM_CHECK_UNDEFINE, // undefine multipath struct ++}; ++ ++int pm_ping_init(void); ++void pm_ping_fini(void); ++int pm_ping_rpc_test_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt); ++void pm_ping_set_path_check_state(struct rpc_xprt *xprt, ++ enum pm_check_state state); ++bool pm_ping_is_test_xprt_task(struct rpc_task *task); ++int pm_ping_rpc_test_xprt_with_callback(struct rpc_clnt *clnt, ++ struct rpc_xprt *xprt, ++ void (*func)(void *data), ++ void *data); ++ ++#endif // PM_PING_H +diff --git a/fs/nfs/enfs/pm_state.c b/fs/nfs/enfs/pm_state.c +new file mode 100644 +index 000000000000..220621a207a2 +--- /dev/null ++++ b/fs/nfs/enfs/pm_state.c +@@ -0,0 +1,158 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: path state file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++#include "pm_state.h" ++#include <linux/sunrpc/xprt.h> ++ ++#include "enfs.h" ++#include "enfs_log.h" ++ ++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ enum pm_path_state state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return PM_STATE_UNDEFINED; ++ } ++ ++ xprt_get(xprt); ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ xprt_put(xprt); ++ return PM_STATE_UNDEFINED; ++ } ++ ++ state = atomic_read(&ctx->path_state); ++ ++ xprt_put(xprt); ++ ++ return state; ++} ++ ++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state) ++{ ++ struct enfs_xprt_context *ctx = NULL; ++ enum pm_path_state cur_state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ xprt_get(xprt); ++ ++ ctx = (struct enfs_xprt_context *)xprt->multipath_context; ++ if (ctx == NULL) { ++ enfs_log_error("The xprt multipath ctx is not valid.\n"); ++ xprt_put(xprt); ++ return; ++ } ++ ++ cur_state = atomic_read(&ctx->path_state); ++ if (cur_state == state) { ++ enfs_log_debug("The xprt is already {%d}.\n", state); ++ xprt_put(xprt); ++ return; ++ } ++ ++ atomic_set(&ctx->path_state, state); ++ enfs_log_info("The xprt {%p} path state change from {%d} to {%d}.\n", ++ xprt, cur_state, state); ++ ++ xprt_put(xprt); ++} ++ ++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len) ++{ ++ enum pm_path_state state; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ if ((buf == NULL) || (len <= 0)) { ++ enfs_log_error("Buffer is not valid, len=%d.\n", len); ++ return; ++ } ++ ++ state = pm_get_path_state(xprt); ++ ++ switch (state) { ++ case PM_STATE_INIT: ++ (void)snprintf(buf, len, "Init"); ++ break; ++ case PM_STATE_NORMAL: ++ (void)snprintf(buf, len, "Normal"); ++ break; ++ case PM_STATE_FAULT: ++ (void)snprintf(buf, len, "Fault"); ++ break; ++ default: ++ (void)snprintf(buf, len, "Unknown"); ++ break; ++ } ++} ++ ++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len) ++{ ++ int i; ++ unsigned long state; ++ static unsigned long xprt_mask[] = { ++ XPRT_LOCKED, XPRT_CONNECTED, ++ XPRT_CONNECTING, XPRT_CLOSE_WAIT, ++ XPRT_BOUND, XPRT_BINDING, XPRT_CLOSING, ++ XPRT_CONGESTED}; ++ ++ static const char *const xprt_state_desc[] = { ++ "LOCKED", "CONNECTED", "CONNECTING", ++ "CLOSE_WAIT", "BOUND", "BINDING", ++ "CLOSING", "CONGESTED"}; ++ int pos = 0; ++ int ret = 0; ++ ++ if (xprt == NULL) { ++ enfs_log_error("The xprt is not valid.\n"); ++ return; ++ } ++ ++ if ((buf == NULL) || (len <= 0)) { ++ enfs_log_error( ++ "Xprt state buffer is not valid, len=%d.\n", ++ len); ++ return; ++ } ++ ++ xprt_get(xprt); ++ state = READ_ONCE(xprt->state); ++ xprt_put(xprt); ++ ++ for (i = 0; i < ARRAY_SIZE(xprt_mask); ++i) { ++ if (pos >= len) ++ break; ++ ++ if (!test_bit(xprt_mask[i], &state)) ++ continue; ++ ++ if (pos == 0) ++ ret = snprintf(buf, len, "%s", xprt_state_desc[i]); ++ else ++ ret = snprintf(buf + pos, len - pos, "|%s", ++ xprt_state_desc[i]); ++ ++ if (ret < 0) { ++ enfs_log_error("format state failed, ret %d.\n", ret); ++ break; ++ } ++ ++ pos += ret; ++ } ++} +diff --git a/fs/nfs/enfs/pm_state.h b/fs/nfs/enfs/pm_state.h +new file mode 100644 +index 000000000000..f5f52e5ab91d +--- /dev/null ++++ b/fs/nfs/enfs/pm_state.h +@@ -0,0 +1,28 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++/* ++ * Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved. ++ * Description: path state header file ++ * Author: y00583252 ++ * Create: 2023-08-12 ++ */ ++ ++#ifndef PM_STATE_H ++#define PM_STATE_H ++ ++#include <linux/types.h> ++#include <linux/sunrpc/xprt.h> ++ ++enum pm_path_state { ++ PM_STATE_INIT, ++ PM_STATE_NORMAL, ++ PM_STATE_FAULT, ++ PM_STATE_UNDEFINED // xprt is not multipath xprt ++}; ++ ++void pm_set_path_state(struct rpc_xprt *xprt, enum pm_path_state state); ++enum pm_path_state pm_get_path_state(struct rpc_xprt *xprt); ++ ++void pm_get_path_state_desc(struct rpc_xprt *xprt, char *buf, int len); ++void pm_get_xprt_state_desc(struct rpc_xprt *xprt, char *buf, int len); ++ ++#endif // PM_STATE_H diff --git a/0006-add_enfs_compile_option.patch b/0006-add_enfs_compile_option.patch new file mode 100644 index 0000000..ff3bc0e --- /dev/null +++ b/0006-add_enfs_compile_option.patch @@ -0,0 +1,70 @@ +diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig +index b04256636d4b..ae53510c0627 100644 +--- a/arch/arm64/configs/openeuler_defconfig ++++ b/arch/arm64/configs/openeuler_defconfig +@@ -5344,6 +5344,7 @@ CONFIG_LOCKD=m + CONFIG_LOCKD_V4=y + CONFIG_NFS_ACL_SUPPORT=m + CONFIG_NFS_COMMON=y ++# CONFIG_ENFS is not set + CONFIG_SUNRPC=m + CONFIG_SUNRPC_GSS=m + CONFIG_SUNRPC_BACKCHANNEL=y +diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig +index 59baeb2973af..ccc317f7fdb2 100644 +--- a/arch/x86/configs/openeuler_defconfig ++++ b/arch/x86/configs/openeuler_defconfig +@@ -6825,6 +6825,7 @@ CONFIG_LOCKD=m + CONFIG_LOCKD_V4=y + CONFIG_NFS_ACL_SUPPORT=m + CONFIG_NFS_COMMON=y ++CONFIG_ENFS=y + CONFIG_SUNRPC=m + CONFIG_SUNRPC_GSS=m + CONFIG_SUNRPC_BACKCHANNEL=y +diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig +index e55f86713948..872c9b7671b1 100644 +--- a/fs/nfs/Kconfig ++++ b/fs/nfs/Kconfig +@@ -196,3 +196,14 @@ config NFS_DEBUG + depends on NFS_FS && SUNRPC_DEBUG + select CRC32 + default y ++ ++config ENFS ++ tristate "NFS client support for ENFS" ++ depends on NFS_FS ++ default n ++ help ++ This option enables support multipath of the NFS protocol ++ in the kernel's NFS client. ++ This feature will improve performance and reliability. ++ ++ If sure, say Y. +diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile +index c587e3c4c6a6..19d0ac2ba3b8 100644 +--- a/fs/nfs/Makefile ++++ b/fs/nfs/Makefile +@@ -12,6 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ + nfs-$(CONFIG_ROOT_NFS) += nfsroot.o + nfs-$(CONFIG_SYSCTL) += sysctl.o + nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o ++nfs-$(CONFIG_ENFS) += enfs_adapter.o + + obj-$(CONFIG_NFS_V2) += nfsv2.o + nfsv2-y := nfs2super.o proc.o nfs2xdr.o +@@ -34,3 +35,5 @@ nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o + obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ + obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ + obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ ++ ++obj-$(CONFIG_ENFS) += enfs/ +diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile +index 090658c3da12..fe4e3b28c5d1 100644 +--- a/net/sunrpc/Makefile ++++ b/net/sunrpc/Makefile +@@ -19,3 +19,4 @@ sunrpc-$(CONFIG_SUNRPC_DEBUG) += debugfs.o + sunrpc-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel_rqst.o + sunrpc-$(CONFIG_PROC_FS) += stats.o + sunrpc-$(CONFIG_SYSCTL) += sysctl.o ++sunrpc-$(CONFIG_ENFS) += sunrpc_enfs_adapter.o -- 2.25.0.windows.1

1 0

[PATCH openEuler-1.0-LTS] netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c
by Lu Wei 25 Sep '23

25 Sep '23

From: Kyle Zeng <zengyhkyle(a)gmail.com> mainline inclusion from mainline-v4.20-rc2 commit 886503f34d63e681662057448819edb5b1057a97 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I83QCZ CVE: CVE-2023-42753 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- The missing IP_SET_HASH_WITH_NET0 macro in ip_set_hash_netportnet can lead to the use of wrong `CIDR_POS(c)` for calculating array offsets, which can lead to integer underflow. As a result, it leads to slab out-of-bound access. This patch adds back the IP_SET_HASH_WITH_NET0 macro to ip_set_hash_netportnet to address the issue. Fixes: 886503f34d63 ("netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net") Suggested-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> Acked-by: Jozsef Kadlecsik <kadlec(a)netfilter.org> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/netfilter/ipset/ip_set_hash_netportnet.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 613e18e720a4..9290a4d7b862 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -39,6 +39,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net"); #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 +#define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ -- 2.34.1

2 1

[PATCH openEuler-23.09] gpio: loongson: Add 3A/3B/3C/7A gpio dirver support
by Ming Wang 25 Sep '23

25 Sep '23

LoongArch inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6BWFP -------------------------------- Signed-off-by: Juxin Gao <gaojuxin(a)loongson.cn> Signed-off-by: Ming Wang <wangming01(a)loongson.cn> --- drivers/gpio/Kconfig | 3 +- drivers/gpio/gpio-loongson.c | 414 ++++++++++++++++++++++++++++------- 2 files changed, 341 insertions(+), 76 deletions(-) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index f45c6a36551c..be0cf9c87cd6 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -377,7 +377,8 @@ config GPIO_LOGICVC config GPIO_LOONGSON bool "Loongson-2/3 GPIO support" - depends on CPU_LOONGSON2EF || CPU_LOONGSON64 + depends on CPU_LOONGSON2EF || CPU_LOONGSON64 || LOONGARCH + default m help Driver for GPIO functionality on Loongson-2F/3A/3B processors. diff --git a/drivers/gpio/gpio-loongson.c b/drivers/gpio/gpio-loongson.c index a42145873cc9..a3a3d647a043 100644 --- a/drivers/gpio/gpio-loongson.c +++ b/drivers/gpio/gpio-loongson.c @@ -1,13 +1,13 @@ -// SPDX-License-Identifier: GPL-2.0-or-later /* - * Loongson-2F/3A/3B GPIO Support + * Loongson-3A/3B/3C/7A GPIO Support * - * Copyright (c) 2008 Richard Liu, STMicroelectronics <richard.liu(a)st.com> - * Copyright (c) 2008-2010 Arnaud Patard <apatard(a)mandriva.com> - * Copyright (c) 2013 Hongbing Hu <huhb(a)lemote.com> - * Copyright (c) 2014 Huacai Chen <chenhc(a)lemote.com> + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. */ +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> @@ -16,120 +16,384 @@ #include <linux/gpio/driver.h> #include <linux/platform_device.h> #include <linux/bitops.h> +#include <linux/property.h> #include <asm/types.h> -#include <loongson.h> -#define STLS2F_N_GPIO 4 -#define STLS3A_N_GPIO 16 +/* ============== Data structrues =============== */ -#ifdef CONFIG_CPU_LOONGSON64 -#define LOONGSON_N_GPIO STLS3A_N_GPIO -#else -#define LOONGSON_N_GPIO STLS2F_N_GPIO -#endif +/* gpio data */ +struct platform_gpio_data { + u32 gpio_conf; + u32 gpio_out; + u32 gpio_in; + u32 in_start_bit; + u32 support_irq; + char *label; + int gpio_base; + int ngpio; +}; + +#define GPIO_IO_CONF(x) (x->base + x->conf_offset) +#define GPIO_OUT(x) (x->base + x->out_offset) +#define GPIO_IN(x) (x->base + x->in_offset) + +#define LS7A_GPIO_OEN_BYTE(x, gpio) (x->base + x->conf_offset + gpio) +#define LS7A_GPIO_OUT_BYTE(x, gpio) (x->base + x->out_offset + gpio) +#define LS7A_GPIO_IN_BYTE(x, gpio) (x->base + x->in_offset + gpio) + +struct loongson_gpio_chip { + struct gpio_chip chip; + spinlock_t lock; + void __iomem *base; + int conf_offset; + int out_offset; + int in_offset; + int in_start_bit; + u16 *gsi_idx_map; + u16 mapsize; + bool support_irq; +}; /* - * Offset into the register where we read lines, we write them from offset 0. - * This offset is the only thing that stand between us and using - * GPIO_GENERIC. + * GPIO primitives. */ -#define LOONGSON_GPIO_IN_OFFSET 16 +static int loongson_gpio_request(struct gpio_chip *chip, unsigned int pin) +{ + if (pin >= chip->ngpio) + return -EINVAL; + else + return 0; +} + +static inline void +__set_direction(struct loongson_gpio_chip *lgpio, unsigned int pin, int input) +{ + u64 temp; + u8 value; -static DEFINE_SPINLOCK(gpio_lock); + if (!strcmp(lgpio->chip.label, "loongson,loongson3-gpio") || + !strncmp(lgpio->chip.label, "LOON0007", 8)) { + temp = readq(GPIO_IO_CONF(lgpio)); + if (input) + temp |= 1ULL << pin; + else + temp &= ~(1ULL << pin); + writeq(temp, GPIO_IO_CONF(lgpio)); + return; + } + if (!strcmp(lgpio->chip.label, "loongson,ls7a-gpio") || + !strncmp(lgpio->chip.label, "LOON0002", 8)) { + if (input) + value = 1; + else + value = 0; + writeb(value, LS7A_GPIO_OEN_BYTE(lgpio, pin)); + return; + } +} -static int loongson_gpio_get_value(struct gpio_chip *chip, unsigned gpio) +static void __set_level(struct loongson_gpio_chip *lgpio, unsigned int pin, int high) { - u32 val; + u64 temp; + u8 value; - spin_lock(&gpio_lock); - val = LOONGSON_GPIODATA; - spin_unlock(&gpio_lock); + /* If GPIO controller is on 3A,then... */ + if (!strcmp(lgpio->chip.label, "loongson,loongson3-gpio") || + !strncmp(lgpio->chip.label, "LOON0007", 8)) { + temp = readq(GPIO_OUT(lgpio)); + if (high) + temp |= 1ULL << pin; + else + temp &= ~(1ULL << pin); + writeq(temp, GPIO_OUT(lgpio)); + return; + } - return !!(val & BIT(gpio + LOONGSON_GPIO_IN_OFFSET)); + if (!strcmp(lgpio->chip.label, "loongson,ls7a-gpio") || + !strncmp(lgpio->chip.label, "LOON0002", 8)) { + if (high) + value = 1; + else + value = 0; + writeb(value, LS7A_GPIO_OUT_BYTE(lgpio, pin)); + return; + } } -static void loongson_gpio_set_value(struct gpio_chip *chip, - unsigned gpio, int value) +static int loongson_gpio_direction_input(struct gpio_chip *chip, unsigned int pin) { - u32 val; + unsigned long flags; + struct loongson_gpio_chip *lgpio = + container_of(chip, struct loongson_gpio_chip, chip); - spin_lock(&gpio_lock); - val = LOONGSON_GPIODATA; - if (value) - val |= BIT(gpio); - else - val &= ~BIT(gpio); - LOONGSON_GPIODATA = val; - spin_unlock(&gpio_lock); + spin_lock_irqsave(&lgpio->lock, flags); + __set_direction(lgpio, pin, 1); + spin_unlock_irqrestore(&lgpio->lock, flags); + + return 0; } -static int loongson_gpio_direction_input(struct gpio_chip *chip, unsigned gpio) +static int loongson_gpio_direction_output(struct gpio_chip *chip, + unsigned int pin, int value) { - u32 temp; + struct loongson_gpio_chip *lgpio = + container_of(chip, struct loongson_gpio_chip, chip); + unsigned long flags; - spin_lock(&gpio_lock); - temp = LOONGSON_GPIOIE; - temp |= BIT(gpio); - LOONGSON_GPIOIE = temp; - spin_unlock(&gpio_lock); + spin_lock_irqsave(&lgpio->lock, flags); + __set_level(lgpio, pin, value); + __set_direction(lgpio, pin, 0); + spin_unlock_irqrestore(&lgpio->lock, flags); return 0; } -static int loongson_gpio_direction_output(struct gpio_chip *chip, - unsigned gpio, int level) +static int loongson_gpio_get(struct gpio_chip *chip, unsigned int pin) { - u32 temp; + struct loongson_gpio_chip *lgpio = + container_of(chip, struct loongson_gpio_chip, chip); + u64 temp; + u8 value; + + /* GPIO controller in 3A is different for 7A */ + if (!strcmp(lgpio->chip.label, "loongson,loongson3-gpio") || + !strncmp(lgpio->chip.label, "LOON0007", 8)) { + temp = readq(GPIO_IN(lgpio)); + return ((temp & (1ULL << (pin + lgpio->in_start_bit))) != 0); + } + + if (!strcmp(lgpio->chip.label, "loongson,ls7a-gpio") || + !strncmp(lgpio->chip.label, "LOON0002", 8)) { + value = readb(LS7A_GPIO_IN_BYTE(lgpio, pin)); + return (value & 1); + } + + return -ENXIO; +} + +static void loongson_gpio_set(struct gpio_chip *chip, unsigned int pin, int value) +{ + struct loongson_gpio_chip *lgpio = + container_of(chip, struct loongson_gpio_chip, chip); + unsigned long flags; + + spin_lock_irqsave(&lgpio->lock, flags); + __set_level(lgpio, pin, value); + spin_unlock_irqrestore(&lgpio->lock, flags); +} + +static int loongson_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) +{ + struct platform_device *pdev = + container_of(chip->parent, struct platform_device, dev); + struct loongson_gpio_chip *lgpio = + container_of(chip, struct loongson_gpio_chip, chip); + + if (offset >= chip->ngpio) + return -EINVAL; + + if ((lgpio->gsi_idx_map != NULL) && (offset < lgpio->mapsize)) + offset = lgpio->gsi_idx_map[offset]; + + return platform_get_irq(pdev, offset); +} + +static int loongson_gpio_init(struct device *dev, struct loongson_gpio_chip *lgpio, + struct device_node *np, + void __iomem *base) +{ + lgpio->chip.request = loongson_gpio_request; + lgpio->chip.direction_input = loongson_gpio_direction_input; + lgpio->chip.get = loongson_gpio_get; + lgpio->chip.direction_output = loongson_gpio_direction_output; + lgpio->chip.set = loongson_gpio_set; + lgpio->chip.can_sleep = 0; + lgpio->chip.fwnode = dev_fwnode(dev); + lgpio->chip.parent = dev; + spin_lock_init(&lgpio->lock); + lgpio->base = (void __iomem *)base; + + if (!strcmp(lgpio->chip.label, "loongson,ls7a-gpio") || + !strncmp(lgpio->chip.label, "LOON0002", 8) || + !strcmp(lgpio->chip.label, "loongson,loongson3-gpio") || + !strncmp(lgpio->chip.label, "LOON0007", 8)) { - loongson_gpio_set_value(chip, gpio, level); - spin_lock(&gpio_lock); - temp = LOONGSON_GPIOIE; - temp &= ~BIT(gpio); - LOONGSON_GPIOIE = temp; - spin_unlock(&gpio_lock); + lgpio->chip.to_irq = loongson_gpio_to_irq; + } + gpiochip_add(&lgpio->chip); return 0; } + +static void of_loongson_gpio_get_props(struct device_node *np, + struct loongson_gpio_chip *lgpio) +{ + const char *name; + + of_property_read_u32(np, "ngpios", (u32 *)&lgpio->chip.ngpio); + of_property_read_u32(np, "gpio_base", (u32 *)&lgpio->chip.base); + of_property_read_u32(np, "conf_offset", (u32 *)&lgpio->conf_offset); + of_property_read_u32(np, "out_offset", (u32 *)&lgpio->out_offset); + of_property_read_u32(np, "in_offset", (u32 *)&lgpio->in_offset); + of_property_read_string(np, "compatible", &name); + if (!strcmp(name, "loongson,loongson3-gpio")) { + of_property_read_u32(np, "in_start_bit", + (u32 *)&lgpio->in_start_bit); + if (of_property_read_bool(np, "support_irq")) + lgpio->support_irq = true; + } + lgpio->chip.label = kstrdup(name, GFP_KERNEL); +} + +static void acpi_loongson_gpio_get_props(struct platform_device *pdev, + struct loongson_gpio_chip *lgpio) +{ + + struct device *dev = &pdev->dev; + int rval; + + device_property_read_u32(dev, "ngpios", (u32 *)&lgpio->chip.ngpio); + device_property_read_u32(dev, "gpio_base", (u32 *)&lgpio->chip.base); + device_property_read_u32(dev, "conf_offset", (u32 *)&lgpio->conf_offset); + device_property_read_u32(dev, "out_offset", (u32 *)&lgpio->out_offset); + device_property_read_u32(dev, "in_offset", (u32 *)&lgpio->in_offset); + rval = device_property_read_u16_array(dev, "gsi_idx_map", NULL, 0); + if (rval > 0) { + lgpio->gsi_idx_map = + kmalloc_array(rval, sizeof(*lgpio->gsi_idx_map), + GFP_KERNEL); + if (unlikely(!lgpio->gsi_idx_map)) { + dev_err(dev, "Alloc gsi_idx_map fail!\n"); + } else { + lgpio->mapsize = rval; + device_property_read_u16_array(dev, "gsi_idx_map", + lgpio->gsi_idx_map, lgpio->mapsize); + } + } + if (!strcmp(pdev->name, "LOON0007")) { + device_property_read_u32(dev, "in_start_bit", + (u32 *)&lgpio->in_start_bit); + if (device_property_read_bool(dev, "support_irq")) + lgpio->support_irq = true; + } + lgpio->chip.label = kstrdup(pdev->name, GFP_KERNEL); +} + +static void platform_loongson_gpio_get_props(struct platform_device *pdev, + struct loongson_gpio_chip *lgpio) +{ + struct platform_gpio_data *gpio_data = + (struct platform_gpio_data *)pdev->dev.platform_data; + + lgpio->chip.ngpio = gpio_data->ngpio; + lgpio->chip.base = gpio_data->gpio_base; + lgpio->conf_offset = gpio_data->gpio_conf; + lgpio->out_offset = gpio_data->gpio_out; + lgpio->in_offset = gpio_data->gpio_in; + if (!strcmp(gpio_data->label, "loongson,loongson3-gpio")) { + lgpio->in_start_bit = gpio_data->in_start_bit; + lgpio->support_irq = gpio_data->support_irq; + } + lgpio->chip.label = kstrdup(gpio_data->label, GFP_KERNEL); +} + static int loongson_gpio_probe(struct platform_device *pdev) { - struct gpio_chip *gc; + struct resource *iores; + void __iomem *base; + struct loongson_gpio_chip *lgpio; + struct device_node *np = pdev->dev.of_node; struct device *dev = &pdev->dev; + int ret = 0; - gc = devm_kzalloc(dev, sizeof(*gc), GFP_KERNEL); - if (!gc) + lgpio = kzalloc(sizeof(struct loongson_gpio_chip), GFP_KERNEL); + if (!lgpio) return -ENOMEM; - gc->label = "loongson-gpio-chip"; - gc->base = 0; - gc->ngpio = LOONGSON_N_GPIO; - gc->get = loongson_gpio_get_value; - gc->set = loongson_gpio_set_value; - gc->direction_input = loongson_gpio_direction_input; - gc->direction_output = loongson_gpio_direction_output; + if (np) + of_loongson_gpio_get_props(np, lgpio); + else if (ACPI_COMPANION(&pdev->dev)) + acpi_loongson_gpio_get_props(pdev, lgpio); + else + platform_loongson_gpio_get_props(pdev, lgpio); + + iores = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!iores) { + ret = -ENODEV; + goto out; + } + if (!request_mem_region(iores->start, resource_size(iores), + pdev->name)) { + ret = -EBUSY; + goto out; + } + base = ioremap(iores->start, resource_size(iores)); + if (!base) { + ret = -ENOMEM; + goto out; + } + platform_set_drvdata(pdev, lgpio); + loongson_gpio_init(dev, lgpio, np, base); - return gpiochip_add_data(gc, NULL); + return 0; +out: + pr_err("%s: %s: missing mandatory property\n", __func__, np->name); + return ret; } -static struct platform_driver loongson_gpio_driver = { +static int loongson_gpio_remove(struct platform_device *pdev) +{ + struct loongson_gpio_chip *lgpio = platform_get_drvdata(pdev); + struct resource *mem; + + platform_set_drvdata(pdev, NULL); + gpiochip_remove(&lgpio->chip); + iounmap(lgpio->base); + kfree(lgpio->gsi_idx_map); + kfree(lgpio); + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + release_mem_region(mem->start, resource_size(mem)); + return 0; +} + +static const struct of_device_id loongson_gpio_dt_ids[] = { + { .compatible = "loongson,loongson3-gpio"}, + { .compatible = "loongson,ls7a-gpio"}, + {} +}; +MODULE_DEVICE_TABLE(of, loongson_gpio_dt_ids); + +static const struct acpi_device_id loongson_gpio_acpi_match[] = { + {"LOON0002"}, + {"LOON0007"}, + {} +}; +MODULE_DEVICE_TABLE(acpi, loongson_gpio_acpi_match); + +static struct platform_driver ls_gpio_driver = { .driver = { .name = "loongson-gpio", + .owner = THIS_MODULE, + .of_match_table = loongson_gpio_dt_ids, + .acpi_match_table = ACPI_PTR(loongson_gpio_acpi_match), }, .probe = loongson_gpio_probe, + .remove = loongson_gpio_remove, }; static int __init loongson_gpio_setup(void) { - struct platform_device *pdev; - int ret; - - ret = platform_driver_register(&loongson_gpio_driver); - if (ret) { - pr_err("error registering loongson GPIO driver\n"); - return ret; - } + return platform_driver_register(&ls_gpio_driver); +} +subsys_initcall(loongson_gpio_setup); - pdev = platform_device_register_simple("loongson-gpio", -1, NULL, 0); - return PTR_ERR_OR_ZERO(pdev); +static void __exit loongson_gpio_driver(void) +{ + platform_driver_unregister(&ls_gpio_driver); } -postcore_initcall(loongson_gpio_setup); +module_exit(loongson_gpio_driver); +MODULE_AUTHOR("Loongson Technology Corporation Limited"); +MODULE_DESCRIPTION("LOONGSON GPIO"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:loongson_gpio"); -- 2.39.2

2 1

[PATCH OLK-5.10] scsi: lpfc: Fix ioremap issues in lpfc_sli4_pci_mem_setup()
by Yong Hu 25 Sep '23

25 Sep '23

From: Shuchang Li <lishuchang(a)hust.edu.cn> stable inclusion from stable-v5.10.180 commit bab8dc38b1a0a12bc064fc064269033bdcf5b88e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZCDZ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit 91a0c0c1413239d0548b5aac4c82f38f6d53a91e ] When if_type equals zero and pci_resource_start(pdev, PCI_64BIT_BAR4) returns false, drbl_regs_memmap_p is not remapped. This passes a NULL pointer to iounmap(), which can trigger a WARN() on certain arches. When if_type equals six and pci_resource_start(pdev, PCI_64BIT_BAR4) returns true, drbl_regs_memmap_p may has been remapped and ctrl_regs_memmap_p is not remapped. This is a resource leak and passes a NULL pointer to iounmap(). To fix these issues, we need to add null checks before iounmap(), and change some goto labels. Fixes: 1351e69fc6db ("scsi: lpfc: Add push-to-adapter support to sli4") Signed-off-by: Shuchang Li <lishuchang(a)hust.edu.cn> Link: https://lore.kernel.org/r/20230404072133.1022-1-lishuchang@hust.edu.cn Reviewed-by: Justin Tee <justin.tee(a)broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yong Hu <yong.hu(a)windriver.com> --- drivers/scsi/lpfc/lpfc_init.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 17200b453cbb..1bb3c96a04bd 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -10477,7 +10477,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) goto out_iounmap_all; } else { error = -ENOMEM; - goto out_iounmap_all; + goto out_iounmap_ctrl; } } @@ -10495,7 +10495,7 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) dev_err(&pdev->dev, "ioremap failed for SLI4 HBA dpp registers.\n"); error = -ENOMEM; - goto out_iounmap_ctrl; + goto out_iounmap_all; } phba->pci_bar4_memmap_p = phba->sli4_hba.dpp_regs_memmap_p; } @@ -10520,9 +10520,11 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) return 0; out_iounmap_all: - iounmap(phba->sli4_hba.drbl_regs_memmap_p); + if (phba->sli4_hba.drbl_regs_memmap_p) + iounmap(phba->sli4_hba.drbl_regs_memmap_p); out_iounmap_ctrl: - iounmap(phba->sli4_hba.ctrl_regs_memmap_p); + if (phba->sli4_hba.ctrl_regs_memmap_p) + iounmap(phba->sli4_hba.ctrl_regs_memmap_p); out_iounmap_conf: iounmap(phba->sli4_hba.conf_regs_memmap_p); -- 2.34.1

2 1

[PATCH OLK-5.10] scsi: lpfc: Prevent lpfc_debugfs_lockstat_write() buffer overflow
by Yong Hu 25 Sep '23

25 Sep '23

From: Justin Tee <justin.tee(a)broadcom.com> stable inclusion from stable-v5.10.181 commit e0e7faee3a7dd6f51350cda64997116a247eb045 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZCDZ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit c6087b82a9146826564a55c5ca0164cac40348f5 ] A static code analysis tool flagged the possibility of buffer overflow when using copy_from_user() for a debugfs entry. Currently, it is possible that copy_from_user() copies more bytes than what would fit in the mybuf char array. Add a min() restriction check between sizeof(mybuf) - 1 and nbytes passed from the userspace buffer to protect against buffer overflow. Link: https://lore.kernel.org/r/20230301231626.9621-2-justintee8345@gmail.com Signed-off-by: Justin Tee <justin.tee(a)broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yong Hu <yong.hu(a)windriver.com> --- drivers/scsi/lpfc/lpfc_debugfs.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index fbc76d69ea0b..2b77cbbcdccb 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -2159,10 +2159,13 @@ lpfc_debugfs_lockstat_write(struct file *file, const char __user *buf, char mybuf[64]; char *pbuf; int i; + size_t bsize; memset(mybuf, 0, sizeof(mybuf)); - if (copy_from_user(mybuf, buf, nbytes)) + bsize = min(nbytes, (sizeof(mybuf) - 1)); + + if (copy_from_user(mybuf, buf, bsize)) return -EFAULT; pbuf = &mybuf[0]; @@ -2183,7 +2186,7 @@ lpfc_debugfs_lockstat_write(struct file *file, const char __user *buf, qp->lock_conflict.wq_access = 0; } } - return nbytes; + return bsize; } #endif -- 2.34.1

2 1

[PATCH openEuler-23.09 0/5] LoongArch: add old BPI compatibility
by yangyinglu 25 Sep '23

25 Sep '23

yangyinglu (5): LoongArch: add kernel setvirtmap for runtime LoongArch: Old BPI compatibility LoongArch: Fix virtual machine startup error LoongArch: Fixed EIOINTC structure members LoongArch: use arch specific phys_to_dma arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/addrspace.h | 1 + arch/loongarch/include/asm/efi.h | 1 + arch/loongarch/include/asm/irq.h | 1 + arch/loongarch/include/asm/loongarch.h | 1 + arch/loongarch/kernel/Makefile | 1 + arch/loongarch/kernel/acpi.c | 7 +- arch/loongarch/kernel/dma.c | 26 +- arch/loongarch/kernel/efi.c | 175 ++++++++- arch/loongarch/kernel/env.c | 6 + arch/loongarch/kernel/irq.c | 25 +- arch/loongarch/kernel/legacy_boot.c | 484 +++++++++++++++++++++++++ arch/loongarch/kernel/legacy_boot.h | 90 +++++ arch/loongarch/kernel/mem.c | 26 +- arch/loongarch/kernel/numa.c | 39 +- arch/loongarch/kernel/reset.c | 3 +- arch/loongarch/kernel/setup.c | 18 +- arch/loongarch/kernel/smp.c | 6 +- arch/loongarch/pci/acpi.c | 147 +++++++- drivers/firmware/efi/Makefile | 1 + drivers/irqchip/irq-loongarch-cpu.c | 7 +- drivers/irqchip/irq-loongson-eiointc.c | 46 ++- drivers/irqchip/irq-loongson-pch-pic.c | 5 + 23 files changed, 1075 insertions(+), 42 deletions(-) create mode 100644 arch/loongarch/kernel/legacy_boot.c create mode 100644 arch/loongarch/kernel/legacy_boot.h -- 2.20.1

2 6

[PATCH openEuler-23.09 0/5] LoongArch: add rtc driver and fix
by Ming Wang 25 Sep '23

25 Sep '23

Ming Wang (5): rtc: Add rtc driver for the Loongson family chips LoongArch: kdump: Add memory reservation for old kernel LoongArch: kexec: Add compatibility with old interfaces LoongArch: Fix kdump failure on v40 interface specification LoongArch: kdump: Add high memory reservation arch/loongarch/kernel/machine_kexec.c | 45 ++- arch/loongarch/kernel/setup.c | 94 +++++- drivers/rtc/Kconfig | 13 + drivers/rtc/Makefile | 1 + drivers/rtc/rtc-loongson.c | 397 ++++++++++++++++++++++++++ 5 files changed, 535 insertions(+), 15 deletions(-) create mode 100644 drivers/rtc/rtc-loongson.c -- 2.39.2

2 6

启动 openEuler 2023 年度优秀项目推荐
by Huxinwei 25 Sep '23

25 Sep '23

各位社区的开发者：经 openEuler技术委员会9月20日会议讨论，现正式启动 openEuler 2023年度优秀项目的评选，请各位社区开发者和参与者推荐。当前在评选标准和项目设置上的考虑，可以参见：oEEP (openeuler.org)<https://www.openeuler.org/zh/oEEP/?name=oEEP-0007%20openEuler%E4%BC%98%E7%A…> 。截止 2023 年 10 月 15 日（周日）为止，任意三名以上社区参与者联名，可以向 tc(a)openeuler.org<mailto:tc@openeuler.org> 推荐您认可的项目。推荐项目的邮件请在邮件主题中明确包含 “openEuler 2023 年度优秀项目推荐” 字样。推荐项目的邮件内容中，请明确联名推荐人的邮箱地址和相应的 gitee id，推荐的项目名称，项目代码仓位置，推荐获奖的方向。我将汇总所有推荐，在 10 月 18 日之前通过社区邮件列表公示。欢迎大家的参与和推荐 Regards openEuler Technical Committee

1 0

[PATCH openEuler-23.09 0/4] LoongArch: Add cpufreq and BMC
by Weihao Li 25 Sep '23

25 Sep '23

Weihao Li (4): cpufreq: Add cpufreq driver for LoongArch fbdev: add ls2k500sfb driver for ls2k500 bmc. ipmi: add ls2k500 bmc ipmi support. LoongArch: defconfig: enable CONFIG_FB_LS2K500=m. arch/loongarch/Kconfig | 6 + arch/loongarch/configs/loongson3_defconfig | 5 + arch/loongarch/include/asm/fpu.h | 13 +- drivers/char/ipmi/Makefile | 4 + drivers/char/ipmi/btlock.h | 92 ++ drivers/char/ipmi/ipmi_si.h | 11 + drivers/char/ipmi/ipmi_si_intf.c | 4 + drivers/char/ipmi/ipmi_si_ls2k500.c | 172 +++ drivers/char/ipmi/kcs_bmc_ls2k500.h | 67 + drivers/cpufreq/Kconfig | 11 + drivers/cpufreq/Makefile | 1 + drivers/cpufreq/loongson3-acpi-cpufreq.c | 1549 ++++++++++++++++++++ drivers/video/fbdev/Kconfig | 9 + drivers/video/fbdev/Makefile | 1 + drivers/video/fbdev/ls2k500sfb.c | 791 ++++++++++ 15 files changed, 2735 insertions(+), 1 deletion(-) create mode 100644 drivers/char/ipmi/btlock.h create mode 100644 drivers/char/ipmi/ipmi_si_ls2k500.c create mode 100644 drivers/char/ipmi/kcs_bmc_ls2k500.h create mode 100644 drivers/cpufreq/loongson3-acpi-cpufreq.c create mode 100644 drivers/video/fbdev/ls2k500sfb.c -- 2.20.1

2 5

[PATCH openEuler-23.09 0/5] LoongArch: add rtc driver and fix
by Ming Wang 25 Sep '23

25 Sep '23

Ming Wang (5): rtc: Add rtc driver for the Loongson family chips LoongArch: kdump: Add memory reservation for old kernel LoongArch: kexec: Add compatibility with old interfaces LoongArch: Fix kdump failure on v40 interface specification LoongArch: kdump: Add high memory reservation arch/loongarch/kernel/machine_kexec.c | 45 ++- arch/loongarch/kernel/setup.c | 94 +++++- drivers/rtc/Kconfig | 13 + drivers/rtc/Makefile | 1 + drivers/rtc/rtc-loongson.c | 397 ++++++++++++++++++++++++++ 5 files changed, 535 insertions(+), 15 deletions(-) create mode 100644 drivers/rtc/rtc-loongson.c -- 2.39.2

1 5

[PATCH OLK-5.10] sdei_watchdog: Avoid exception during sdei handler
by Zheng Zengkai 23 Sep '23

23 Sep '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I82QPR -------------------------------- On Kunpeng920 platform, when firmware triggers SDEI event too soon, A WARN_ON() will be called in sdei_watchdog_callback(), this leads to warning "sdei: unsafe: exception during handler" being reported in _sdei_handler(). As the comments for the warning mentioned, We took a synchronous exception from the SDEI handler. This could deadlock, and if you interrupt KVM it will hyp-panic instead. Remove the WARN_ON() to avoid potential issue and warning. Fixes: 0fa83fd0f8f7 ("sdei_watchdog: avoid possible false hardlockup") Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/arm64/kernel/watchdog_sdei.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/kernel/watchdog_sdei.c b/arch/arm64/kernel/watchdog_sdei.c index aa980b090598..7fd8c2d3dd1b 100644 --- a/arch/arm64/kernel/watchdog_sdei.c +++ b/arch/arm64/kernel/watchdog_sdei.c @@ -78,7 +78,6 @@ static int sdei_watchdog_callback(u32 event, if (delta < watchdog_thresh * (u64)NSEC_PER_SEC * 4 / 5) { pr_err(FW_BUG "SDEI Watchdog event triggered too soon, " "time to last check:%lld ns\n", delta); - WARN_ON(1); return 0; } -- 2.20.1

2 1

[PATCH openEuler-1.0-LTS] sdei_watchdog: Avoid exception during sdei handler
by Zheng Zengkai 23 Sep '23

23 Sep '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I82QPR -------------------------------- On Kunpeng920 platform, when firmware triggers SDEI event too soon, A WARN_ON() will be called in sdei_watchdog_callback(), this leads to warning "sdei: unsafe: exception during handler" being reported in _sdei_handler(). As the comments for the warning mentioned, We took a synchronous exception from the SDEI handler. This could deadlock, and if you interrupt KVM it will hyp-panic instead. Remove the WARN_ON() to avoid potential issue and warning. Fixes: 37433b57ffdd ("sdei_watchdog: avoid possible false hardlockup") Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/arm64/kernel/watchdog_sdei.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/kernel/watchdog_sdei.c b/arch/arm64/kernel/watchdog_sdei.c index a499a14b23c1..5884abdaeb9d 100644 --- a/arch/arm64/kernel/watchdog_sdei.c +++ b/arch/arm64/kernel/watchdog_sdei.c @@ -78,7 +78,6 @@ static int sdei_watchdog_callback(u32 event, if (delta < watchdog_thresh * (u64)NSEC_PER_SEC * 4 / 5) { pr_err(FW_BUG "SDEI Watchdog event triggered too soon, " "time to last check:%lld ns\n", delta); - WARN_ON(1); return 0; } -- 2.20.1

2 1

[PATCH 01/88] scsi: mpt3sas: Define hba_port structure
by Hao Zhang 22 Sep '23

22 Sep '23

From: Sreekanth Reddy <sreekanth.reddy(a)broadcom.com> Commit b22a0fac8c056e88fc72f7241fa9077b804634a6 upstream. Define a new hba_port structure which holds the following variables: - port_id: Port ID of the narrow/wide port of the HBA - sas_address: SAS Address of the remote device that is attached to the current HBA port - phy_mask: HBA's phy bits to which above SAS addressed device is attached - flags: This field is used to refresh port details during HBA reset Link: https://lore.kernel.org/r/20201027130847.9962-2-sreekanth.reddy@broadcom.com Signed-off-by: Sreekanth Reddy <sreekanth.reddy(a)broadcom.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Integrated-by: Siyu Zhang <siyu.zhang(a)windriver.com> --- drivers/scsi/mpt3sas/mpt3sas_base.h | 35 ++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 86774747fe25..9a3429b1e7ce 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -420,6 +420,7 @@ struct Mpi2ManufacturingPage11_t { * @flags: MPT_TARGET_FLAGS_XXX flags * @deleted: target flaged for deletion * @tm_busy: target is busy with TM request. + * @port: hba port entry containing target's port number info * @sas_dev: The sas_device associated with this target * @pcie_dev: The pcie device associated with this target */ @@ -432,6 +433,7 @@ struct MPT3SAS_TARGET { u32 flags; u8 deleted; u8 tm_busy; + struct hba_port *port; struct _sas_device *sas_dev; struct _pcie_device *pcie_dev; }; @@ -534,6 +536,7 @@ struct _internal_cmd { * addition routine. * @chassis_slot: chassis slot * @is_chassis_slot_valid: chassis slot valid or not + * @port: hba port entry containing device's port number info */ struct _sas_device { struct list_head list; @@ -560,6 +563,7 @@ struct _sas_device { u8 is_chassis_slot_valid; u8 connector_name[5]; struct kref refcount; + struct hba_port *port; }; static inline void sas_device_get(struct _sas_device *s) @@ -730,6 +734,7 @@ struct _boot_device { * @remote_identify: attached device identification * @rphy: sas transport rphy object * @port: sas transport wide/narrow port object + * @hba_port: hba port entry containing port's port number info * @phy_list: _sas_phy list objects belonging to this port */ struct _sas_port { @@ -738,6 +743,7 @@ struct _sas_port { struct sas_identify remote_identify; struct sas_rphy *rphy; struct sas_port *port; + struct hba_port *hba_port; struct list_head phy_list; }; @@ -751,6 +757,7 @@ struct _sas_port { * @handle: device handle for this phy * @attached_handle: device handle for attached device * @phy_belongs_to_port: port has been created for this phy + * @port: hba port entry containing port number info */ struct _sas_phy { struct list_head port_siblings; @@ -761,6 +768,7 @@ struct _sas_phy { u16 handle; u16 attached_handle; u8 phy_belongs_to_port; + struct hba_port *port; }; /** @@ -776,6 +784,7 @@ struct _sas_phy { * @responding: used in _scsih_expander_device_mark_responding * @phy: a list of phys that make up this sas_host/expander * @sas_port_list: list of ports attached to this sas_host/expander + * @port: hba port entry containing node's port number info */ struct _sas_node { struct list_head list; @@ -787,11 +796,11 @@ struct _sas_node { u16 enclosure_handle; u64 enclosure_logical_id; u8 responding; + struct hba_port *port; struct _sas_phy *phy; struct list_head sas_port_list; }; - /** * struct _enclosure_node - enclosure information * @list: list of enclosures @@ -1009,6 +1018,27 @@ struct reply_post_struct { dma_addr_t reply_post_free_dma; }; +/** + * struct hba_port - Saves each HBA's Wide/Narrow port info + * @sas_address: sas address of this wide/narrow port's attached device + * @phy_mask: HBA PHY's belonging to this port + * @port_id: port number + * @flags: hba port flags + */ +struct hba_port { + struct list_head list; + u64 sas_address; + u32 phy_mask; + u8 port_id; + u8 flags; +}; + +/* hba port flags */ +#define HBA_PORT_FLAG_DIRTY_PORT 0x01 +#define HBA_PORT_FLAG_NEW_PORT 0x02 + +#define MULTIPATH_DISABLED_PORT_ID 0xFF + typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc); /** * struct MPT3SAS_ADAPTER - per adapter struct @@ -1191,6 +1221,7 @@ typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc); * which ensures the syncrhonization between cli/sysfs_show path. * @atomic_desc_capable: Atomic Request Descriptor support. * @GET_MSIX_INDEX: Get the msix index of high iops queues. + * @port_table_list: list containing HBA's wide/narrow port's info */ struct MPT3SAS_ADAPTER { struct list_head list; @@ -1483,6 +1514,8 @@ struct MPT3SAS_ADAPTER { PUT_SMID_IO_FP_HIP put_smid_hi_priority; PUT_SMID_DEFAULT put_smid_default; GET_MSIX_INDEX get_msix_index_for_smlio; + + struct list_head port_table_list; }; struct mpt3sas_debugfs_buffer { -- 2.33.0

1 87

openEuler kernel SIG双周例会
by openEuler conference 22 Sep '23

22 Sep '23

您好！ Kernel SIG 邀请您参加 2023-09-22 14:15 召开的WeLink会议(自动录制) 会议主题：openEuler kernel SIG双周例会会议链接：https://bmeeting.huaweicloud.com:36443/#/j/984839769 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the WeLink conference(auto recording) will be held at 2023-09-22 14:15, The subject of the conference is openEuler kernel SIG双周例会, You can join the meeting at https://bmeeting.huaweicloud.com:36443/#/j/984839769. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

（备用）openEuler Kernel SIG双周例会
by openEuler conference 22 Sep '23

22 Sep '23

您好！ Kernel SIG 邀请您参加 2023-09-22 14:15 召开的Zoom会议(自动录制) 会议主题：（备用）openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中会议链接：https://us06web.zoom.us/j/83148210957?pwd=UO852Qaa2nEd3cIHULjWDmtCAmZ90O.1 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-09-22 14:15, The subject of the conference is （备用）openEuler Kernel SIG双周例会, Summary: 1. 进展update 2. 议题征集中 You can join the meeting at https://us06web.zoom.us/j/83148210957?pwd=UO852Qaa2nEd3cIHULjWDmtCAmZ90O.1. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS] cpuidle: Fix kobject memory leaks in error paths
by Xia Fukun 22 Sep '23

22 Sep '23

From: Anel Orazgaliyeva <anelkz(a)amazon.de> stable inclusion from stable-v4.19.294 commit 22d44652b6d6404b96a40bb051d1046e6c005ae5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I81G0T CVE: NA -------------------------------- [ Upstream commit e5f5a66c9aa9c331da5527c2e3fd9394e7091e01 ] Commit c343bf1ba5ef ("cpuidle: Fix three reference count leaks") fixes the cleanup of kobjects; however, it removes kfree() calls altogether, leading to memory leaks. Fix those and also defer the initialization of dev->kobj_dev until after the error check, so that we do not end up with a dangling pointer. Fixes: c343bf1ba5ef ("cpuidle: Fix three reference count leaks") Signed-off-by: Anel Orazgaliyeva <anelkz(a)amazon.de> Suggested-by: Aman Priyadarshi <apeureka(a)amazon.de> [ rjw: Subject edits ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Xia Fukun <xiafukun(a)huawei.com> --- drivers/cpuidle/sysfs.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 38986a36197e..76fcd45eadb5 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -481,6 +481,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device) &kdev->kobj, "state%d", i); if (ret) { kobject_put(&kobj->kobj); + kfree(kobj); goto error_state; } cpuidle_add_s2idle_attr_group(kobj); @@ -612,6 +613,7 @@ static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev) &kdev->kobj, "driver"); if (ret) { kobject_put(&kdrv->kobj); + kfree(kdrv); return ret; } @@ -698,7 +700,6 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev) if (!kdev) return -ENOMEM; kdev->dev = dev; - dev->kobj_dev = kdev; init_completion(&kdev->kobj_unregister); @@ -706,9 +707,11 @@ int cpuidle_add_sysfs(struct cpuidle_device *dev) "cpuidle"); if (error) { kobject_put(&kdev->kobj); + kfree(kdev); return error; } + dev->kobj_dev = kdev; kobject_uevent(&kdev->kobj, KOBJ_ADD); return 0; -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] cec-api: prevent leaking memory through hole in structure
by Zhao Wenhui 21 Sep '23

21 Sep '23

From: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> mainline inclusion from mainline-v5.9-rc1 commit 6c42227c3467549ddc65efe99c869021d2f4a570 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I82DIP CVE: CVE-2020-36766 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Fix this smatch warning: drivers/media/cec/core/cec-api.c:156 cec_adap_g_log_addrs() warn: check that 'log_addrs' doesn't leak information (struct has a hole after 'features') Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org> Signed-off-by: Zhao Wenhui <zhaowenhui8(a)huawei.com> --- drivers/media/cec/cec-api.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c index 4961573850d5..b2b3f779592f 100644 --- a/drivers/media/cec/cec-api.c +++ b/drivers/media/cec/cec-api.c @@ -147,7 +147,13 @@ static long cec_adap_g_log_addrs(struct cec_adapter *adap, struct cec_log_addrs log_addrs; mutex_lock(&adap->lock); - log_addrs = adap->log_addrs; + /* + * We use memcpy here instead of assignment since there is a + * hole at the end of struct cec_log_addrs that an assignment + * might ignore. So when we do copy_to_user() we could leak + * one byte of memory. + */ + memcpy(&log_addrs, &adap->log_addrs, sizeof(log_addrs)); if (!adap->is_configured) memset(log_addrs.log_addr, CEC_LOG_ADDR_INVALID, sizeof(log_addrs.log_addr)); -- 2.34.1

2 1

[PATCH OLK-5.10] etmem: Fixed an issue where the module reference counting is incorrect
by liubo 21 Sep '23

21 Sep '23

euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I839LV CVE: NA ---------------------------------------------------- When the /proc/pid/idle_page and /proc/pid/swap_page are opened, the try_module_get command is used to add reference counting to prevent the module from being released. However, if the file fails to be opened, the reference count must be correctly released in the abnormal process. Signed-off-by: liubo <liubo254(a)huawei.com> --- fs/proc/task_mmu.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 502893304027..9182d0c6d22c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1911,15 +1911,20 @@ static int mm_idle_open(struct inode *inode, struct file *file) } mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR(mm)) + if (IS_ERR(mm)) { + module_put(module); return PTR_ERR(mm); + } file->private_data = mm; if (proc_page_scan_operations.open) - return proc_page_scan_operations.open(inode, file); + ret = proc_page_scan_operations.open(inode, file); - return 0; + if (ret != 0) + module_put(module); + + return ret; } static int mm_idle_release(struct inode *inode, struct file *file) @@ -2004,15 +2009,20 @@ static int mm_swap_open(struct inode *inode, struct file *file) } mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR(mm)) + if (IS_ERR(mm)) { + module_put(module); return PTR_ERR(mm); + } file->private_data = mm; if (proc_swap_pages_operations.open) - return proc_swap_pages_operations.open(inode, file); + ret = proc_swap_pages_operations.open(inode, file); - return 0; + if (ret != 0) + module_put(module); + + return ret; } static int mm_swap_release(struct inode *inode, struct file *file) -- 2.33.0

2 1

[PATCH openEuler-1.0-LTS] crypto: hisilicon - reset before init the device
by wangyuan 21 Sep '23

21 Sep '23

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I830AI CVE: NA -------------------------------- Before initializing the device, reset the device to clear the residual data to prevent unexpected problems, such as reboot scene, which may maintain device state before reboot. Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/hpre/hpre_main.c | 68 +++++++++++-------- drivers/crypto/hisilicon/qm.c | 83 ++++++++++++++++------- drivers/crypto/hisilicon/rde/rde_main.c | 64 ++++++++--------- drivers/crypto/hisilicon/sec2/sec_main.c | 39 ++++++----- drivers/crypto/hisilicon/zip/zip_main.c | 42 +++++++----- 5 files changed, 175 insertions(+), 121 deletions(-) diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index 1a980f255ad4..cbe8ea438fd2 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -780,28 +780,6 @@ static void hpre_debugfs_exit(struct hisi_qm *qm) debugfs_remove_recursive(qm->debug.debug_root); } -static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) -{ - int ret; - - qm->algs = "rsa\ndh\n"; - qm->uacce_mode = uacce_mode; - qm->pdev = pdev; - ret = hisi_qm_pre_init(qm, pf_q_num, HPRE_PF_DEF_Q_BASE); - if (ret) - return ret; - if (qm->ver == QM_HW_V1) { - pci_warn(pdev, "HPRE version 1 is not supported!\n"); - return -EINVAL; - } - - qm->qm_list = &hpre_devices; - qm->sqe_size = HPRE_SQE_SIZE; - qm->dev_name = hpre_name; - - return 0; -} - static void hpre_log_hw_error(struct hisi_qm *qm, u32 err_sts) { const struct hpre_hw_error *err = hpre_hw_errors; @@ -836,30 +814,36 @@ static void hpre_open_axi_master_ooo(struct hisi_qm *qm) HPRE_ADDR(qm, HPRE_AM_OOO_SHUTDOWN_ENB)); } -static int hpre_pf_probe_init(struct hisi_qm *qm) +static void hpre_err_ini_set(struct hisi_qm *qm) { - int ret; - - if (qm->ver != QM_HW_V2) - return -EINVAL; + if (qm->fun_type == QM_HW_VF) + return; - qm->ctrl_q_num = HPRE_QUEUE_NUM_V2; qm->err_ini.get_dev_hw_err_status = hpre_get_hw_err_status; qm->err_ini.clear_dev_hw_err_status = hpre_clear_hw_err_status; qm->err_ini.err_info.ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR | - HPRE_OOO_ECC_2BIT_ERR; + HPRE_OOO_ECC_2BIT_ERR; qm->err_ini.err_info.ce = QM_BASE_CE; qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; qm->err_ini.err_info.fe = 0; qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; qm->err_ini.err_info.acpi_rst = "HRST"; - qm->err_ini.hw_err_disable = hpre_hw_error_disable; qm->err_ini.hw_err_enable = hpre_hw_error_enable; qm->err_ini.set_usr_domain_cache = hpre_set_user_domain_and_cache; qm->err_ini.log_dev_hw_err = hpre_log_hw_error; qm->err_ini.open_axi_master_ooo = hpre_open_axi_master_ooo; qm->err_ini.err_info.msi_wr_port = HPRE_WR_MSI_PORT; +} + +static int hpre_pf_probe_init(struct hisi_qm *qm) +{ + int ret; + + if (qm->ver != QM_HW_V2) + return -EINVAL; + + qm->ctrl_q_num = HPRE_QUEUE_NUM_V2; ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) @@ -870,6 +854,30 @@ static int hpre_pf_probe_init(struct hisi_qm *qm) return 0; } +static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) +{ + int ret; + + qm->algs = "rsa\ndh\n"; + qm->uacce_mode = uacce_mode; + qm->pdev = pdev; + ret = hisi_qm_pre_init(qm, pf_q_num, HPRE_PF_DEF_Q_BASE); + if (ret) + return ret; + + if (qm->ver == QM_HW_V1) { + pci_warn(pdev, "HPRE version 1 is not supported!\n"); + return -EINVAL; + } + + qm->qm_list = &hpre_devices; + qm->sqe_size = HPRE_SQE_SIZE; + qm->dev_name = hpre_name; + hpre_err_ini_set(qm); + + return 0; +} + static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct hisi_qm *qm; diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 739b1a6565fd..f2706dc0d55e 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -230,6 +230,7 @@ #define QMC_ALIGN(sz) ALIGN(sz, 32) static int __hisi_qm_start(struct hisi_qm *qm); +static int qm_reset_device(struct hisi_qm *qm); enum vft_type { SQC_VFT = 0, @@ -2584,6 +2585,30 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) return ret; } +static int qm_clear_device(struct hisi_qm *qm) +{ + u32 val; + int ret; + + if (qm->fun_type == QM_HW_VF) + return 0; + + /* OOO register set and check */ + writel(MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + MASTER_GLOBAL_CTRL); + + ret = readl_relaxed_poll_timeout(qm->io_base + MASTER_TRANS_RETURN, + val, (val == MASTER_TRANS_RETURN_RW), + QM_REG_RD_INTVRL_US, + QM_REG_RD_TMOUT_US); + if (ret) { + pci_warn(qm->pdev, "Device is busy, can not clear device.\n"); + writel(0x0, qm->io_base + MASTER_GLOBAL_CTRL); + return ret; + } + + return qm_reset_device(qm); +} + static int hisi_qm_pci_init(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -2626,8 +2651,14 @@ static int hisi_qm_pci_init(struct hisi_qm *qm) goto err_set_mask_and_coherent; } + ret = qm_clear_device(qm); + if (ret) + goto err_free_vectors; + return 0; +err_free_vectors: + pci_free_irq_vectors(pdev); err_set_mask_and_coherent: devm_iounmap(dev, qm->io_base); err_ioremap: @@ -3808,6 +3839,34 @@ static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) } } +static int qm_reset_device(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + unsigned long long value = 0; + acpi_status s; + + /* The reset related sub-control registers are not in PCI BAR */ + if (ACPI_HANDLE(&pdev->dev)) { + s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), + qm->err_ini.err_info.acpi_rst, + NULL, &value); + if (ACPI_FAILURE(s)) { + pci_err(pdev, "NO controller reset method!\n"); + return -EIO; + } + + if (value) { + pci_err(pdev, "Reset step %llu failed!\n", value); + return -EIO; + } + + return 0; + } + + pci_err(pdev, "No reset method!\n"); + return -EINVAL; +} + static int qm_soft_reset(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -3853,29 +3912,7 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - /* The reset related sub-control registers are not in PCI BAR */ - if (ACPI_HANDLE(&pdev->dev)) { - unsigned long long value = 0; - acpi_status s; - - s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), - qm->err_ini.err_info.acpi_rst, - NULL, &value); - if (ACPI_FAILURE(s)) { - pci_err(pdev, "NO controller reset method!\n"); - return -EIO; - } - - if (value) { - pci_err(pdev, "Reset step %llu failed!\n", value); - return -EIO; - } - } else { - pci_err(pdev, "No reset method!\n"); - return -EINVAL; - } - - return 0; + return qm_reset_device(qm); } static int qm_vf_reset_done(struct pci_dev *pdev, diff --git a/drivers/crypto/hisilicon/rde/rde_main.c b/drivers/crypto/hisilicon/rde/rde_main.c index f3f70079aa77..f2e00ff891db 100644 --- a/drivers/crypto/hisilicon/rde/rde_main.c +++ b/drivers/crypto/hisilicon/rde/rde_main.c @@ -28,15 +28,8 @@ #define HRDE_QUEUE_NUM_V2 1024 #define HRDE_PCI_DEVICE_ID 0xa25a #define HRDE_SQE_SIZE 64 -#define HRDE_SQ_SIZE (HRDE_SQE_SIZE * QM_Q_DEPTH) #define HRDE_PF_DEF_Q_NUM 64 #define HRDE_PF_DEF_Q_BASE 0 -#define HRDE_RD_INTVRL_US 10 -#define HRDE_RD_TMOUT_US 1000 -#define HRDE_RST_TMOUT_MS 400 -#define HRDE_ENABLE 1 -#define HRDE_DISABLE 0 -#define HRDE_PCI_COMMAND_INVALID 0xFFFFFFFF #define HRDE_RAS_INT_MSK 0x310290 #define HRDE_RAS_CE_MSK BIT(2) @@ -101,7 +94,7 @@ static struct hisi_qm_list rde_devices; static void hisi_rde_ras_proc(struct work_struct *work); static const struct hisi_rde_hw_error rde_hw_error[] = { - {.int_msk = BIT(0), .msg = "Rde_ecc_1bitt_err"}, + {.int_msk = BIT(0), .msg = "Rde_ecc_1bit_err"}, {.int_msk = BIT(1), .msg = "Rde_ecc_2bit_err"}, {.int_msk = BIT(2), .msg = "Rde_stat_mgmt_state_timeout_err"}, {.int_msk = BIT(3), .msg = "Rde_data_wr_state_timeout_err"}, @@ -269,7 +262,7 @@ static int hisi_rde_set_user_domain_and_cache(struct hisi_qm *qm) writel(AXI_M_CFG, qm->io_base + QM_AXI_M_CFG); writel(AXI_M_CFG_ENABLE, qm->io_base + QM_AXI_M_CFG_ENABLE); - /* disable BME/PM/SRIOV FLR*/ + /* disable BME/PM/SRIOV FLR */ writel(PEH_AXUSER_CFG, qm->io_base + QM_PEH_AXUSER_CFG); writel(PEH_AXUSER_CFG_ENABLE, qm->io_base + QM_PEH_AXUSER_CFG_ENABLE); @@ -351,7 +344,7 @@ static int current_qm_write(struct ctrl_debug_file *file, u32 val) u32 tmp; if (val > 0) { - pr_err("Function id should be smaller than 0.\n"); + pr_err("Function id should be equal to 0.\n"); return -EINVAL; } @@ -423,7 +416,7 @@ static ssize_t ctrl_debug_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ctrl_debug_file *file = filp->private_data; - char tbuf[20]; + char tbuf[HRDE_DBGFS_VAL_MAX_LEN]; unsigned long val; int len, ret; @@ -623,6 +616,24 @@ static void hisi_rde_open_master_ooo(struct hisi_qm *qm) writel(val | HRDE_AXI_SHUTDOWN_EN, qm->io_base + HRDE_CFG); } +static void hisi_rde_err_ini_set(struct hisi_qm *qm) +{ + qm->err_ini.get_dev_hw_err_status = hisi_rde_get_hw_err_status; + qm->err_ini.clear_dev_hw_err_status = hisi_rde_clear_hw_err_status; + qm->err_ini.err_info.ecc_2bits_mask = HRDE_ECC_2BIT_ERR; + qm->err_ini.err_info.ce = QM_BASE_CE; + qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; + qm->err_ini.err_info.fe = 0; + qm->err_ini.err_info.msi = 0; + qm->err_ini.err_info.acpi_rst = "RRST"; + qm->err_ini.hw_err_disable = hisi_rde_hw_error_disable; + qm->err_ini.hw_err_enable = hisi_rde_hw_error_enable; + qm->err_ini.set_usr_domain_cache = hisi_rde_set_user_domain_and_cache; + qm->err_ini.log_dev_hw_err = hisi_rde_hw_error_log; + qm->err_ini.open_axi_master_ooo = hisi_rde_open_master_ooo; + qm->err_ini.err_info.msi_wr_port = HRDE_WR_MSI_PORT; +} + static int hisi_rde_pf_probe_init(struct hisi_qm *qm) { struct hisi_rde *hisi_rde = container_of(qm, struct hisi_rde, qm); @@ -649,21 +660,6 @@ static int hisi_rde_pf_probe_init(struct hisi_qm *qm) return -EINVAL; } - qm->err_ini.get_dev_hw_err_status = hisi_rde_get_hw_err_status; - qm->err_ini.clear_dev_hw_err_status = hisi_rde_clear_hw_err_status; - qm->err_ini.err_info.ecc_2bits_mask = HRDE_ECC_2BIT_ERR; - qm->err_ini.err_info.ce = QM_BASE_CE; - qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; - qm->err_ini.err_info.fe = 0; - qm->err_ini.err_info.msi = 0; - qm->err_ini.err_info.acpi_rst = "RRST"; - qm->err_ini.hw_err_disable = hisi_rde_hw_error_disable; - qm->err_ini.hw_err_enable = hisi_rde_hw_error_enable; - qm->err_ini.set_usr_domain_cache = hisi_rde_set_user_domain_and_cache; - qm->err_ini.log_dev_hw_err = hisi_rde_hw_error_log; - qm->err_ini.open_axi_master_ooo = hisi_rde_open_master_ooo; - qm->err_ini.err_info.msi_wr_port = HRDE_WR_MSI_PORT; - ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) return ret; @@ -690,6 +686,7 @@ static int hisi_rde_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HRDE_SQE_SIZE; qm->dev_name = hisi_rde_name; qm->abnormal_fix = hisi_rde_abnormal_fix; + hisi_rde_err_ini_set(qm); return 0; } @@ -727,31 +724,31 @@ static int hisi_rde_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = hisi_rde_qm_pre_init(qm, pdev); if (ret) { - pci_err(pdev, "Pre init qm failed!\n"); + pci_err(pdev, "Failed to pre init qm!\n"); return ret; } ret = hisi_qm_init(qm); if (ret) { - pci_err(pdev, "Init qm failed!\n"); + pci_err(pdev, "Failed to init qm!\n"); return ret; } ret = hisi_rde_pf_probe_init(qm); if (ret) { - pci_err(pdev, "Init pf failed!\n"); + pci_err(pdev, "Failed to init pf!\n"); goto err_qm_uninit; } ret = hisi_qm_start(qm); if (ret) { - pci_err(pdev, "Start qm failed!\n"); + pci_err(pdev, "Failed to start qm!\n"); goto err_qm_uninit; } ret = hisi_rde_debugfs_init(qm); if (ret) - pci_warn(pdev, "Init debugfs failed!\n"); + pci_warn(pdev, "Failed to init debugfs!\n"); hisi_qm_add_to_list(qm, &rde_devices); @@ -793,8 +790,7 @@ static void hisi_rde_ras_proc(struct work_struct *work) ret = hisi_qm_process_dev_error(pdev); if (ret == PCI_ERS_RESULT_NEED_RESET) if (hisi_qm_controller_reset(&hisi_rde->qm)) - dev_err(&pdev->dev, "Hisi_rde reset fail.\n"); - + dev_err(&pdev->dev, "Failed to reset device!\n"); } int hisi_rde_abnormal_fix(struct hisi_qm *qm) @@ -850,7 +846,7 @@ static int __init hisi_rde_init(void) ret = pci_register_driver(&hisi_rde_pci_driver); if (ret < 0) { hisi_rde_unregister_debugfs(); - pr_err("Register pci driver failed.\n"); + pr_err("Failed to register pci driver!\n"); } return ret; diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index a568d5363c1e..0f32dcb69e12 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -712,29 +712,17 @@ static void sec_open_axi_master_ooo(struct hisi_qm *qm) writel(val | SEC_AXI_SHUTDOWN_ENABLE, SEC_ADDR(qm, SEC_CONTROL_REG)); } -static int sec_pf_probe_init(struct hisi_qm *qm) +static void sec_err_ini_set(struct hisi_qm *qm) { - int ret; - - switch (qm->ver) { - case QM_HW_V1: - qm->ctrl_q_num = SEC_QUEUE_NUM_V1; - break; - - case QM_HW_V2: - qm->ctrl_q_num = SEC_QUEUE_NUM_V2; - break; - - default: - return -EINVAL; - } + if (qm->fun_type == QM_HW_VF) + return; qm->err_ini.get_dev_hw_err_status = sec_get_hw_err_status; qm->err_ini.clear_dev_hw_err_status = sec_clear_hw_err_status; qm->err_ini.err_info.ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC; qm->err_ini.err_info.ce = QM_BASE_CE; qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT | - QM_ACC_WB_NOT_READY_TIMEOUT; + QM_ACC_WB_NOT_READY_TIMEOUT; qm->err_ini.err_info.fe = 0; qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; qm->err_ini.err_info.acpi_rst = "SRST"; @@ -744,6 +732,24 @@ static int sec_pf_probe_init(struct hisi_qm *qm) qm->err_ini.log_dev_hw_err = sec_log_hw_error; qm->err_ini.open_axi_master_ooo = sec_open_axi_master_ooo; qm->err_ini.err_info.msi_wr_port = SEC_WR_MSI_PORT; +} + +static int sec_pf_probe_init(struct hisi_qm *qm) +{ + int ret; + + switch (qm->ver) { + case QM_HW_V1: + qm->ctrl_q_num = SEC_QUEUE_NUM_V1; + break; + + case QM_HW_V2: + qm->ctrl_q_num = SEC_QUEUE_NUM_V2; + break; + + default: + return -EINVAL; + } ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) @@ -807,6 +813,7 @@ static int sec_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qm_list = &sec_devices; qm->sqe_size = SEC_SQE_SIZE; qm->dev_name = sec_name; + sec_err_ini_set(qm); return 0; } diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 17bbab667553..1ca51793e26a 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -204,7 +204,7 @@ static struct debugfs_reg32 hzip_dfx_regs[] = { {"HZIP_AVG_DELAY ", 0x28ull}, {"HZIP_MEM_VISIBLE_DATA ", 0x30ull}, {"HZIP_MEM_VISIBLE_ADDR ", 0x34ull}, - {"HZIP_COMSUMED_BYTE ", 0x38ull}, + {"HZIP_CONSUMED_BYTE ", 0x38ull}, {"HZIP_PRODUCED_BYTE ", 0x40ull}, {"HZIP_COMP_INF ", 0x70ull}, {"HZIP_PRE_OUT ", 0x78ull}, @@ -755,6 +755,28 @@ static void hisi_zip_close_axi_master_ooo(struct hisi_qm *qm) qm->io_base + HZIP_CORE_INT_SET); } +static void hisi_zip_err_ini_set(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_VF) + return; + + qm->err_ini.get_dev_hw_err_status = hisi_zip_get_hw_err_status; + qm->err_ini.clear_dev_hw_err_status = hisi_zip_clear_hw_err_status; + qm->err_ini.err_info.ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; + qm->err_ini.err_info.ce = QM_BASE_CE; + qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; + qm->err_ini.err_info.fe = 0; + qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; + qm->err_ini.err_info.acpi_rst = "ZRST"; + qm->err_ini.hw_err_disable = hisi_zip_hw_error_disable; + qm->err_ini.hw_err_enable = hisi_zip_hw_error_enable; + qm->err_ini.set_usr_domain_cache = hisi_zip_set_user_domain_and_cache; + qm->err_ini.log_dev_hw_err = hisi_zip_log_hw_error; + qm->err_ini.open_axi_master_ooo = hisi_zip_open_axi_master_ooo; + qm->err_ini.close_axi_master_ooo = hisi_zip_close_axi_master_ooo; + qm->err_ini.err_info.msi_wr_port = HZIP_WR_PORT; +} + static int hisi_zip_pf_probe_init(struct hisi_qm *qm) { struct hisi_zip *zip = container_of(qm, struct hisi_zip, qm); @@ -781,23 +803,6 @@ static int hisi_zip_pf_probe_init(struct hisi_qm *qm) return -EINVAL; } - qm->err_ini.get_dev_hw_err_status = hisi_zip_get_hw_err_status; - qm->err_ini.clear_dev_hw_err_status = hisi_zip_clear_hw_err_status; - qm->err_ini.err_info.ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; - qm->err_ini.err_info.ce = QM_BASE_CE; - qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; - qm->err_ini.err_info.fe = 0; - qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; - qm->err_ini.err_info.acpi_rst = "ZRST"; - qm->err_ini.hw_err_disable = hisi_zip_hw_error_disable; - qm->err_ini.hw_err_enable = hisi_zip_hw_error_enable; - qm->err_ini.set_usr_domain_cache = hisi_zip_set_user_domain_and_cache; - qm->err_ini.log_dev_hw_err = hisi_zip_log_hw_error; - qm->err_ini.open_axi_master_ooo = hisi_zip_open_axi_master_ooo; - qm->err_ini.close_axi_master_ooo = hisi_zip_close_axi_master_ooo; - - qm->err_ini.err_info.msi_wr_port = HZIP_WR_PORT; - ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) return ret; @@ -822,6 +827,7 @@ static int hisi_zip_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HZIP_SQE_SIZE; qm->dev_name = hisi_zip_name; qm->qm_list = &zip_devices; + hisi_zip_err_ini_set(qm); return 0; } -- 2.30.0

2 1

[PATCH openEuler-23.09 0/5] LoongArch: add old BPI compatibility
by yangyinglu 21 Sep '23

21 Sep '23

LoongArch: add kernel setvirtmap for runtime LoongArch: Old BPI compatibility LoongArch: Fix virtual machine startup error LoongArch: Fixed EIOINTC structure members LoongArch: use arch specific phys_to_dma arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/addrspace.h | 1 + arch/loongarch/include/asm/efi.h | 1 + arch/loongarch/include/asm/irq.h | 1 + arch/loongarch/include/asm/loongarch.h | 1 + arch/loongarch/kernel/Makefile | 1 + arch/loongarch/kernel/acpi.c | 7 +- arch/loongarch/kernel/dma.c | 26 +- arch/loongarch/kernel/efi.c | 175 ++++++++- arch/loongarch/kernel/env.c | 6 + arch/loongarch/kernel/irq.c | 25 +- arch/loongarch/kernel/legacy_boot.c | 484 +++++++++++++++++++++++++ arch/loongarch/kernel/legacy_boot.h | 90 +++++ arch/loongarch/kernel/mem.c | 26 +- arch/loongarch/kernel/numa.c | 39 +- arch/loongarch/kernel/reset.c | 3 +- arch/loongarch/kernel/setup.c | 18 +- arch/loongarch/kernel/smp.c | 6 +- arch/loongarch/pci/acpi.c | 147 +++++++- drivers/firmware/efi/Makefile | 1 + drivers/irqchip/irq-loongarch-cpu.c | 7 +- drivers/irqchip/irq-loongson-eiointc.c | 46 ++- drivers/irqchip/irq-loongson-pch-pic.c | 5 + 23 files changed, 1075 insertions(+), 42 deletions(-) create mode 100644 arch/loongarch/kernel/legacy_boot.c create mode 100644 arch/loongarch/kernel/legacy_boot.h -- 2.20.1

2 6

[PATCH openEuler-1.0-LTS] crypto: hisilicon - reset before init the device
by w00416078 21 Sep '23

21 Sep '23

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I830AI CVE: NA -------------------------------- Before initializing the device, reset the device to clear the residual data to prevent unexpected problems, such as reboot scene, which may maintain device state before reboot. Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/hpre/hpre_main.c | 68 +++++++++++-------- drivers/crypto/hisilicon/qm.c | 83 ++++++++++++++++------- drivers/crypto/hisilicon/rde/rde_main.c | 64 ++++++++--------- drivers/crypto/hisilicon/sec2/sec_main.c | 39 ++++++----- drivers/crypto/hisilicon/zip/zip_main.c | 42 +++++++----- 5 files changed, 175 insertions(+), 121 deletions(-) diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index 1a980f255ad4..cbe8ea438fd2 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -780,28 +780,6 @@ static void hpre_debugfs_exit(struct hisi_qm *qm) debugfs_remove_recursive(qm->debug.debug_root); } -static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) -{ - int ret; - - qm->algs = "rsa\ndh\n"; - qm->uacce_mode = uacce_mode; - qm->pdev = pdev; - ret = hisi_qm_pre_init(qm, pf_q_num, HPRE_PF_DEF_Q_BASE); - if (ret) - return ret; - if (qm->ver == QM_HW_V1) { - pci_warn(pdev, "HPRE version 1 is not supported!\n"); - return -EINVAL; - } - - qm->qm_list = &hpre_devices; - qm->sqe_size = HPRE_SQE_SIZE; - qm->dev_name = hpre_name; - - return 0; -} - static void hpre_log_hw_error(struct hisi_qm *qm, u32 err_sts) { const struct hpre_hw_error *err = hpre_hw_errors; @@ -836,30 +814,36 @@ static void hpre_open_axi_master_ooo(struct hisi_qm *qm) HPRE_ADDR(qm, HPRE_AM_OOO_SHUTDOWN_ENB)); } -static int hpre_pf_probe_init(struct hisi_qm *qm) +static void hpre_err_ini_set(struct hisi_qm *qm) { - int ret; - - if (qm->ver != QM_HW_V2) - return -EINVAL; + if (qm->fun_type == QM_HW_VF) + return; - qm->ctrl_q_num = HPRE_QUEUE_NUM_V2; qm->err_ini.get_dev_hw_err_status = hpre_get_hw_err_status; qm->err_ini.clear_dev_hw_err_status = hpre_clear_hw_err_status; qm->err_ini.err_info.ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR | - HPRE_OOO_ECC_2BIT_ERR; + HPRE_OOO_ECC_2BIT_ERR; qm->err_ini.err_info.ce = QM_BASE_CE; qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; qm->err_ini.err_info.fe = 0; qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; qm->err_ini.err_info.acpi_rst = "HRST"; - qm->err_ini.hw_err_disable = hpre_hw_error_disable; qm->err_ini.hw_err_enable = hpre_hw_error_enable; qm->err_ini.set_usr_domain_cache = hpre_set_user_domain_and_cache; qm->err_ini.log_dev_hw_err = hpre_log_hw_error; qm->err_ini.open_axi_master_ooo = hpre_open_axi_master_ooo; qm->err_ini.err_info.msi_wr_port = HPRE_WR_MSI_PORT; +} + +static int hpre_pf_probe_init(struct hisi_qm *qm) +{ + int ret; + + if (qm->ver != QM_HW_V2) + return -EINVAL; + + qm->ctrl_q_num = HPRE_QUEUE_NUM_V2; ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) @@ -870,6 +854,30 @@ static int hpre_pf_probe_init(struct hisi_qm *qm) return 0; } +static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) +{ + int ret; + + qm->algs = "rsa\ndh\n"; + qm->uacce_mode = uacce_mode; + qm->pdev = pdev; + ret = hisi_qm_pre_init(qm, pf_q_num, HPRE_PF_DEF_Q_BASE); + if (ret) + return ret; + + if (qm->ver == QM_HW_V1) { + pci_warn(pdev, "HPRE version 1 is not supported!\n"); + return -EINVAL; + } + + qm->qm_list = &hpre_devices; + qm->sqe_size = HPRE_SQE_SIZE; + qm->dev_name = hpre_name; + hpre_err_ini_set(qm); + + return 0; +} + static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct hisi_qm *qm; diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 739b1a6565fd..f2706dc0d55e 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -230,6 +230,7 @@ #define QMC_ALIGN(sz) ALIGN(sz, 32) static int __hisi_qm_start(struct hisi_qm *qm); +static int qm_reset_device(struct hisi_qm *qm); enum vft_type { SQC_VFT = 0, @@ -2584,6 +2585,30 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) return ret; } +static int qm_clear_device(struct hisi_qm *qm) +{ + u32 val; + int ret; + + if (qm->fun_type == QM_HW_VF) + return 0; + + /* OOO register set and check */ + writel(MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + MASTER_GLOBAL_CTRL); + + ret = readl_relaxed_poll_timeout(qm->io_base + MASTER_TRANS_RETURN, + val, (val == MASTER_TRANS_RETURN_RW), + QM_REG_RD_INTVRL_US, + QM_REG_RD_TMOUT_US); + if (ret) { + pci_warn(qm->pdev, "Device is busy, can not clear device.\n"); + writel(0x0, qm->io_base + MASTER_GLOBAL_CTRL); + return ret; + } + + return qm_reset_device(qm); +} + static int hisi_qm_pci_init(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -2626,8 +2651,14 @@ static int hisi_qm_pci_init(struct hisi_qm *qm) goto err_set_mask_and_coherent; } + ret = qm_clear_device(qm); + if (ret) + goto err_free_vectors; + return 0; +err_free_vectors: + pci_free_irq_vectors(pdev); err_set_mask_and_coherent: devm_iounmap(dev, qm->io_base); err_ioremap: @@ -3808,6 +3839,34 @@ static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) } } +static int qm_reset_device(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + unsigned long long value = 0; + acpi_status s; + + /* The reset related sub-control registers are not in PCI BAR */ + if (ACPI_HANDLE(&pdev->dev)) { + s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), + qm->err_ini.err_info.acpi_rst, + NULL, &value); + if (ACPI_FAILURE(s)) { + pci_err(pdev, "NO controller reset method!\n"); + return -EIO; + } + + if (value) { + pci_err(pdev, "Reset step %llu failed!\n", value); + return -EIO; + } + + return 0; + } + + pci_err(pdev, "No reset method!\n"); + return -EINVAL; +} + static int qm_soft_reset(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -3853,29 +3912,7 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - /* The reset related sub-control registers are not in PCI BAR */ - if (ACPI_HANDLE(&pdev->dev)) { - unsigned long long value = 0; - acpi_status s; - - s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), - qm->err_ini.err_info.acpi_rst, - NULL, &value); - if (ACPI_FAILURE(s)) { - pci_err(pdev, "NO controller reset method!\n"); - return -EIO; - } - - if (value) { - pci_err(pdev, "Reset step %llu failed!\n", value); - return -EIO; - } - } else { - pci_err(pdev, "No reset method!\n"); - return -EINVAL; - } - - return 0; + return qm_reset_device(qm); } static int qm_vf_reset_done(struct pci_dev *pdev, diff --git a/drivers/crypto/hisilicon/rde/rde_main.c b/drivers/crypto/hisilicon/rde/rde_main.c index f3f70079aa77..f2e00ff891db 100644 --- a/drivers/crypto/hisilicon/rde/rde_main.c +++ b/drivers/crypto/hisilicon/rde/rde_main.c @@ -28,15 +28,8 @@ #define HRDE_QUEUE_NUM_V2 1024 #define HRDE_PCI_DEVICE_ID 0xa25a #define HRDE_SQE_SIZE 64 -#define HRDE_SQ_SIZE (HRDE_SQE_SIZE * QM_Q_DEPTH) #define HRDE_PF_DEF_Q_NUM 64 #define HRDE_PF_DEF_Q_BASE 0 -#define HRDE_RD_INTVRL_US 10 -#define HRDE_RD_TMOUT_US 1000 -#define HRDE_RST_TMOUT_MS 400 -#define HRDE_ENABLE 1 -#define HRDE_DISABLE 0 -#define HRDE_PCI_COMMAND_INVALID 0xFFFFFFFF #define HRDE_RAS_INT_MSK 0x310290 #define HRDE_RAS_CE_MSK BIT(2) @@ -101,7 +94,7 @@ static struct hisi_qm_list rde_devices; static void hisi_rde_ras_proc(struct work_struct *work); static const struct hisi_rde_hw_error rde_hw_error[] = { - {.int_msk = BIT(0), .msg = "Rde_ecc_1bitt_err"}, + {.int_msk = BIT(0), .msg = "Rde_ecc_1bit_err"}, {.int_msk = BIT(1), .msg = "Rde_ecc_2bit_err"}, {.int_msk = BIT(2), .msg = "Rde_stat_mgmt_state_timeout_err"}, {.int_msk = BIT(3), .msg = "Rde_data_wr_state_timeout_err"}, @@ -269,7 +262,7 @@ static int hisi_rde_set_user_domain_and_cache(struct hisi_qm *qm) writel(AXI_M_CFG, qm->io_base + QM_AXI_M_CFG); writel(AXI_M_CFG_ENABLE, qm->io_base + QM_AXI_M_CFG_ENABLE); - /* disable BME/PM/SRIOV FLR*/ + /* disable BME/PM/SRIOV FLR */ writel(PEH_AXUSER_CFG, qm->io_base + QM_PEH_AXUSER_CFG); writel(PEH_AXUSER_CFG_ENABLE, qm->io_base + QM_PEH_AXUSER_CFG_ENABLE); @@ -351,7 +344,7 @@ static int current_qm_write(struct ctrl_debug_file *file, u32 val) u32 tmp; if (val > 0) { - pr_err("Function id should be smaller than 0.\n"); + pr_err("Function id should be equal to 0.\n"); return -EINVAL; } @@ -423,7 +416,7 @@ static ssize_t ctrl_debug_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ctrl_debug_file *file = filp->private_data; - char tbuf[20]; + char tbuf[HRDE_DBGFS_VAL_MAX_LEN]; unsigned long val; int len, ret; @@ -623,6 +616,24 @@ static void hisi_rde_open_master_ooo(struct hisi_qm *qm) writel(val | HRDE_AXI_SHUTDOWN_EN, qm->io_base + HRDE_CFG); } +static void hisi_rde_err_ini_set(struct hisi_qm *qm) +{ + qm->err_ini.get_dev_hw_err_status = hisi_rde_get_hw_err_status; + qm->err_ini.clear_dev_hw_err_status = hisi_rde_clear_hw_err_status; + qm->err_ini.err_info.ecc_2bits_mask = HRDE_ECC_2BIT_ERR; + qm->err_ini.err_info.ce = QM_BASE_CE; + qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; + qm->err_ini.err_info.fe = 0; + qm->err_ini.err_info.msi = 0; + qm->err_ini.err_info.acpi_rst = "RRST"; + qm->err_ini.hw_err_disable = hisi_rde_hw_error_disable; + qm->err_ini.hw_err_enable = hisi_rde_hw_error_enable; + qm->err_ini.set_usr_domain_cache = hisi_rde_set_user_domain_and_cache; + qm->err_ini.log_dev_hw_err = hisi_rde_hw_error_log; + qm->err_ini.open_axi_master_ooo = hisi_rde_open_master_ooo; + qm->err_ini.err_info.msi_wr_port = HRDE_WR_MSI_PORT; +} + static int hisi_rde_pf_probe_init(struct hisi_qm *qm) { struct hisi_rde *hisi_rde = container_of(qm, struct hisi_rde, qm); @@ -649,21 +660,6 @@ static int hisi_rde_pf_probe_init(struct hisi_qm *qm) return -EINVAL; } - qm->err_ini.get_dev_hw_err_status = hisi_rde_get_hw_err_status; - qm->err_ini.clear_dev_hw_err_status = hisi_rde_clear_hw_err_status; - qm->err_ini.err_info.ecc_2bits_mask = HRDE_ECC_2BIT_ERR; - qm->err_ini.err_info.ce = QM_BASE_CE; - qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; - qm->err_ini.err_info.fe = 0; - qm->err_ini.err_info.msi = 0; - qm->err_ini.err_info.acpi_rst = "RRST"; - qm->err_ini.hw_err_disable = hisi_rde_hw_error_disable; - qm->err_ini.hw_err_enable = hisi_rde_hw_error_enable; - qm->err_ini.set_usr_domain_cache = hisi_rde_set_user_domain_and_cache; - qm->err_ini.log_dev_hw_err = hisi_rde_hw_error_log; - qm->err_ini.open_axi_master_ooo = hisi_rde_open_master_ooo; - qm->err_ini.err_info.msi_wr_port = HRDE_WR_MSI_PORT; - ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) return ret; @@ -690,6 +686,7 @@ static int hisi_rde_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HRDE_SQE_SIZE; qm->dev_name = hisi_rde_name; qm->abnormal_fix = hisi_rde_abnormal_fix; + hisi_rde_err_ini_set(qm); return 0; } @@ -727,31 +724,31 @@ static int hisi_rde_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = hisi_rde_qm_pre_init(qm, pdev); if (ret) { - pci_err(pdev, "Pre init qm failed!\n"); + pci_err(pdev, "Failed to pre init qm!\n"); return ret; } ret = hisi_qm_init(qm); if (ret) { - pci_err(pdev, "Init qm failed!\n"); + pci_err(pdev, "Failed to init qm!\n"); return ret; } ret = hisi_rde_pf_probe_init(qm); if (ret) { - pci_err(pdev, "Init pf failed!\n"); + pci_err(pdev, "Failed to init pf!\n"); goto err_qm_uninit; } ret = hisi_qm_start(qm); if (ret) { - pci_err(pdev, "Start qm failed!\n"); + pci_err(pdev, "Failed to start qm!\n"); goto err_qm_uninit; } ret = hisi_rde_debugfs_init(qm); if (ret) - pci_warn(pdev, "Init debugfs failed!\n"); + pci_warn(pdev, "Failed to init debugfs!\n"); hisi_qm_add_to_list(qm, &rde_devices); @@ -793,8 +790,7 @@ static void hisi_rde_ras_proc(struct work_struct *work) ret = hisi_qm_process_dev_error(pdev); if (ret == PCI_ERS_RESULT_NEED_RESET) if (hisi_qm_controller_reset(&hisi_rde->qm)) - dev_err(&pdev->dev, "Hisi_rde reset fail.\n"); - + dev_err(&pdev->dev, "Failed to reset device!\n"); } int hisi_rde_abnormal_fix(struct hisi_qm *qm) @@ -850,7 +846,7 @@ static int __init hisi_rde_init(void) ret = pci_register_driver(&hisi_rde_pci_driver); if (ret < 0) { hisi_rde_unregister_debugfs(); - pr_err("Register pci driver failed.\n"); + pr_err("Failed to register pci driver!\n"); } return ret; diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index a568d5363c1e..0f32dcb69e12 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -712,29 +712,17 @@ static void sec_open_axi_master_ooo(struct hisi_qm *qm) writel(val | SEC_AXI_SHUTDOWN_ENABLE, SEC_ADDR(qm, SEC_CONTROL_REG)); } -static int sec_pf_probe_init(struct hisi_qm *qm) +static void sec_err_ini_set(struct hisi_qm *qm) { - int ret; - - switch (qm->ver) { - case QM_HW_V1: - qm->ctrl_q_num = SEC_QUEUE_NUM_V1; - break; - - case QM_HW_V2: - qm->ctrl_q_num = SEC_QUEUE_NUM_V2; - break; - - default: - return -EINVAL; - } + if (qm->fun_type == QM_HW_VF) + return; qm->err_ini.get_dev_hw_err_status = sec_get_hw_err_status; qm->err_ini.clear_dev_hw_err_status = sec_clear_hw_err_status; qm->err_ini.err_info.ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC; qm->err_ini.err_info.ce = QM_BASE_CE; qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT | - QM_ACC_WB_NOT_READY_TIMEOUT; + QM_ACC_WB_NOT_READY_TIMEOUT; qm->err_ini.err_info.fe = 0; qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; qm->err_ini.err_info.acpi_rst = "SRST"; @@ -744,6 +732,24 @@ static int sec_pf_probe_init(struct hisi_qm *qm) qm->err_ini.log_dev_hw_err = sec_log_hw_error; qm->err_ini.open_axi_master_ooo = sec_open_axi_master_ooo; qm->err_ini.err_info.msi_wr_port = SEC_WR_MSI_PORT; +} + +static int sec_pf_probe_init(struct hisi_qm *qm) +{ + int ret; + + switch (qm->ver) { + case QM_HW_V1: + qm->ctrl_q_num = SEC_QUEUE_NUM_V1; + break; + + case QM_HW_V2: + qm->ctrl_q_num = SEC_QUEUE_NUM_V2; + break; + + default: + return -EINVAL; + } ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) @@ -807,6 +813,7 @@ static int sec_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qm_list = &sec_devices; qm->sqe_size = SEC_SQE_SIZE; qm->dev_name = sec_name; + sec_err_ini_set(qm); return 0; } diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 17bbab667553..1ca51793e26a 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -204,7 +204,7 @@ static struct debugfs_reg32 hzip_dfx_regs[] = { {"HZIP_AVG_DELAY ", 0x28ull}, {"HZIP_MEM_VISIBLE_DATA ", 0x30ull}, {"HZIP_MEM_VISIBLE_ADDR ", 0x34ull}, - {"HZIP_COMSUMED_BYTE ", 0x38ull}, + {"HZIP_CONSUMED_BYTE ", 0x38ull}, {"HZIP_PRODUCED_BYTE ", 0x40ull}, {"HZIP_COMP_INF ", 0x70ull}, {"HZIP_PRE_OUT ", 0x78ull}, @@ -755,6 +755,28 @@ static void hisi_zip_close_axi_master_ooo(struct hisi_qm *qm) qm->io_base + HZIP_CORE_INT_SET); } +static void hisi_zip_err_ini_set(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_VF) + return; + + qm->err_ini.get_dev_hw_err_status = hisi_zip_get_hw_err_status; + qm->err_ini.clear_dev_hw_err_status = hisi_zip_clear_hw_err_status; + qm->err_ini.err_info.ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; + qm->err_ini.err_info.ce = QM_BASE_CE; + qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; + qm->err_ini.err_info.fe = 0; + qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; + qm->err_ini.err_info.acpi_rst = "ZRST"; + qm->err_ini.hw_err_disable = hisi_zip_hw_error_disable; + qm->err_ini.hw_err_enable = hisi_zip_hw_error_enable; + qm->err_ini.set_usr_domain_cache = hisi_zip_set_user_domain_and_cache; + qm->err_ini.log_dev_hw_err = hisi_zip_log_hw_error; + qm->err_ini.open_axi_master_ooo = hisi_zip_open_axi_master_ooo; + qm->err_ini.close_axi_master_ooo = hisi_zip_close_axi_master_ooo; + qm->err_ini.err_info.msi_wr_port = HZIP_WR_PORT; +} + static int hisi_zip_pf_probe_init(struct hisi_qm *qm) { struct hisi_zip *zip = container_of(qm, struct hisi_zip, qm); @@ -781,23 +803,6 @@ static int hisi_zip_pf_probe_init(struct hisi_qm *qm) return -EINVAL; } - qm->err_ini.get_dev_hw_err_status = hisi_zip_get_hw_err_status; - qm->err_ini.clear_dev_hw_err_status = hisi_zip_clear_hw_err_status; - qm->err_ini.err_info.ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; - qm->err_ini.err_info.ce = QM_BASE_CE; - qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; - qm->err_ini.err_info.fe = 0; - qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; - qm->err_ini.err_info.acpi_rst = "ZRST"; - qm->err_ini.hw_err_disable = hisi_zip_hw_error_disable; - qm->err_ini.hw_err_enable = hisi_zip_hw_error_enable; - qm->err_ini.set_usr_domain_cache = hisi_zip_set_user_domain_and_cache; - qm->err_ini.log_dev_hw_err = hisi_zip_log_hw_error; - qm->err_ini.open_axi_master_ooo = hisi_zip_open_axi_master_ooo; - qm->err_ini.close_axi_master_ooo = hisi_zip_close_axi_master_ooo; - - qm->err_ini.err_info.msi_wr_port = HZIP_WR_PORT; - ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) return ret; @@ -822,6 +827,7 @@ static int hisi_zip_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HZIP_SQE_SIZE; qm->dev_name = hisi_zip_name; qm->qm_list = &zip_devices; + hisi_zip_err_ini_set(qm); return 0; } -- 2.30.0

2 1

[PATCH OLK-5.10] ext4: do not mark inode dirty every time when appending using delalloc
by WoZ1zh1 20 Sep '23

20 Sep '23

From: Liu Song <liusong(a)linux.alibaba.com> mainline inclusion from mainline-v6.6-rc1 commit 03de20bed203b0819225d4de98353c1f8755a1dd category: perf bugzilla: https://gitee.com/openeuler/kernel/issues/I82QPS CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- In the delalloc append write scenario, if inode's i_size is extended due to buffer write, there are delalloc writes pending in the range up to i_size, and no need to touch i_disksize since writeback will push i_disksize up to i_size eventually. Offers significant performance improvement in high-frequency append write scenarios. I conducted tests in my 32-core environment by launching 32 concurrent threads to append write to the same file. Each write operation had a length of 1024 bytes and was repeated 100000 times. Without using this patch, the test was completed in 7705 ms. However, with this patch, the test was completed in 5066 ms, resulting in a performance improvement of 34%. Moreover, in test scenarios of Kafka version 2.6.2, using packet size of 2K, with this patch resulted in a 10% performance improvement. Signed-off-by: Liu Song <liusong(a)linux.alibaba.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230810154333.84921-1-liusong@linux.alibaba.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: WoZ1zh1 <wozizhi(a)huawei.com> --- fs/ext4/inode.c | 88 ++++++++++++++++++++++++++++++++++--------------- 1 file changed, 62 insertions(+), 26 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a61e7ab21a16..1b6e16702298 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3080,14 +3080,73 @@ static int ext4_da_should_update_i_disksize(struct page *page, return 1; } +static int ext4_da_do_write_end(struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page) +{ + struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; + bool disksize_changed = false; + loff_t new_i_size; + + /* + * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES + * flag, which all that's needed to trigger page writeback. + */ + copied = block_write_end(NULL, mapping, pos, len, copied, page, NULL); + new_i_size = pos + copied; + + /* + * It's important to update i_size while still holding page lock, + * because page writeout could otherwise come in and zero beyond + * i_size. + * + * Since we are holding inode lock, we are sure i_disksize <= + * i_size. We also know that if i_disksize < i_size, there are + * delalloc writes pending in the range up to i_size. If the end of + * the current write is <= i_size, there's no need to touch + * i_disksize since writeback will push i_disksize up to i_size + * eventually. If the end of the current write is > i_size and + * inside an allocated block which ext4_da_should_update_i_disksize() + * checked, we need to update i_disksize here as certain + * ext4_writepages() paths not allocating blocks and update i_disksize. + */ + if (new_i_size > inode->i_size) { + unsigned long end; + + i_size_write(inode, new_i_size); + end = (new_i_size - 1) & (PAGE_SIZE - 1); + if (copied && ext4_da_should_update_i_disksize(page, end)) { + ext4_update_i_disksize(inode, new_i_size); + disksize_changed = true; + } + } + + unlock_page(page); + put_page(page); + + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); + + if (disksize_changed) { + handle_t *handle; + + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + } + + return copied; +} + static int ext4_da_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - loff_t new_i_size; - unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; if (write_mode == FALL_BACK_TO_NONDELALLOC) @@ -3104,30 +3163,7 @@ static int ext4_da_write_end(struct file *file, if (unlikely(copied < len) && !PageUptodate(page)) copied = 0; - start = pos & (PAGE_SIZE - 1); - end = start + copied - 1; - - /* - * Since we are holding inode lock, we are sure i_disksize <= - * i_size. We also know that if i_disksize < i_size, there are - * delalloc writes pending in the range upto i_size. If the end of - * the current write is <= i_size, there's no need to touch - * i_disksize since writeback will push i_disksize upto i_size - * eventually. If the end of the current write is > i_size and - * inside an allocated block (ext4_da_should_update_i_disksize() - * check), we need to update i_disksize here as neither - * ext4_writepage() nor certain ext4_writepages() paths not - * allocating blocks update i_disksize. - * - * Note that we defer inode dirtying to generic_write_end() / - * ext4_da_write_inline_data_end(). - */ - new_i_size = pos + copied; - if (copied && new_i_size > inode->i_size && - ext4_da_should_update_i_disksize(page, end)) - ext4_update_i_disksize(inode, new_i_size); - - return generic_write_end(file, mapping, pos, len, copied, page, fsdata); + return ext4_da_do_write_end(mapping, pos, len, copied, page); } /* -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] crypto: hisilicon - reset before init the device
by w00416078 20 Sep '23

20 Sep '23

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: bugfix bugzilla:https://gitee.com/openeuler/kernel/issues/I830AI CVE: NA -------------------------------- Before initializing the device, reset the device to clear the residual data to prevent unexpected problems, such as reboot scene, which may maintain device state before reboot. Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/hpre/hpre_main.c | 68 +++++++++++-------- drivers/crypto/hisilicon/qm.c | 83 ++++++++++++++++------- drivers/crypto/hisilicon/rde/rde_main.c | 64 ++++++++--------- drivers/crypto/hisilicon/sec2/sec_main.c | 39 ++++++----- drivers/crypto/hisilicon/zip/zip_main.c | 42 +++++++----- 5 files changed, 175 insertions(+), 121 deletions(-) diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index 1a980f255ad4..cbe8ea438fd2 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -780,28 +780,6 @@ static void hpre_debugfs_exit(struct hisi_qm *qm) debugfs_remove_recursive(qm->debug.debug_root); } -static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) -{ - int ret; - - qm->algs = "rsa\ndh\n"; - qm->uacce_mode = uacce_mode; - qm->pdev = pdev; - ret = hisi_qm_pre_init(qm, pf_q_num, HPRE_PF_DEF_Q_BASE); - if (ret) - return ret; - if (qm->ver == QM_HW_V1) { - pci_warn(pdev, "HPRE version 1 is not supported!\n"); - return -EINVAL; - } - - qm->qm_list = &hpre_devices; - qm->sqe_size = HPRE_SQE_SIZE; - qm->dev_name = hpre_name; - - return 0; -} - static void hpre_log_hw_error(struct hisi_qm *qm, u32 err_sts) { const struct hpre_hw_error *err = hpre_hw_errors; @@ -836,30 +814,36 @@ static void hpre_open_axi_master_ooo(struct hisi_qm *qm) HPRE_ADDR(qm, HPRE_AM_OOO_SHUTDOWN_ENB)); } -static int hpre_pf_probe_init(struct hisi_qm *qm) +static void hpre_err_ini_set(struct hisi_qm *qm) { - int ret; - - if (qm->ver != QM_HW_V2) - return -EINVAL; + if (qm->fun_type == QM_HW_VF) + return; - qm->ctrl_q_num = HPRE_QUEUE_NUM_V2; qm->err_ini.get_dev_hw_err_status = hpre_get_hw_err_status; qm->err_ini.clear_dev_hw_err_status = hpre_clear_hw_err_status; qm->err_ini.err_info.ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR | - HPRE_OOO_ECC_2BIT_ERR; + HPRE_OOO_ECC_2BIT_ERR; qm->err_ini.err_info.ce = QM_BASE_CE; qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; qm->err_ini.err_info.fe = 0; qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; qm->err_ini.err_info.acpi_rst = "HRST"; - qm->err_ini.hw_err_disable = hpre_hw_error_disable; qm->err_ini.hw_err_enable = hpre_hw_error_enable; qm->err_ini.set_usr_domain_cache = hpre_set_user_domain_and_cache; qm->err_ini.log_dev_hw_err = hpre_log_hw_error; qm->err_ini.open_axi_master_ooo = hpre_open_axi_master_ooo; qm->err_ini.err_info.msi_wr_port = HPRE_WR_MSI_PORT; +} + +static int hpre_pf_probe_init(struct hisi_qm *qm) +{ + int ret; + + if (qm->ver != QM_HW_V2) + return -EINVAL; + + qm->ctrl_q_num = HPRE_QUEUE_NUM_V2; ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) @@ -870,6 +854,30 @@ static int hpre_pf_probe_init(struct hisi_qm *qm) return 0; } +static int hpre_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) +{ + int ret; + + qm->algs = "rsa\ndh\n"; + qm->uacce_mode = uacce_mode; + qm->pdev = pdev; + ret = hisi_qm_pre_init(qm, pf_q_num, HPRE_PF_DEF_Q_BASE); + if (ret) + return ret; + + if (qm->ver == QM_HW_V1) { + pci_warn(pdev, "HPRE version 1 is not supported!\n"); + return -EINVAL; + } + + qm->qm_list = &hpre_devices; + qm->sqe_size = HPRE_SQE_SIZE; + qm->dev_name = hpre_name; + hpre_err_ini_set(qm); + + return 0; +} + static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct hisi_qm *qm; diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 739b1a6565fd..f2706dc0d55e 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -230,6 +230,7 @@ #define QMC_ALIGN(sz) ALIGN(sz, 32) static int __hisi_qm_start(struct hisi_qm *qm); +static int qm_reset_device(struct hisi_qm *qm); enum vft_type { SQC_VFT = 0, @@ -2584,6 +2585,30 @@ static int hisi_qm_memory_init(struct hisi_qm *qm) return ret; } +static int qm_clear_device(struct hisi_qm *qm) +{ + u32 val; + int ret; + + if (qm->fun_type == QM_HW_VF) + return 0; + + /* OOO register set and check */ + writel(MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + MASTER_GLOBAL_CTRL); + + ret = readl_relaxed_poll_timeout(qm->io_base + MASTER_TRANS_RETURN, + val, (val == MASTER_TRANS_RETURN_RW), + QM_REG_RD_INTVRL_US, + QM_REG_RD_TMOUT_US); + if (ret) { + pci_warn(qm->pdev, "Device is busy, can not clear device.\n"); + writel(0x0, qm->io_base + MASTER_GLOBAL_CTRL); + return ret; + } + + return qm_reset_device(qm); +} + static int hisi_qm_pci_init(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -2626,8 +2651,14 @@ static int hisi_qm_pci_init(struct hisi_qm *qm) goto err_set_mask_and_coherent; } + ret = qm_clear_device(qm); + if (ret) + goto err_free_vectors; + return 0; +err_free_vectors: + pci_free_irq_vectors(pdev); err_set_mask_and_coherent: devm_iounmap(dev, qm->io_base); err_ioremap: @@ -3808,6 +3839,34 @@ static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) } } +static int qm_reset_device(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + unsigned long long value = 0; + acpi_status s; + + /* The reset related sub-control registers are not in PCI BAR */ + if (ACPI_HANDLE(&pdev->dev)) { + s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), + qm->err_ini.err_info.acpi_rst, + NULL, &value); + if (ACPI_FAILURE(s)) { + pci_err(pdev, "NO controller reset method!\n"); + return -EIO; + } + + if (value) { + pci_err(pdev, "Reset step %llu failed!\n", value); + return -EIO; + } + + return 0; + } + + pci_err(pdev, "No reset method!\n"); + return -EINVAL; +} + static int qm_soft_reset(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -3853,29 +3912,7 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - /* The reset related sub-control registers are not in PCI BAR */ - if (ACPI_HANDLE(&pdev->dev)) { - unsigned long long value = 0; - acpi_status s; - - s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), - qm->err_ini.err_info.acpi_rst, - NULL, &value); - if (ACPI_FAILURE(s)) { - pci_err(pdev, "NO controller reset method!\n"); - return -EIO; - } - - if (value) { - pci_err(pdev, "Reset step %llu failed!\n", value); - return -EIO; - } - } else { - pci_err(pdev, "No reset method!\n"); - return -EINVAL; - } - - return 0; + return qm_reset_device(qm); } static int qm_vf_reset_done(struct pci_dev *pdev, diff --git a/drivers/crypto/hisilicon/rde/rde_main.c b/drivers/crypto/hisilicon/rde/rde_main.c index f3f70079aa77..f2e00ff891db 100644 --- a/drivers/crypto/hisilicon/rde/rde_main.c +++ b/drivers/crypto/hisilicon/rde/rde_main.c @@ -28,15 +28,8 @@ #define HRDE_QUEUE_NUM_V2 1024 #define HRDE_PCI_DEVICE_ID 0xa25a #define HRDE_SQE_SIZE 64 -#define HRDE_SQ_SIZE (HRDE_SQE_SIZE * QM_Q_DEPTH) #define HRDE_PF_DEF_Q_NUM 64 #define HRDE_PF_DEF_Q_BASE 0 -#define HRDE_RD_INTVRL_US 10 -#define HRDE_RD_TMOUT_US 1000 -#define HRDE_RST_TMOUT_MS 400 -#define HRDE_ENABLE 1 -#define HRDE_DISABLE 0 -#define HRDE_PCI_COMMAND_INVALID 0xFFFFFFFF #define HRDE_RAS_INT_MSK 0x310290 #define HRDE_RAS_CE_MSK BIT(2) @@ -101,7 +94,7 @@ static struct hisi_qm_list rde_devices; static void hisi_rde_ras_proc(struct work_struct *work); static const struct hisi_rde_hw_error rde_hw_error[] = { - {.int_msk = BIT(0), .msg = "Rde_ecc_1bitt_err"}, + {.int_msk = BIT(0), .msg = "Rde_ecc_1bit_err"}, {.int_msk = BIT(1), .msg = "Rde_ecc_2bit_err"}, {.int_msk = BIT(2), .msg = "Rde_stat_mgmt_state_timeout_err"}, {.int_msk = BIT(3), .msg = "Rde_data_wr_state_timeout_err"}, @@ -269,7 +262,7 @@ static int hisi_rde_set_user_domain_and_cache(struct hisi_qm *qm) writel(AXI_M_CFG, qm->io_base + QM_AXI_M_CFG); writel(AXI_M_CFG_ENABLE, qm->io_base + QM_AXI_M_CFG_ENABLE); - /* disable BME/PM/SRIOV FLR*/ + /* disable BME/PM/SRIOV FLR */ writel(PEH_AXUSER_CFG, qm->io_base + QM_PEH_AXUSER_CFG); writel(PEH_AXUSER_CFG_ENABLE, qm->io_base + QM_PEH_AXUSER_CFG_ENABLE); @@ -351,7 +344,7 @@ static int current_qm_write(struct ctrl_debug_file *file, u32 val) u32 tmp; if (val > 0) { - pr_err("Function id should be smaller than 0.\n"); + pr_err("Function id should be equal to 0.\n"); return -EINVAL; } @@ -423,7 +416,7 @@ static ssize_t ctrl_debug_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ctrl_debug_file *file = filp->private_data; - char tbuf[20]; + char tbuf[HRDE_DBGFS_VAL_MAX_LEN]; unsigned long val; int len, ret; @@ -623,6 +616,24 @@ static void hisi_rde_open_master_ooo(struct hisi_qm *qm) writel(val | HRDE_AXI_SHUTDOWN_EN, qm->io_base + HRDE_CFG); } +static void hisi_rde_err_ini_set(struct hisi_qm *qm) +{ + qm->err_ini.get_dev_hw_err_status = hisi_rde_get_hw_err_status; + qm->err_ini.clear_dev_hw_err_status = hisi_rde_clear_hw_err_status; + qm->err_ini.err_info.ecc_2bits_mask = HRDE_ECC_2BIT_ERR; + qm->err_ini.err_info.ce = QM_BASE_CE; + qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; + qm->err_ini.err_info.fe = 0; + qm->err_ini.err_info.msi = 0; + qm->err_ini.err_info.acpi_rst = "RRST"; + qm->err_ini.hw_err_disable = hisi_rde_hw_error_disable; + qm->err_ini.hw_err_enable = hisi_rde_hw_error_enable; + qm->err_ini.set_usr_domain_cache = hisi_rde_set_user_domain_and_cache; + qm->err_ini.log_dev_hw_err = hisi_rde_hw_error_log; + qm->err_ini.open_axi_master_ooo = hisi_rde_open_master_ooo; + qm->err_ini.err_info.msi_wr_port = HRDE_WR_MSI_PORT; +} + static int hisi_rde_pf_probe_init(struct hisi_qm *qm) { struct hisi_rde *hisi_rde = container_of(qm, struct hisi_rde, qm); @@ -649,21 +660,6 @@ static int hisi_rde_pf_probe_init(struct hisi_qm *qm) return -EINVAL; } - qm->err_ini.get_dev_hw_err_status = hisi_rde_get_hw_err_status; - qm->err_ini.clear_dev_hw_err_status = hisi_rde_clear_hw_err_status; - qm->err_ini.err_info.ecc_2bits_mask = HRDE_ECC_2BIT_ERR; - qm->err_ini.err_info.ce = QM_BASE_CE; - qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; - qm->err_ini.err_info.fe = 0; - qm->err_ini.err_info.msi = 0; - qm->err_ini.err_info.acpi_rst = "RRST"; - qm->err_ini.hw_err_disable = hisi_rde_hw_error_disable; - qm->err_ini.hw_err_enable = hisi_rde_hw_error_enable; - qm->err_ini.set_usr_domain_cache = hisi_rde_set_user_domain_and_cache; - qm->err_ini.log_dev_hw_err = hisi_rde_hw_error_log; - qm->err_ini.open_axi_master_ooo = hisi_rde_open_master_ooo; - qm->err_ini.err_info.msi_wr_port = HRDE_WR_MSI_PORT; - ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) return ret; @@ -690,6 +686,7 @@ static int hisi_rde_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HRDE_SQE_SIZE; qm->dev_name = hisi_rde_name; qm->abnormal_fix = hisi_rde_abnormal_fix; + hisi_rde_err_ini_set(qm); return 0; } @@ -727,31 +724,31 @@ static int hisi_rde_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = hisi_rde_qm_pre_init(qm, pdev); if (ret) { - pci_err(pdev, "Pre init qm failed!\n"); + pci_err(pdev, "Failed to pre init qm!\n"); return ret; } ret = hisi_qm_init(qm); if (ret) { - pci_err(pdev, "Init qm failed!\n"); + pci_err(pdev, "Failed to init qm!\n"); return ret; } ret = hisi_rde_pf_probe_init(qm); if (ret) { - pci_err(pdev, "Init pf failed!\n"); + pci_err(pdev, "Failed to init pf!\n"); goto err_qm_uninit; } ret = hisi_qm_start(qm); if (ret) { - pci_err(pdev, "Start qm failed!\n"); + pci_err(pdev, "Failed to start qm!\n"); goto err_qm_uninit; } ret = hisi_rde_debugfs_init(qm); if (ret) - pci_warn(pdev, "Init debugfs failed!\n"); + pci_warn(pdev, "Failed to init debugfs!\n"); hisi_qm_add_to_list(qm, &rde_devices); @@ -793,8 +790,7 @@ static void hisi_rde_ras_proc(struct work_struct *work) ret = hisi_qm_process_dev_error(pdev); if (ret == PCI_ERS_RESULT_NEED_RESET) if (hisi_qm_controller_reset(&hisi_rde->qm)) - dev_err(&pdev->dev, "Hisi_rde reset fail.\n"); - + dev_err(&pdev->dev, "Failed to reset device!\n"); } int hisi_rde_abnormal_fix(struct hisi_qm *qm) @@ -850,7 +846,7 @@ static int __init hisi_rde_init(void) ret = pci_register_driver(&hisi_rde_pci_driver); if (ret < 0) { hisi_rde_unregister_debugfs(); - pr_err("Register pci driver failed.\n"); + pr_err("Failed to register pci driver!\n"); } return ret; diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index a568d5363c1e..0f32dcb69e12 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -712,29 +712,17 @@ static void sec_open_axi_master_ooo(struct hisi_qm *qm) writel(val | SEC_AXI_SHUTDOWN_ENABLE, SEC_ADDR(qm, SEC_CONTROL_REG)); } -static int sec_pf_probe_init(struct hisi_qm *qm) +static void sec_err_ini_set(struct hisi_qm *qm) { - int ret; - - switch (qm->ver) { - case QM_HW_V1: - qm->ctrl_q_num = SEC_QUEUE_NUM_V1; - break; - - case QM_HW_V2: - qm->ctrl_q_num = SEC_QUEUE_NUM_V2; - break; - - default: - return -EINVAL; - } + if (qm->fun_type == QM_HW_VF) + return; qm->err_ini.get_dev_hw_err_status = sec_get_hw_err_status; qm->err_ini.clear_dev_hw_err_status = sec_clear_hw_err_status; qm->err_ini.err_info.ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC; qm->err_ini.err_info.ce = QM_BASE_CE; qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT | - QM_ACC_WB_NOT_READY_TIMEOUT; + QM_ACC_WB_NOT_READY_TIMEOUT; qm->err_ini.err_info.fe = 0; qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; qm->err_ini.err_info.acpi_rst = "SRST"; @@ -744,6 +732,24 @@ static int sec_pf_probe_init(struct hisi_qm *qm) qm->err_ini.log_dev_hw_err = sec_log_hw_error; qm->err_ini.open_axi_master_ooo = sec_open_axi_master_ooo; qm->err_ini.err_info.msi_wr_port = SEC_WR_MSI_PORT; +} + +static int sec_pf_probe_init(struct hisi_qm *qm) +{ + int ret; + + switch (qm->ver) { + case QM_HW_V1: + qm->ctrl_q_num = SEC_QUEUE_NUM_V1; + break; + + case QM_HW_V2: + qm->ctrl_q_num = SEC_QUEUE_NUM_V2; + break; + + default: + return -EINVAL; + } ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) @@ -807,6 +813,7 @@ static int sec_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qm_list = &sec_devices; qm->sqe_size = SEC_SQE_SIZE; qm->dev_name = sec_name; + sec_err_ini_set(qm); return 0; } diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 17bbab667553..1ca51793e26a 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -204,7 +204,7 @@ static struct debugfs_reg32 hzip_dfx_regs[] = { {"HZIP_AVG_DELAY ", 0x28ull}, {"HZIP_MEM_VISIBLE_DATA ", 0x30ull}, {"HZIP_MEM_VISIBLE_ADDR ", 0x34ull}, - {"HZIP_COMSUMED_BYTE ", 0x38ull}, + {"HZIP_CONSUMED_BYTE ", 0x38ull}, {"HZIP_PRODUCED_BYTE ", 0x40ull}, {"HZIP_COMP_INF ", 0x70ull}, {"HZIP_PRE_OUT ", 0x78ull}, @@ -755,6 +755,28 @@ static void hisi_zip_close_axi_master_ooo(struct hisi_qm *qm) qm->io_base + HZIP_CORE_INT_SET); } +static void hisi_zip_err_ini_set(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_VF) + return; + + qm->err_ini.get_dev_hw_err_status = hisi_zip_get_hw_err_status; + qm->err_ini.clear_dev_hw_err_status = hisi_zip_clear_hw_err_status; + qm->err_ini.err_info.ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; + qm->err_ini.err_info.ce = QM_BASE_CE; + qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; + qm->err_ini.err_info.fe = 0; + qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; + qm->err_ini.err_info.acpi_rst = "ZRST"; + qm->err_ini.hw_err_disable = hisi_zip_hw_error_disable; + qm->err_ini.hw_err_enable = hisi_zip_hw_error_enable; + qm->err_ini.set_usr_domain_cache = hisi_zip_set_user_domain_and_cache; + qm->err_ini.log_dev_hw_err = hisi_zip_log_hw_error; + qm->err_ini.open_axi_master_ooo = hisi_zip_open_axi_master_ooo; + qm->err_ini.close_axi_master_ooo = hisi_zip_close_axi_master_ooo; + qm->err_ini.err_info.msi_wr_port = HZIP_WR_PORT; +} + static int hisi_zip_pf_probe_init(struct hisi_qm *qm) { struct hisi_zip *zip = container_of(qm, struct hisi_zip, qm); @@ -781,23 +803,6 @@ static int hisi_zip_pf_probe_init(struct hisi_qm *qm) return -EINVAL; } - qm->err_ini.get_dev_hw_err_status = hisi_zip_get_hw_err_status; - qm->err_ini.clear_dev_hw_err_status = hisi_zip_clear_hw_err_status; - qm->err_ini.err_info.ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; - qm->err_ini.err_info.ce = QM_BASE_CE; - qm->err_ini.err_info.nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; - qm->err_ini.err_info.fe = 0; - qm->err_ini.err_info.msi = QM_DB_RANDOM_INVALID; - qm->err_ini.err_info.acpi_rst = "ZRST"; - qm->err_ini.hw_err_disable = hisi_zip_hw_error_disable; - qm->err_ini.hw_err_enable = hisi_zip_hw_error_enable; - qm->err_ini.set_usr_domain_cache = hisi_zip_set_user_domain_and_cache; - qm->err_ini.log_dev_hw_err = hisi_zip_log_hw_error; - qm->err_ini.open_axi_master_ooo = hisi_zip_open_axi_master_ooo; - qm->err_ini.close_axi_master_ooo = hisi_zip_close_axi_master_ooo; - - qm->err_ini.err_info.msi_wr_port = HZIP_WR_PORT; - ret = qm->err_ini.set_usr_domain_cache(qm); if (ret) return ret; @@ -822,6 +827,7 @@ static int hisi_zip_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HZIP_SQE_SIZE; qm->dev_name = hisi_zip_name; qm->qm_list = &zip_devices; + hisi_zip_err_ini_set(qm); return 0; } -- 2.30.0

2 1

[PATCH v2 openEuler-23.09 0/7] LoongArch: backport drm and spi driver and some bugfixes
by Hongchen Zhang 20 Sep '23

20 Sep '23

Backport the following patches from upstream. Hongchen Zhang (7): LoongArch: Allow usage of LSX/LASX in the kernel spi: loongson: add bus driver for the loongson spi controller drm: Add kms driver for loongson display controller drm/loongson: Remove a useless check in cursor_plane_atomic_async_check() drm/loongson: Add a check for lsdc_bo_create() errors LoongArch: mm: Add p?d_leaf() definitions LoongArch: Fix module relocation error with binutils 2.41 MAINTAINERS | 4 + arch/loongarch/Makefile | 2 + arch/loongarch/include/asm/pgtable.h | 3 + arch/loongarch/kernel/kfpu.c | 55 +- drivers/gpu/drm/Kconfig | 2 + drivers/gpu/drm/Makefile | 1 + drivers/gpu/drm/loongson/Kconfig | 17 + drivers/gpu/drm/loongson/Makefile | 22 + drivers/gpu/drm/loongson/loongson_device.c | 102 ++ drivers/gpu/drm/loongson/loongson_module.c | 33 + drivers/gpu/drm/loongson/loongson_module.h | 12 + drivers/gpu/drm/loongson/lsdc_benchmark.c | 133 +++ drivers/gpu/drm/loongson/lsdc_benchmark.h | 13 + drivers/gpu/drm/loongson/lsdc_crtc.c | 1024 +++++++++++++++++ drivers/gpu/drm/loongson/lsdc_debugfs.c | 110 ++ drivers/gpu/drm/loongson/lsdc_drv.c | 457 ++++++++ drivers/gpu/drm/loongson/lsdc_drv.h | 388 +++++++ drivers/gpu/drm/loongson/lsdc_gem.c | 311 +++++ drivers/gpu/drm/loongson/lsdc_gem.h | 37 + drivers/gpu/drm/loongson/lsdc_gfxpll.c | 199 ++++ drivers/gpu/drm/loongson/lsdc_gfxpll.h | 52 + drivers/gpu/drm/loongson/lsdc_i2c.c | 179 +++ drivers/gpu/drm/loongson/lsdc_i2c.h | 29 + drivers/gpu/drm/loongson/lsdc_irq.c | 74 ++ drivers/gpu/drm/loongson/lsdc_irq.h | 16 + drivers/gpu/drm/loongson/lsdc_output.h | 21 + drivers/gpu/drm/loongson/lsdc_output_7a1000.c | 178 +++ drivers/gpu/drm/loongson/lsdc_output_7a2000.c | 552 +++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.c | 481 ++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.h | 86 ++ drivers/gpu/drm/loongson/lsdc_plane.c | 793 +++++++++++++ drivers/gpu/drm/loongson/lsdc_probe.c | 56 + drivers/gpu/drm/loongson/lsdc_probe.h | 12 + drivers/gpu/drm/loongson/lsdc_regs.h | 406 +++++++ drivers/gpu/drm/loongson/lsdc_ttm.c | 593 ++++++++++ drivers/gpu/drm/loongson/lsdc_ttm.h | 99 ++ drivers/spi/Kconfig | 26 + drivers/spi/Makefile | 3 + drivers/spi/spi-loongson-core.c | 279 +++++ drivers/spi/spi-loongson-pci.c | 55 + drivers/spi/spi-loongson-plat.c | 47 + drivers/spi/spi-loongson.h | 49 + 42 files changed, 7007 insertions(+), 4 deletions(-) create mode 100644 drivers/gpu/drm/loongson/Kconfig create mode 100644 drivers/gpu/drm/loongson/Makefile create mode 100644 drivers/gpu/drm/loongson/loongson_device.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.h create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.c create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.h create mode 100644 drivers/gpu/drm/loongson/lsdc_crtc.c create mode 100644 drivers/gpu/drm/loongson/lsdc_debugfs.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.c create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.h create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.c create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a1000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a2000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_plane.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.h create mode 100644 drivers/gpu/drm/loongson/lsdc_regs.h create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.c create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.h create mode 100644 drivers/spi/spi-loongson-core.c create mode 100644 drivers/spi/spi-loongson-pci.c create mode 100644 drivers/spi/spi-loongson-plat.c create mode 100644 drivers/spi/spi-loongson.h -- 2.33.0

2 8

[PATCH openEuler-23.09 0/7] LoongArch: backport drm and spi driver and some bugfixes
by Hongchen Zhang 20 Sep '23

20 Sep '23

Backport the following patches from upstream. Dan Carpenter (1): drm/loongson: Add a check for lsdc_bo_create() errors Hongchen Zhang (1): LoongArch: mm: Add p?d_leaf() definitions Huacai Chen (2): LoongArch: Allow usage of LSX/LASX in the kernel LoongArch: Fix module relocation error with binutils 2.41 Sui Jingfeng (2): drm: Add kms driver for loongson display controller drm/loongson: Remove a useless check in cursor_plane_atomic_async_check() Yinbo Zhu (1): spi: loongson: add bus driver for the loongson spi controller MAINTAINERS | 4 + arch/loongarch/Makefile | 2 + arch/loongarch/include/asm/pgtable.h | 3 + arch/loongarch/kernel/kfpu.c | 55 +- drivers/gpio/gpio-loongson.c | 413 +++++-- drivers/gpu/drm/Kconfig | 2 + drivers/gpu/drm/Makefile | 1 + drivers/gpu/drm/loongson/Kconfig | 17 + drivers/gpu/drm/loongson/Makefile | 22 + drivers/gpu/drm/loongson/loongson_device.c | 102 ++ drivers/gpu/drm/loongson/loongson_module.c | 33 + drivers/gpu/drm/loongson/loongson_module.h | 12 + drivers/gpu/drm/loongson/lsdc_benchmark.c | 133 +++ drivers/gpu/drm/loongson/lsdc_benchmark.h | 13 + drivers/gpu/drm/loongson/lsdc_crtc.c | 1024 +++++++++++++++++ drivers/gpu/drm/loongson/lsdc_debugfs.c | 110 ++ drivers/gpu/drm/loongson/lsdc_drv.c | 457 ++++++++ drivers/gpu/drm/loongson/lsdc_drv.h | 388 +++++++ drivers/gpu/drm/loongson/lsdc_gem.c | 311 +++++ drivers/gpu/drm/loongson/lsdc_gem.h | 37 + drivers/gpu/drm/loongson/lsdc_gfxpll.c | 199 ++++ drivers/gpu/drm/loongson/lsdc_gfxpll.h | 52 + drivers/gpu/drm/loongson/lsdc_i2c.c | 179 +++ drivers/gpu/drm/loongson/lsdc_i2c.h | 29 + drivers/gpu/drm/loongson/lsdc_irq.c | 74 ++ drivers/gpu/drm/loongson/lsdc_irq.h | 16 + drivers/gpu/drm/loongson/lsdc_output.h | 21 + drivers/gpu/drm/loongson/lsdc_output_7a1000.c | 178 +++ drivers/gpu/drm/loongson/lsdc_output_7a2000.c | 552 +++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.c | 481 ++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.h | 86 ++ drivers/gpu/drm/loongson/lsdc_plane.c | 793 +++++++++++++ drivers/gpu/drm/loongson/lsdc_probe.c | 56 + drivers/gpu/drm/loongson/lsdc_probe.h | 12 + drivers/gpu/drm/loongson/lsdc_regs.h | 406 +++++++ drivers/gpu/drm/loongson/lsdc_ttm.c | 593 ++++++++++ drivers/gpu/drm/loongson/lsdc_ttm.h | 99 ++ drivers/spi/Kconfig | 26 + drivers/spi/Makefile | 3 + drivers/spi/spi-loongson-core.c | 279 +++++ drivers/spi/spi-loongson-pci.c | 55 + drivers/spi/spi-loongson-plat.c | 47 + drivers/spi/spi-loongson.h | 49 + 43 files changed, 7345 insertions(+), 79 deletions(-) create mode 100644 drivers/gpu/drm/loongson/Kconfig create mode 100644 drivers/gpu/drm/loongson/Makefile create mode 100644 drivers/gpu/drm/loongson/loongson_device.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.h create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.c create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.h create mode 100644 drivers/gpu/drm/loongson/lsdc_crtc.c create mode 100644 drivers/gpu/drm/loongson/lsdc_debugfs.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.c create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.h create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.c create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a1000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a2000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_plane.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.h create mode 100644 drivers/gpu/drm/loongson/lsdc_regs.h create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.c create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.h create mode 100644 drivers/spi/spi-loongson-core.c create mode 100644 drivers/spi/spi-loongson-pci.c create mode 100644 drivers/spi/spi-loongson-plat.c create mode 100644 drivers/spi/spi-loongson.h -- 2.33.0

2 8

[openEuler-23.09 0/7] LoongArch: backport drm and spi driver and some bugfixes
by Hongchen Zhang 20 Sep '23

20 Sep '23

Backport the following patches from upstream. Dan Carpenter (1): drm/loongson: Add a check for lsdc_bo_create() errors Hongchen Zhang (1): LoongArch: mm: Add p?d_leaf() definitions Huacai Chen (2): LoongArch: Allow usage of LSX/LASX in the kernel LoongArch: Fix module relocation error with binutils 2.41 Sui Jingfeng (2): drm: Add kms driver for loongson display controller drm/loongson: Remove a useless check in cursor_plane_atomic_async_check() Yinbo Zhu (1): spi: loongson: add bus driver for the loongson spi controller MAINTAINERS | 4 + arch/loongarch/Makefile | 2 + arch/loongarch/include/asm/pgtable.h | 3 + arch/loongarch/kernel/kfpu.c | 55 +- drivers/gpio/gpio-loongson.c | 413 +++++-- drivers/gpu/drm/Kconfig | 2 + drivers/gpu/drm/Makefile | 1 + drivers/gpu/drm/loongson/Kconfig | 17 + drivers/gpu/drm/loongson/Makefile | 22 + drivers/gpu/drm/loongson/loongson_device.c | 102 ++ drivers/gpu/drm/loongson/loongson_module.c | 33 + drivers/gpu/drm/loongson/loongson_module.h | 12 + drivers/gpu/drm/loongson/lsdc_benchmark.c | 133 +++ drivers/gpu/drm/loongson/lsdc_benchmark.h | 13 + drivers/gpu/drm/loongson/lsdc_crtc.c | 1024 +++++++++++++++++ drivers/gpu/drm/loongson/lsdc_debugfs.c | 110 ++ drivers/gpu/drm/loongson/lsdc_drv.c | 457 ++++++++ drivers/gpu/drm/loongson/lsdc_drv.h | 388 +++++++ drivers/gpu/drm/loongson/lsdc_gem.c | 311 +++++ drivers/gpu/drm/loongson/lsdc_gem.h | 37 + drivers/gpu/drm/loongson/lsdc_gfxpll.c | 199 ++++ drivers/gpu/drm/loongson/lsdc_gfxpll.h | 52 + drivers/gpu/drm/loongson/lsdc_i2c.c | 179 +++ drivers/gpu/drm/loongson/lsdc_i2c.h | 29 + drivers/gpu/drm/loongson/lsdc_irq.c | 74 ++ drivers/gpu/drm/loongson/lsdc_irq.h | 16 + drivers/gpu/drm/loongson/lsdc_output.h | 21 + drivers/gpu/drm/loongson/lsdc_output_7a1000.c | 178 +++ drivers/gpu/drm/loongson/lsdc_output_7a2000.c | 552 +++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.c | 481 ++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.h | 86 ++ drivers/gpu/drm/loongson/lsdc_plane.c | 793 +++++++++++++ drivers/gpu/drm/loongson/lsdc_probe.c | 56 + drivers/gpu/drm/loongson/lsdc_probe.h | 12 + drivers/gpu/drm/loongson/lsdc_regs.h | 406 +++++++ drivers/gpu/drm/loongson/lsdc_ttm.c | 593 ++++++++++ drivers/gpu/drm/loongson/lsdc_ttm.h | 99 ++ drivers/spi/Kconfig | 26 + drivers/spi/Makefile | 3 + drivers/spi/spi-loongson-core.c | 279 +++++ drivers/spi/spi-loongson-pci.c | 55 + drivers/spi/spi-loongson-plat.c | 47 + drivers/spi/spi-loongson.h | 49 + 43 files changed, 7345 insertions(+), 79 deletions(-) create mode 100644 drivers/gpu/drm/loongson/Kconfig create mode 100644 drivers/gpu/drm/loongson/Makefile create mode 100644 drivers/gpu/drm/loongson/loongson_device.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.h create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.c create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.h create mode 100644 drivers/gpu/drm/loongson/lsdc_crtc.c create mode 100644 drivers/gpu/drm/loongson/lsdc_debugfs.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.c create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.h create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.c create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a1000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a2000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_plane.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.h create mode 100644 drivers/gpu/drm/loongson/lsdc_regs.h create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.c create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.h create mode 100644 drivers/spi/spi-loongson-core.c create mode 100644 drivers/spi/spi-loongson-pci.c create mode 100644 drivers/spi/spi-loongson-plat.c create mode 100644 drivers/spi/spi-loongson.h -- 2.33.0

2 9

openEuler Kernel SIG双周例会
by openEuler conference 20 Sep '23

20 Sep '23

您好！ Kernel SIG 邀请您参加 2023-09-22 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中新增议题可直接回复邮件申请，或录入会议看板会议链接：https://us06web.zoom.us/j/83542407044?pwd=UYtASnHgeP3bOAEaO9OCyMaPdQc6iA.1 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-09-22 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1. 进展update 2. 议题征集中新增议题可直接回复邮件申请，或录入会议看板 You can join the meeting at https://us06web.zoom.us/j/83542407044?pwd=UYtASnHgeP3bOAEaO9OCyMaPdQc6iA.1. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[openEuler-23.09 0/7] LoongArch: backport drm and spi driver and some bugfixes
by Hongchen Zhang 20 Sep '23

20 Sep '23

Backport the following patches from upstream. Dan Carpenter (1): drm/loongson: Add a check for lsdc_bo_create() errors Hongchen Zhang (1): LoongArch: mm: Add p?d_leaf() definitions Huacai Chen (2): LoongArch: Allow usage of LSX/LASX in the kernel LoongArch: Fix module relocation error with binutils 2.41 Sui Jingfeng (2): drm: Add kms driver for loongson display controller drm/loongson: Remove a useless check in cursor_plane_atomic_async_check() Yinbo Zhu (1): spi: loongson: add bus driver for the loongson spi controller MAINTAINERS | 4 + arch/loongarch/Makefile | 2 + arch/loongarch/include/asm/pgtable.h | 3 + arch/loongarch/kernel/kfpu.c | 55 +- drivers/gpio/gpio-loongson.c | 413 +++++-- drivers/gpu/drm/Kconfig | 2 + drivers/gpu/drm/Makefile | 1 + drivers/gpu/drm/loongson/Kconfig | 17 + drivers/gpu/drm/loongson/Makefile | 22 + drivers/gpu/drm/loongson/loongson_device.c | 102 ++ drivers/gpu/drm/loongson/loongson_module.c | 33 + drivers/gpu/drm/loongson/loongson_module.h | 12 + drivers/gpu/drm/loongson/lsdc_benchmark.c | 133 +++ drivers/gpu/drm/loongson/lsdc_benchmark.h | 13 + drivers/gpu/drm/loongson/lsdc_crtc.c | 1024 +++++++++++++++++ drivers/gpu/drm/loongson/lsdc_debugfs.c | 110 ++ drivers/gpu/drm/loongson/lsdc_drv.c | 457 ++++++++ drivers/gpu/drm/loongson/lsdc_drv.h | 388 +++++++ drivers/gpu/drm/loongson/lsdc_gem.c | 311 +++++ drivers/gpu/drm/loongson/lsdc_gem.h | 37 + drivers/gpu/drm/loongson/lsdc_gfxpll.c | 199 ++++ drivers/gpu/drm/loongson/lsdc_gfxpll.h | 52 + drivers/gpu/drm/loongson/lsdc_i2c.c | 179 +++ drivers/gpu/drm/loongson/lsdc_i2c.h | 29 + drivers/gpu/drm/loongson/lsdc_irq.c | 74 ++ drivers/gpu/drm/loongson/lsdc_irq.h | 16 + drivers/gpu/drm/loongson/lsdc_output.h | 21 + drivers/gpu/drm/loongson/lsdc_output_7a1000.c | 178 +++ drivers/gpu/drm/loongson/lsdc_output_7a2000.c | 552 +++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.c | 481 ++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.h | 86 ++ drivers/gpu/drm/loongson/lsdc_plane.c | 793 +++++++++++++ drivers/gpu/drm/loongson/lsdc_probe.c | 56 + drivers/gpu/drm/loongson/lsdc_probe.h | 12 + drivers/gpu/drm/loongson/lsdc_regs.h | 406 +++++++ drivers/gpu/drm/loongson/lsdc_ttm.c | 593 ++++++++++ drivers/gpu/drm/loongson/lsdc_ttm.h | 99 ++ drivers/spi/Kconfig | 26 + drivers/spi/Makefile | 3 + drivers/spi/spi-loongson-core.c | 279 +++++ drivers/spi/spi-loongson-pci.c | 55 + drivers/spi/spi-loongson-plat.c | 47 + drivers/spi/spi-loongson.h | 49 + 43 files changed, 7345 insertions(+), 79 deletions(-) create mode 100644 drivers/gpu/drm/loongson/Kconfig create mode 100644 drivers/gpu/drm/loongson/Makefile create mode 100644 drivers/gpu/drm/loongson/loongson_device.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.h create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.c create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.h create mode 100644 drivers/gpu/drm/loongson/lsdc_crtc.c create mode 100644 drivers/gpu/drm/loongson/lsdc_debugfs.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.c create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.h create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.c create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a1000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a2000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_plane.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.h create mode 100644 drivers/gpu/drm/loongson/lsdc_regs.h create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.c create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.h create mode 100644 drivers/spi/spi-loongson-core.c create mode 100644 drivers/spi/spi-loongson-pci.c create mode 100644 drivers/spi/spi-loongson-plat.c create mode 100644 drivers/spi/spi-loongson.h -- 2.33.0

1 7

[PATCH v4 openEuler-23.09 0/3] remote_pager: fix msg_handler_peer.c build failed
by Wupeng Ma 20 Sep '23

20 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> remote_pager: fix msg_handler_peer.c build failed. Chunsheng Luo (3): mmap: export __do_mmap_mm symbol remote_pager: fix msg_handler_peer.c build failed remote_pager: delete unused file drivers/remote_pager/Kconfig | 9 + drivers/remote_pager/Makefile | 1 + drivers/remote_pager/main.c | 7 - drivers/remote_pager/msg_handler_peer.c | 111 ++------ drivers/remote_pager/swap/device/ksymbol.c | 83 ------ drivers/remote_pager/swap/device/ksymbol.h | 35 --- .../remote_pager/swap/device/swap_manager.c | 256 ------------------ .../remote_pager/swap/device/swap_manager.h | 28 -- .../swap/device/swap_policy/policy_list_lru.c | 108 -------- .../swap/device/swap_policy/swap_policy.h | 16 -- mm/mmap.c | 1 + 11 files changed, 33 insertions(+), 622 deletions(-) delete mode 100644 drivers/remote_pager/swap/device/ksymbol.c delete mode 100644 drivers/remote_pager/swap/device/ksymbol.h delete mode 100644 drivers/remote_pager/swap/device/swap_manager.c delete mode 100644 drivers/remote_pager/swap/device/swap_manager.h delete mode 100644 drivers/remote_pager/swap/device/swap_policy/policy_list_lru.c delete mode 100644 drivers/remote_pager/swap/device/swap_policy/swap_policy.h -- 2.25.1

2 4

[openEuler-23.09 0/7] LoongArch: backport drm and spi driver and some bugfixes
by Hongchen Zhang 20 Sep '23

20 Sep '23

Backport the following patches from upstream. Dan Carpenter (1): drm/loongson: Add a check for lsdc_bo_create() errors Hongchen Zhang (1): LoongArch: mm: Add p?d_leaf() definitions Huacai Chen (2): LoongArch: Allow usage of LSX/LASX in the kernel LoongArch: Fix module relocation error with binutils 2.41 Sui Jingfeng (2): drm: Add kms driver for loongson display controller drm/loongson: Remove a useless check in cursor_plane_atomic_async_check() Yinbo Zhu (1): spi: loongson: add bus driver for the loongson spi controller MAINTAINERS | 4 + arch/loongarch/Makefile | 2 + arch/loongarch/include/asm/pgtable.h | 3 + arch/loongarch/kernel/kfpu.c | 55 +- drivers/gpio/gpio-loongson.c | 413 +++++-- drivers/gpu/drm/Kconfig | 2 + drivers/gpu/drm/Makefile | 1 + drivers/gpu/drm/loongson/Kconfig | 17 + drivers/gpu/drm/loongson/Makefile | 22 + drivers/gpu/drm/loongson/loongson_device.c | 102 ++ drivers/gpu/drm/loongson/loongson_module.c | 33 + drivers/gpu/drm/loongson/loongson_module.h | 12 + drivers/gpu/drm/loongson/lsdc_benchmark.c | 133 +++ drivers/gpu/drm/loongson/lsdc_benchmark.h | 13 + drivers/gpu/drm/loongson/lsdc_crtc.c | 1024 +++++++++++++++++ drivers/gpu/drm/loongson/lsdc_debugfs.c | 110 ++ drivers/gpu/drm/loongson/lsdc_drv.c | 457 ++++++++ drivers/gpu/drm/loongson/lsdc_drv.h | 388 +++++++ drivers/gpu/drm/loongson/lsdc_gem.c | 311 +++++ drivers/gpu/drm/loongson/lsdc_gem.h | 37 + drivers/gpu/drm/loongson/lsdc_gfxpll.c | 199 ++++ drivers/gpu/drm/loongson/lsdc_gfxpll.h | 52 + drivers/gpu/drm/loongson/lsdc_i2c.c | 179 +++ drivers/gpu/drm/loongson/lsdc_i2c.h | 29 + drivers/gpu/drm/loongson/lsdc_irq.c | 74 ++ drivers/gpu/drm/loongson/lsdc_irq.h | 16 + drivers/gpu/drm/loongson/lsdc_output.h | 21 + drivers/gpu/drm/loongson/lsdc_output_7a1000.c | 178 +++ drivers/gpu/drm/loongson/lsdc_output_7a2000.c | 552 +++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.c | 481 ++++++++ drivers/gpu/drm/loongson/lsdc_pixpll.h | 86 ++ drivers/gpu/drm/loongson/lsdc_plane.c | 793 +++++++++++++ drivers/gpu/drm/loongson/lsdc_probe.c | 56 + drivers/gpu/drm/loongson/lsdc_probe.h | 12 + drivers/gpu/drm/loongson/lsdc_regs.h | 406 +++++++ drivers/gpu/drm/loongson/lsdc_ttm.c | 593 ++++++++++ drivers/gpu/drm/loongson/lsdc_ttm.h | 99 ++ drivers/spi/Kconfig | 26 + drivers/spi/Makefile | 3 + drivers/spi/spi-loongson-core.c | 279 +++++ drivers/spi/spi-loongson-pci.c | 55 + drivers/spi/spi-loongson-plat.c | 47 + drivers/spi/spi-loongson.h | 49 + 43 files changed, 7345 insertions(+), 79 deletions(-) create mode 100644 drivers/gpu/drm/loongson/Kconfig create mode 100644 drivers/gpu/drm/loongson/Makefile create mode 100644 drivers/gpu/drm/loongson/loongson_device.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.c create mode 100644 drivers/gpu/drm/loongson/loongson_module.h create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.c create mode 100644 drivers/gpu/drm/loongson/lsdc_benchmark.h create mode 100644 drivers/gpu/drm/loongson/lsdc_crtc.c create mode 100644 drivers/gpu/drm/loongson/lsdc_debugfs.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.c create mode 100644 drivers/gpu/drm/loongson/lsdc_drv.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gem.h create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_gfxpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.c create mode 100644 drivers/gpu/drm/loongson/lsdc_i2c.h create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.c create mode 100644 drivers/gpu/drm/loongson/lsdc_irq.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output.h create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a1000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_output_7a2000.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.c create mode 100644 drivers/gpu/drm/loongson/lsdc_pixpll.h create mode 100644 drivers/gpu/drm/loongson/lsdc_plane.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.c create mode 100644 drivers/gpu/drm/loongson/lsdc_probe.h create mode 100644 drivers/gpu/drm/loongson/lsdc_regs.h create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.c create mode 100644 drivers/gpu/drm/loongson/lsdc_ttm.h create mode 100644 drivers/spi/spi-loongson-core.c create mode 100644 drivers/spi/spi-loongson-pci.c create mode 100644 drivers/spi/spi-loongson-plat.c create mode 100644 drivers/spi/spi-loongson.h -- 2.33.0

1 2

[PATCH v3 openEuler-23.09 0/3] remote_pager: fix msg_handler_peer.c build failed
by Wupeng Ma 20 Sep '23

20 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> remote_pager: fix msg_handler_peer.c build failed. Chunsheng Luo (3): mmap: export __do_mmap_mm symbol remote_pager: fix msg_handler_peer.c build failed remote_pager: delete unused file drivers/remote_pager/Kconfig | 8 + drivers/remote_pager/Makefile | 1 + drivers/remote_pager/main.c | 7 - drivers/remote_pager/msg_handler_peer.c | 111 ++------ drivers/remote_pager/swap/device/ksymbol.c | 83 ------ drivers/remote_pager/swap/device/ksymbol.h | 35 --- .../remote_pager/swap/device/swap_manager.c | 256 ------------------ .../remote_pager/swap/device/swap_manager.h | 28 -- .../swap/device/swap_policy/policy_list_lru.c | 108 -------- .../swap/device/swap_policy/swap_policy.h | 16 -- mm/mmap.c | 1 + 11 files changed, 32 insertions(+), 622 deletions(-) delete mode 100644 drivers/remote_pager/swap/device/ksymbol.c delete mode 100644 drivers/remote_pager/swap/device/ksymbol.h delete mode 100644 drivers/remote_pager/swap/device/swap_manager.c delete mode 100644 drivers/remote_pager/swap/device/swap_manager.h delete mode 100644 drivers/remote_pager/swap/device/swap_policy/policy_list_lru.c delete mode 100644 drivers/remote_pager/swap/device/swap_policy/swap_policy.h -- 2.25.1

2 4

[PATCH openEuler-22.03-LTS 0/5] x86/speculation: Add force option to GDS mitigation
by Zeng Heng 19 Sep '23

19 Sep '23

Arnd Bergmann (1): x86: Move gds_ucode_mitigated() declaration to header Daniel Sneddon (3): x86/speculation: Add force option to GDS mitigation x86/speculation: Add Kconfig option for GDS KVM: Add GDS_NO support to KVM Dave Hansen (1): Documentation/x86: Fix backwards on/off logic about YMM support .../hw-vuln/gather_data_sampling.rst | 18 ++++++++--- .../admin-guide/kernel-parameters.txt | 8 ++++- arch/x86/Kconfig | 19 ++++++++++++ arch/x86/include/asm/processor.h | 2 ++ arch/x86/kernel/cpu/bugs.c | 31 ++++++++++++++++++- arch/x86/kvm/x86.c | 3 ++ 6 files changed, 75 insertions(+), 6 deletions(-) -- 2.25.1

2 6

[PATCH openEuler-23.09 v1] sch_netem: fix issues in netem_change() vs get_dist_table()
by Yue Haibing 19 Sep '23

19 Sep '23

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v6.5-rc1 commit 11b73313c12403f617b47752db0ab3deef201af7 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I80FL9 CVE: NA -------------------------------- In blamed commit, I missed that get_dist_table() was allocating memory using GFP_KERNEL, and acquiring qdisc lock to perform the swap of newly allocated table with current one. In this patch, get_dist_table() is allocating memory and copy user data before we acquire the qdisc lock. Then we perform swap operations while being protected by the lock. Note that after this patch netem_change() no longer can do partial changes. If an error is returned, qdisc conf is left unchanged. Fixes: 2174a08db80d ("sch_netem: acquire qdisc lock in netem_change()") Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: Stephen Hemminger <stephen(a)networkplumber.org> Acked-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Reviewed-by: Simon Horman <simon.horman(a)corigine.com> Link: https://lore.kernel.org/r/20230622181503.2327695-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> --- net/sched/sch_netem.c | 59 ++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 34 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e79be1b3e74d..b93ec2a3454e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -773,12 +773,10 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, - const struct nlattr *attr) +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; @@ -793,13 +791,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(*tbl, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } @@ -956,6 +948,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; @@ -966,6 +960,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; @@ -975,26 +981,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; + q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, &q->delay_dist, - tb[TCA_NETEM_DELAY_DIST]); - if (ret) - goto get_table_failure; - } - - if (tb[TCA_NETEM_SLOT_DIST]) { - ret = get_dist_table(sch, &q->slot_dist, - tb[TCA_NETEM_SLOT_DIST]); - if (ret) - goto get_table_failure; - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); @@ -1044,17 +1041,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, unlock: sch_tree_unlock(sch); - return ret; -get_table_failure: - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - - goto unlock; +table_free: + dist_free(delay_dist); + dist_free(slot_dist); + return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, -- 2.34.1

2 1

[PATCH OLK-5.10] [Backport] media: ttusb-dec: fix memory leak in ttusb_dec_exit_dvb()
by ChenXiaoSong 19 Sep '23

19 Sep '23

From: Hyunwoo Kim <imv4bel(a)gmail.com> stable inclusion from stable-v5.10.183 commit eb37fef417a246fe54530901a3ea9c0abc914fc2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I635HP CVE: CVE-2022-45887 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 517a281338322ff8293f988771c98aaa7205e457 ] Since dvb_frontend_detach() is not called in ttusb_dec_exit_dvb(), which is called when the device is disconnected, dvb_frontend_free() is not finally called. This causes a memory leak just by repeatedly plugging and unplugging the device. Fix this issue by adding dvb_frontend_detach() to ttusb_dec_exit_dvb(). Link: https://lore.kernel.org/linux-media/20221117045925.14297-5-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim <imv4bel(a)gmail.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> --- drivers/media/usb/ttusb-dec/ttusb_dec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index df6c5e4a0f05..68f88143c8a6 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -1551,8 +1551,7 @@ static void ttusb_dec_exit_dvb(struct ttusb_dec *dec) dvb_dmx_release(&dec->demux); if (dec->fe) { dvb_unregister_frontend(dec->fe); - if (dec->fe->ops.release) - dec->fe->ops.release(dec->fe); + dvb_frontend_detach(dec->fe); } dvb_unregister_adapter(&dec->adapter); } -- 2.31.1

2 1

[PATCH openEuler-23.09 0/2] xfs: fix NULL dereference in xlog_cil_pcp_dead
by Baokun Li 19 Sep '23

19 Sep '23

Darrick J. Wong (2): xfs: fix per-cpu CIL structure aggregation racing with dying cpus xfs: use per-mount cpumask to track nonempty percpu inodegc lists fs/xfs/xfs_icache.c | 78 ++++++++++++++++--------------------------- fs/xfs/xfs_icache.h | 1 - fs/xfs/xfs_log_cil.c | 52 +++++++++-------------------- fs/xfs/xfs_log_priv.h | 14 ++++---- fs/xfs/xfs_mount.h | 6 ++-- fs/xfs/xfs_super.c | 5 +-- 6 files changed, 55 insertions(+), 101 deletions(-) -- 2.31.1

2 3

[PATCH v3 openEuler-23.09 0/2] remote_pager: fix msg_handler_peer.c build failed
by Wupeng Ma 19 Sep '23

19 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> remote_pager: fix msg_handler_peer.c build failed. Chunsheng Luo (2): mmap: export __do_mmap_mm symbol remote_pager: fix msg_handler_peer.c build failed drivers/remote_pager/Kconfig | 9 ++ drivers/remote_pager/Makefile | 1 + drivers/remote_pager/main.c | 7 - drivers/remote_pager/msg_handler_peer.c | 197 +++++++++++++----------- mm/mmap.c | 1 + 5 files changed, 117 insertions(+), 98 deletions(-) -- 2.25.1

2 3

[PATCH v2 openEuler-23.09 0/2] remote_pager: fix msg_handler_peer.c build failed
by Wupeng Ma 19 Sep '23

19 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> remote_pager: fix msg_handler_peer.c build failed. Chunsheng Luo (2): mmap: export __do_mmap_mm symbol remote_pager: fix msg_handler_peer.c build failed drivers/remote_pager/Kconfig | 9 ++ drivers/remote_pager/Makefile | 1 + drivers/remote_pager/main.c | 7 - drivers/remote_pager/msg_handler_peer.c | 197 +++++++++++++----------- mm/mmap.c | 1 + 5 files changed, 117 insertions(+), 98 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS] crypto: hisilicon/qm - prevent soft lockup in qm_poll_qp()'s loop
by w00416078 19 Sep '23

19 Sep '23

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I82LC6 CVE: NA -------------------------------- The function qm_poll_qp() may take a while due to complex req_cb, so soft lockup may occur in kernel with preemption disabled. Add a cond_resched() to prevent that. Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index e0fd83465dce..739b1a6565fd 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -540,6 +540,8 @@ static void qm_poll_qp(struct hisi_qp *qp, struct hisi_qm *qm) qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, qp->qp_status.cq_head, 0); atomic_dec(&qp->qp_status.used); + + cond_resched(); } /* set c_flag */ qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, -- 2.30.0

2 1

[PATCH openEuler-1.0-LTS] media: ttusb-dec: fix memory leak in ttusb_dec_exit_dvb()
by ChenXiaoSong 19 Sep '23

19 Sep '23

From: Hyunwoo Kim <imv4bel(a)gmail.com> stable inclusion from stable-v4.19.285 commit 3e5af0745a4702ab0df2f880bfe0431eb30f9164 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I635HP CVE: CVE-2022-45887 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit 517a281338322ff8293f988771c98aaa7205e457 ] Since dvb_frontend_detach() is not called in ttusb_dec_exit_dvb(), which is called when the device is disconnected, dvb_frontend_free() is not finally called. This causes a memory leak just by repeatedly plugging and unplugging the device. Fix this issue by adding dvb_frontend_detach() to ttusb_dec_exit_dvb(). Link: https://lore.kernel.org/linux-media/20221117045925.14297-5-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim <imv4bel(a)gmail.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> --- drivers/media/usb/ttusb-dec/ttusb_dec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index f34efa7c61b4..c915e555897b 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -1561,8 +1561,7 @@ static void ttusb_dec_exit_dvb(struct ttusb_dec *dec) dvb_dmx_release(&dec->demux); if (dec->fe) { dvb_unregister_frontend(dec->fe); - if (dec->fe->ops.release) - dec->fe->ops.release(dec->fe); + dvb_frontend_detach(dec->fe); } dvb_unregister_adapter(&dec->adapter); } -- 2.31.1

2 1

[PATCH OLK-5.10] ext4: fix rec_len verify error
by Baokun Li 19 Sep '23

19 Sep '23

From: Shida Zhang <zhangshida(a)kylinos.cn> mainline inclusion from mainline-v6.6-rc2 commit 7fda67e8c3ab6069f75888f67958a6d30454a9f6 category: bugfix bugzilla: 189039, https://gitee.com/openeuler/kernel/issues/I7OXK8 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- With the configuration PAGE_SIZE 64k and filesystem blocksize 64k, a problem occurred when more than 13 million files were directly created under a directory: EXT4-fs error (device xx): ext4_dx_csum_set:492: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D. EXT4-fs error (device xx): ext4_dx_csum_verify:463: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D. EXT4-fs error (device xx): dx_probe:856: inode #xxxx: block 8188: comm xxxxx: Directory index failed checksum When enough files are created, the fake_dirent->reclen will be 0xffff. it doesn't equal to the blocksize 65536, i.e. 0x10000. But it is not the same condition when blocksize equals to 4k. when enough files are created, the fake_dirent->reclen will be 0x1000. it equals to the blocksize 4k, i.e. 0x1000. The problem seems to be related to the limitation of the 16-bit field when the blocksize is set to 64k. To address this, helpers like ext4_rec_len_{from,to}_disk has already been introduced to complete the conversion between the encoded and the plain form of rec_len. So fix this one by using the helper, and all the other in this file too. Cc: stable(a)kernel.org Fixes: dbe89444042a ("ext4: Calculate and verify checksums for htree nodes") Suggested-by: Andreas Dilger <adilger(a)dilger.ca> Suggested-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Shida Zhang <zhangshida(a)kylinos.cn> Reviewed-by: Andreas Dilger <adilger(a)dilger.ca> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Link: https://lore.kernel.org/r/20230803060938.1929759-1-zhangshida@kylinos.cn Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/namei.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 746aed40a3c8..a01aba88c39d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -344,17 +344,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, struct buffer_head *bh) { struct ext4_dir_entry_tail *t; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); #ifdef PARANOID struct ext4_dir_entry *d, *top; d = (struct ext4_dir_entry *)bh->b_data; top = (struct ext4_dir_entry *)(bh->b_data + - (EXT4_BLOCK_SIZE(inode->i_sb) - - sizeof(struct ext4_dir_entry_tail))); - while (d < top && d->rec_len) + (blocksize - sizeof(struct ext4_dir_entry_tail))); + while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize)) d = (struct ext4_dir_entry *)(((void *)d) + - le16_to_cpu(d->rec_len)); + ext4_rec_len_from_disk(d->rec_len, blocksize)); if (d != top) return NULL; @@ -365,7 +365,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, #endif if (t->det_reserved_zero1 || - le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) || + (ext4_rec_len_from_disk(t->det_rec_len, blocksize) != + sizeof(struct ext4_dir_entry_tail)) || t->det_reserved_zero2 || t->det_reserved_ft != EXT4_FT_DIR_CSUM) return NULL; @@ -446,13 +447,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode, struct ext4_dir_entry *dp; struct dx_root_info *root; int count_offset; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); + unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize); - if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb)) + if (rlen == blocksize) count_offset = 8; - else if (le16_to_cpu(dirent->rec_len) == 12) { + else if (rlen == 12) { dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); - if (le16_to_cpu(dp->rec_len) != - EXT4_BLOCK_SIZE(inode->i_sb) - 12) + if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12) return NULL; root = (struct dx_root_info *)(((void *)dp + 12)); if (root->reserved_zero || @@ -1261,6 +1263,7 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, unsigned int buflen = bh->b_size; char *base = bh->b_data; struct dx_hash_info h = *hinfo; + int blocksize = EXT4_BLOCK_SIZE(dir->i_sb); if (ext4_has_metadata_csum(dir->i_sb)) buflen -= sizeof(struct ext4_dir_entry_tail); @@ -1274,11 +1277,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; - map_tail->size = le16_to_cpu(de->rec_len); + map_tail->size = ext4_rec_len_from_disk(de->rec_len, + blocksize); count++; cond_resched(); } - de = ext4_next_entry(de, dir->i_sb->s_blocksize); + de = ext4_next_entry(de, blocksize); } return count; } -- 2.31.1

2 1

[PATCH openEuler-23.09 0/2] remote_pager: fix msg_handler_peer.c build failed
by Wupeng Ma 19 Sep '23

19 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> remote_pager: fix msg_handler_peer.c build failed. Chunsheng Luo (2): mmap: export __do_mmap_mm symbol remote_pager: fix msg_handler_peer.c build failed drivers/remote_pager/Kconfig | 9 ++ drivers/remote_pager/Makefile | 1 + drivers/remote_pager/main.c | 7 - drivers/remote_pager/msg_handler_peer.c | 197 +++++++++++++----------- mm/mmap.c | 1 + 5 files changed, 117 insertions(+), 98 deletions(-) -- 2.25.1

2 3

[PATCH OLK-5.10] Add new config 'CONFIG_EXT4_ERROR_REPORT' to control ext3/4 error reporting
by Baokun Li 19 Sep '23

19 Sep '23

From: Zhihao Cheng <chengzhihao1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 187975, https://gitee.com/openeuler/kernel/issues/I7T77P -------------------------------- Add new config 'CONFIG_EXT4_ERROR_REPORT' to control ext3/4 error reporting. Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/ext4/Kconfig | 8 ++++++++ fs/ext4/ext4.h | 2 ++ fs/ext4/super.c | 19 +++++++++++++++++++ 5 files changed, 31 insertions(+) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index f055d8e93bc4..514d35e099f7 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -6211,6 +6211,7 @@ CONFIG_EXT4_FS=m CONFIG_EXT4_USE_FOR_EXT2=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ERROR_REPORT=y # CONFIG_EXT4_DEBUG is not set CONFIG_JBD2=m # CONFIG_JBD2_DEBUG is not set diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 9adedd9d615a..203c5e353d94 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -7308,6 +7308,7 @@ CONFIG_EXT4_FS=m CONFIG_EXT4_USE_FOR_EXT2=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ERROR_REPORT=y # CONFIG_EXT4_DEBUG is not set CONFIG_JBD2=m # CONFIG_JBD2_DEBUG is not set diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 86699c8cab28..ae108d47ff00 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -117,3 +117,11 @@ config EXT4_KUNIT_TESTS to the KUnit documentation in Documentation/dev-tools/kunit/. If unsure, say N. + +config EXT4_ERROR_REPORT + bool "Ext4 error reporting by netlink" + depends on EXT4_FS && NET + default n + help + Implement the ext3/ext4 file system error report. Report error to + userspace by netlink diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 56776dea9cd1..74f72a22f5ec 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -46,6 +46,7 @@ #include <linux/compiler.h> +#ifdef CONFIG_EXT4_ERROR_REPORT #define NL_EXT4_ERROR_GROUP 1 #define EXT4_ERROR_MAGIC 0xAE32014U struct ext4_err_msg { @@ -54,6 +55,7 @@ struct ext4_err_msg { unsigned long s_flags; int ext4_errno; }; +#endif /* * The fourth extended filesystem constants/structures diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4afc9dab14cf..d24816506339 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -55,9 +55,11 @@ #include "mballoc.h" #include "fsmap.h" +#ifdef CONFIG_EXT4_ERROR_REPORT #include <uapi/linux/netlink.h> #include <net/sock.h> #include <net/net_namespace.h> +#endif #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> @@ -90,8 +92,10 @@ static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum); +#ifdef CONFIG_EXT4_ERROR_REPORT static void ext4_netlink_send_info(struct super_block *sb, int ext4_errno); static struct sock *ext4nl; +#endif /* * Lock ordering @@ -616,6 +620,7 @@ static void save_error_info(struct super_block *sb, int error, spin_unlock(&sbi->s_error_lock); } +#ifdef CONFIG_EXT4_ERROR_REPORT static void ext4_netlink_send_info(struct super_block *sb, int ext4_errno) { int size; @@ -651,6 +656,7 @@ static void ext4_netlink_send_info(struct super_block *sb, int ext4_errno) kfree_skb(skb); } } +#endif /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. @@ -713,11 +719,16 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, sb->s_id); } +#ifdef CONFIG_EXT4_ERROR_REPORT if (sb_rdonly(sb)) return; if (continue_fs) goto out; +#else + if (sb_rdonly(sb) || continue_fs) + return; +#endif ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); @@ -727,8 +738,10 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, */ smp_wmb(); sb->s_flags |= SB_RDONLY; +#ifdef CONFIG_EXT4_ERROR_REPORT out: ext4_netlink_send_info(sb, force_ro ? 2 : 1); +#endif } static void flush_stashed_error_work(struct work_struct *work) @@ -6855,7 +6868,9 @@ wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; static int __init ext4_init_fs(void) { int i, err; +#ifdef CONFIG_EXT4_ERROR_REPORT struct netlink_kernel_cfg cfg = {.groups = NL_EXT4_ERROR_GROUP,}; +#endif ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64); ext4_li_info = NULL; @@ -6908,9 +6923,11 @@ static int __init ext4_init_fs(void) if (err) goto out; +#ifdef CONFIG_EXT4_ERROR_REPORT ext4nl = netlink_kernel_create(&init_net, NETLINK_FILESYSTEM, &cfg); if (!ext4nl) printk(KERN_ERR "EXT4-fs: Cannot create netlink socket.\n"); +#endif return 0; out: unregister_as_ext2(); @@ -6951,7 +6968,9 @@ static void __exit ext4_exit_fs(void) ext4_exit_post_read_processing(); ext4_exit_es(); ext4_exit_pending(); +#ifdef CONFIG_EXT4_ERROR_REPORT netlink_kernel_release(ext4nl); +#endif } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); -- 2.31.1

2 1

[PATCH 1/2] mmap: export __do_mmap_mm symbol
by Wupeng Ma 19 Sep '23

19 Sep '23

From: Chunsheng Luo <luochunsheng(a)huawei.com> euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7WLVX --------------------------------------------- export __do_mmap_mm symbol by referring to the earlier version Signed-off-by: Chunsheng Luo <luochunsheng(a)huawei.com> --- mm/mmap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/mmap.c b/mm/mmap.c index 2aef07b8a85e..819c37e7eb1f 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1469,6 +1469,7 @@ unsigned long __do_mmap_mm(struct mm_struct *mm, struct file *file, unsigned lon *populate = len; return addr; } +EXPORT_SYMBOL(__do_mmap_mm); unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, -- 2.33.0

1 1

[PATCH OLK-5.10] sched/qos: Fix warning in CPU hotplug scenarios
by Xia Fukun 19 Sep '23

19 Sep '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZMCB CVE: NA -------------------------------- CPU hotplug callbacks race against distribute_cfs_runtime(), when the QOS_SCHED feature is enabled, there may be situations where the cfs_rq-> runtime_remaining == 1 and cfs_rq is QOS_THROTTLED. Turn off the Qos_throttle when the CPU is offline. No longer allocate time to cfs_rq in this scenario to fix the warning. Fixes: 4eb6eb7941dc ("sched/qos: Don't unthrottle cfs_rq when cfs_rq is throttled by qos") Signed-off-by: Xia Fukun <xiafukun(a)huawei.com> --- kernel/sched/fair.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index daa853b19853..b8bf7acb9f9a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5267,6 +5267,19 @@ static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) if (!cfs_rq_throttled(cfs_rq)) goto next; + /* + * CPU hotplug callbacks race against distribute_cfs_runtime() + * when the QOS_SCHED feature is enabled, there may be + * situations where the runtime_remaining > 0. + * Qos_sched does not care whether the cfs_rq has time left, + * so no longer allocate time to cfs_rq in this scenario. + */ +#ifdef CONFIG_QOS_SCHED + if (cfs_rq->throttled == QOS_THROTTLED && + cfs_rq->runtime_remaining > 0) + goto next; +#endif + /* By the above check, this should never be true */ SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); @@ -7923,6 +7936,10 @@ static __always_inline bool check_qos_cfs_rq(struct cfs_rq *cfs_rq) if (unlikely(cfs_rq && is_offline_level(cfs_rq->tg->qos_level) && !sched_idle_cpu(smp_processor_id()) && cfs_rq->h_nr_running == cfs_rq->idle_h_nr_running)) { + + if (!rq_of(cfs_rq)->online) + return false; + throttle_qos_cfs_rq(cfs_rq); return true; } -- 2.34.1

2 1

[PATCH openEuler-23.09] mm/mlock: return EINVAL for illegal user memory range in mlock
by Wupeng Ma 19 Sep '23

19 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7TW89 -------------------------------- While testing mlock, we have a problem if the len of mlock is ULONG_MAX. The return value of mlock is zero. But nothing will be locked since the len in do_mlock overflows to zero due to the following code in mlock: len = PAGE_ALIGN(len + (offset_in_page(start))); The same problem happens in munlock. Since TASK_SIZE is the maximum user space address. The start or len of mlock shouldn't be bigger than this. Function access_ok can be used to check this issue, so return -EINVAL if bigger. Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- mm/mlock.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/mm/mlock.c b/mm/mlock.c index 40b43f8740df..e90139d42f88 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -479,8 +479,6 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, end = start + len; if (end < start) return -EINVAL; - if (end == start) - return 0; vma = vma_iter_load(&vmi); if (!vma) return -ENOMEM; @@ -574,9 +572,15 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla if (!can_do_mlock()) return -EPERM; + if (!len) + return 0; + len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; + if (!len) + return -EINVAL; + lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; @@ -634,8 +638,13 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) start = untagged_addr(start); + if (!len) + return 0; + len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; + if (!len) + return -EINVAL; if (mmap_write_lock_killable(current->mm)) return -EINTR; -- 2.25.1

2 1

[PATCH OLK-5.10] uacce: modify the configuration mode of device isolation stragety
by Wenkai Lin 19 Sep '23

19 Sep '23

From: Qi Tao <taoqi10(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I82ARL CVE: NA ------------------------------------------------------------------ cancel the reference counting of the accelerator device so that the device (with hardware errors) isolation stragety can also be modified while the accelerator is running a task. Signed-off-by: Qi Tao <taoqi10(a)huawei.com> Signed-off-by: JiangShui Yang <yangjiangshui(a)h-partners.com> --- drivers/misc/uacce/uacce.c | 5 ----- include/linux/uacce.h | 2 -- 2 files changed, 7 deletions(-) diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index 21a4f5892aff..7a64eed01df7 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -88,7 +88,6 @@ static int uacce_put_queue(struct uacce_queue *q) uacce->ops->put_queue(q); q->state = UACCE_Q_ZOMBIE; - atomic_dec(&uacce->ref); return 0; } @@ -348,7 +347,6 @@ static int uacce_fops_open(struct inode *inode, struct file *filep) goto out_with_bond; } - atomic_inc(&uacce->ref); init_waitqueue_head(&q->wait); filep->private_data = q; q->state = UACCE_Q_INIT; @@ -821,9 +819,6 @@ static ssize_t isolate_strategy_store(struct device *dev, struct device_attribut if (val > UACCE_MAX_ERR_THRESHOLD) return -EINVAL; - if (atomic_read(&uacce->ref)) - return -EBUSY; - ret = uacce->ops->isolate_err_threshold_write(uacce, val); if (ret) return ret; diff --git a/include/linux/uacce.h b/include/linux/uacce.h index 8187c1bda236..9b0c04a9cff7 100644 --- a/include/linux/uacce.h +++ b/include/linux/uacce.h @@ -148,7 +148,6 @@ struct uacce_queue { * @mutex: protects uacce operation * @priv: private pointer of the uacce * @queues: list of queues - * @ref: reference of the uacce */ struct uacce_device { const char *algs; @@ -164,7 +163,6 @@ struct uacce_device { struct device dev; struct mutex mutex; void *priv; - atomic_t ref; struct uacce_err_isolate *isolate; struct list_head queues; }; -- 2.30.0

2 1

[PATCH OLK-5.10 v2] jbd2: Fix potential data lost in recovering journal raced with synchronizing fs bdev
by Zhihao Cheng 19 Sep '23

19 Sep '23

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I828EV CVE: NA Reference: https://lore.kernel.org/linux-ext4/20230911155822.kbg2xayc7ys24kay@quack3/T… -------------------------------- JBD2 makes sure journal data is fallen on fs device by sync_blockdev(), however, other process could intercept the EIO information from bdev's mapping, which leads journal recovering successful even EIO occurs during data written back to fs device. We found this problem in our product, iscsi + multipath is chosen for block device of ext4. Unstable network may trigger kpartx to rescan partitions in device mapper layer. Detailed process is shown as following: mount kpartx irq jbd2_journal_recover do_one_pass memcpy(nbh->b_data, obh->b_data) // copy data to fs dev from journal mark_buffer_dirty // mark bh dirty vfs_read generic_file_read_iter // dio filemap_write_and_wait_range __filemap_fdatawrite_range do_writepages block_write_full_folio submit_bh_wbc >> EIO occurs in disk << end_buffer_async_write mark_buffer_write_io_error mapping_set_error set_bit(AS_EIO, &mapping->flags) // set! filemap_check_errors test_and_clear_bit(AS_EIO, &mapping->flags) // clear! err2 = sync_blockdev filemap_write_and_wait filemap_check_errors test_and_clear_bit(AS_EIO, &mapping->flags) // false err2 = 0 Filesystem is mounted successfully even data from journal is failed written into disk, and ext4/ocfs2 could become corrupted. Fix it by comparing the wb_err state in fs block device before recovering and after recovering. Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217888 Cc: stable(a)vger.kernel.org Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> --- v1->v3: Initialize wb_err. Untialized wb_err could be same with mapping->wb_err(eg. EIO without ERRSEQ_SEEN). When EIO occurs again, mapping->wb_err won't be changed, and wb_err is still same with mapping->wb_err. fs/jbd2/recovery.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 9e4537349380..cdf4c553f058 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -292,6 +292,8 @@ int jbd2_journal_recover(journal_t *journal) journal_superblock_t * sb; struct recovery_info info; + errseq_t wb_err; + struct address_space *mapping; memset(&info, 0, sizeof(info)); sb = journal->j_superblock; @@ -309,6 +311,9 @@ int jbd2_journal_recover(journal_t *journal) return 0; } + wb_err = 0; + mapping = journal->j_fs_dev->bd_inode->i_mapping; + errseq_check_and_advance(&mapping->wb_err, &wb_err); err = do_one_pass(journal, &info, PASS_SCAN); if (!err) err = do_one_pass(journal, &info, PASS_REVOKE); @@ -327,6 +332,9 @@ int jbd2_journal_recover(journal_t *journal) jbd2_journal_clear_revoke(journal); err2 = sync_blockdev(journal->j_fs_dev); + if (!err) + err = err2; + err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err); if (!err) err = err2; /* Make sure all replayed data is on permanent storage */ -- 2.31.1

2 1

[PATCH openEuler-23.09] config: Disable x86 IBT for kpatch
by Wei Li 19 Sep '23

19 Sep '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I82GQG -------------------------------- The CONFIG_X86_KERNEL_IBT option causes the compiled symbols to lack the __prefix__ symbol, leading kpatch to incorrectly determine that the symbol has no padding. In reality, the symbol does have padding, resulting in a compilation failure for kpatch. Let's disable IBT for now. Signed-off-by: Wei Li <liwei391(a)huawei.com> --- arch/x86/configs/openeuler_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 6bbaaaa82a0b..d3c0da3ddd64 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -457,7 +457,7 @@ CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT=1 CONFIG_X86_PAT=y CONFIG_ARCH_USES_PG_UNCACHED=y CONFIG_X86_UMIP=y -CONFIG_X86_KERNEL_IBT=y +# CONFIG_X86_KERNEL_IBT is not set CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS=y CONFIG_X86_INTEL_TSX_MODE_OFF=y # CONFIG_X86_INTEL_TSX_MODE_ON is not set -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] crypto:hisilicon/qm - cache write back before flr and poweroff
by w00416078 19 Sep '23

19 Sep '23

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4YKIJ CVE: NA -------------------------------- In order to prevent an error when the hardware writes back cache, the driver should write back the hardware cache before flr and poweroff. If vfs is enabled, we should process abnormal scenes of the whole vfs. Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> Reviewed-by: Weili Qian <qianweili(a)huawei.com> Reviewed-by: Ling Mingqiang <lingmingqiang(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 8fa855fd2387..e0fd83465dce 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -2772,6 +2772,8 @@ void hisi_qm_dev_shutdown(struct pci_dev *pdev) ret = hisi_qm_stop(qm, QM_NORMAL); if (ret) dev_err(&pdev->dev, "Fail to stop qm in shutdown!\n"); + + hisi_qm_cache_wb(qm); } EXPORT_SYMBOL_GPL(hisi_qm_dev_shutdown); @@ -3718,12 +3720,16 @@ static int qm_vf_reset_prepare(struct pci_dev *pdev, pci_save_state(dev); ret = hisi_qm_stop(qm, stop_reason); - if (ret) - goto prepare_fail; + if (ret) { + hisi_qm_set_hw_reset(qm, + QM_RESET_STOP_TX_OFFSET); + hisi_qm_set_hw_reset(qm, + QM_RESET_STOP_RX_OFFSET); + atomic_set(&qm->status.flags, QM_STOP); + } } } -prepare_fail: mutex_unlock(&qm_list->lock); return ret; } @@ -4117,19 +4123,26 @@ void hisi_qm_reset_prepare(struct pci_dev *pdev) if (qm->vfs_num) { ret = qm_vf_reset_prepare(pdev, qm->qm_list, QM_FLR); - if (ret) { - pci_err(pdev, "Fails to prepare reset!\n"); - return; - } + if (ret) + pci_err(pdev, "Failed to stop vfs!\n"); } ret = hisi_qm_stop(qm, QM_FLR); if (ret) { - pci_err(pdev, "Fails to stop QM!\n"); - return; + pci_err(pdev, "Failed to stop QM!\n"); + goto err_prepare; } + hisi_qm_cache_wb(qm); pci_info(pdev, "FLR resetting...\n"); + return; + +err_prepare: + pci_info(pdev, "FLR resetting prepare failed!\n"); + hisi_qm_set_hw_reset(qm, QM_RESET_STOP_TX_OFFSET); + hisi_qm_set_hw_reset(qm, QM_RESET_STOP_RX_OFFSET); + atomic_set(&qm->status.flags, QM_STOP); + hisi_qm_cache_wb(qm); } EXPORT_SYMBOL_GPL(hisi_qm_reset_prepare); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS v2 00/11] Fix booting failure on arm64
by Wei Li 18 Sep '23

18 Sep '23

The arm64 test machine boot failed when using hulk_defconfig after d63c76835476 ("arm64: efi: Execute runtime services from a dedicated stack"), revert this patch set first for weekly release. Wei Li (11): Revert "arm64: efi: Make efi_rt_lock a raw_spinlock" Revert "efi: rt-wrapper: Add missing include" Revert "arm64: efi: Recover from synchronous exceptions occurring in firmware" Revert "arm64: efi: Execute runtime services from a dedicated stack" Revert "efi: fix userspace infinite retry read efivars after EFI runtime services page fault" Revert "arm64: efi: Restore register x18 if it was corrupted" Revert "x86/efi: fix a -Wtype-limits compilation warning" Revert "efi: Fix build error due to enum collision between efi.h and ima.h" Revert "efi: Fix debugobjects warning on 'efi_rts_work'" Revert "efi/x86: Handle page faults occurring while running EFI runtime services" Revert "efi: Make efi_rts_work accessible to efi page fault handler" arch/arm64/include/asm/efi.h | 12 --- arch/arm64/kernel/efi-rt-wrapper.S | 49 +---------- arch/arm64/kernel/efi.c | 50 ----------- arch/arm64/mm/fault.c | 4 - arch/x86/include/asm/efi.h | 1 - arch/x86/mm/fault.c | 9 -- arch/x86/platform/efi/quirks.c | 78 ----------------- drivers/firmware/efi/runtime-wrappers.c | 109 +++++++++++++++--------- include/linux/efi.h | 42 --------- 9 files changed, 70 insertions(+), 284 deletions(-) -- 2.25.1

2 12

[PATCH openEuler-1.0-LTS] crypto:hisilicon/sec - modify hw endian config
by w00416078 18 Sep '23

18 Sep '23

From: Yu'an Wang <wangyuan46(a)huawei.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4YKLC CVE: NA -------------------------------- When the endian configuration of the hardware is abnormal, it will affect the normal function. Currently the soft configuration method can't restore the faulty device. The endian needs to be configured according to the system properties. So fix it. Signed-off-by: Yu'an Wang <wangyuan46(a)huawei.com> Reviewed-by: Kai Ye <yekai13(a)huawei.com> Reviewed-by: Ling Mingqiang <lingmingqiang(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> --- drivers/crypto/hisilicon/sec2/sec_main.c | 36 +++++++----------------- 1 file changed, 10 insertions(+), 26 deletions(-) diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 58f726ba022f..a568d5363c1e 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -255,33 +255,19 @@ static const struct pci_device_id sec_dev_ids[] = { }; MODULE_DEVICE_TABLE(pci, sec_dev_ids); -static u8 sec_get_endian(struct hisi_qm *qm) +static void sec_set_endian(struct hisi_qm *qm) { u32 reg; - /* - * As for VF, it is a wrong way to get endian setting by - * reading a register of the engine - */ - if (qm->pdev->is_virtfn) { - dev_err_ratelimited(&qm->pdev->dev, - "cannot access a register in VF!\n"); - return SEC_LE; - } - reg = readl_relaxed(qm->io_base + SEC_ENGINE_PF_CFG_OFF + - SEC_ACC_COMMON_REG_OFF + SEC_CONTROL_REG); - - /* BD little endian mode */ - if (!(reg & BIT(0))) - return SEC_LE; + reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG)); + reg &= ~(BIT(1) | BIT(0)); + if (IS_ENABLED(CONFIG_64BIT)) + reg |= BIT(1); - /* BD 32-bits big endian mode */ - else if (!(reg & BIT(1))) - return SEC_32BE; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + reg |= BIT(0); - /* BD 64-bits big endian mode */ - else - return SEC_64BE; + writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG)); } static int sec_engine_init(struct hisi_qm *qm) @@ -331,9 +317,7 @@ static int sec_engine_init(struct hisi_qm *qm) SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG3)); /* config endian */ - reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG)); - reg |= sec_get_endian(qm); - writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG)); + sec_set_endian(qm); return 0; } @@ -813,7 +797,7 @@ static int sec_qm_pre_init(struct hisi_qm *qm, struct pci_dev *pdev) { int ret; - qm->algs = "sec\ncipher\ndigest\naead\n"; + qm->algs = "cipher\ndigest\naead\n"; qm->uacce_mode = uacce_mode; qm->pdev = pdev; ret = hisi_qm_pre_init(qm, pf_q_num, SEC_PF_DEF_Q_BASE); -- 2.34.1

2 1

[PATCH OLK-5.10 0/2] Not clear ATA_PFLAG_EH_PENDING and not thaw the port twice in ata_eh_reset()
by Xingui Yang 18 Sep '23

18 Sep '23

Clear port pending interrupts before reset, as per AHCI specifications (Szuying). Followup fixes for this one are to not clear ATA_PFLAG_EH_PENDING in ata_eh_reset() to allow EH to continue on with other actions recorded with error interrupts triggered before EH completes. A~Nd an additional fix to avoid thawing a port twice in EH (Niklas). Niklas Cassel (2): ata: libata-eh: do not clear ATA_PFLAG_EH_PENDING in ata_eh_reset() ata: libata-eh: do not thaw the port twice in ata_eh_reset() drivers/ata/libata-eh.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) -- 2.17.1

2 3

[PATCH OLK-5.10 0/2] Not clear ATA_PFLAG_EH_PENDING and not thaw the port twice in ata_eh_reset()
by Xingui Yang 18 Sep '23

18 Sep '23

Clear port pending interrupts before reset, as per AHCI specifications (Szuying). Followup fixes for this one are to not clear ATA_PFLAG_EH_PENDING in ata_eh_reset() to allow EH to continue on with other actions recorded with error interrupts triggered before EH completes. A~Nd an additional fix to avoid thawing a port twice in EH (Niklas). Niklas Cassel (2): ata: libata-eh: do not clear ATA_PFLAG_EH_PENDING in ata_eh_reset() ata: libata-eh: do not thaw the port twice in ata_eh_reset() drivers/ata/libata-eh.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) -- 2.17.1

2 3

[PATCH openEuler-1.0-LTS v1 0/3] Fix booting failure on arm64
by Wei Li 18 Sep '23

18 Sep '23

The arm64 test machine boot failed when using hulk_defconfig after d63c76835476 ("arm64: efi: Execute runtime services from a dedicated stack"), revert it first for weekly release. Wei Li (3): Revert "arm64: efi: Make efi_rt_lock a raw_spinlock" Revert "arm64: efi: Recover from synchronous exceptions occurring in firmware" Revert "arm64: efi: Execute runtime services from a dedicated stack" arch/arm64/include/asm/efi.h | 12 ------ arch/arm64/kernel/efi-rt-wrapper.S | 39 ++----------------- arch/arm64/kernel/efi.c | 50 ------------------------- arch/arm64/mm/fault.c | 4 -- drivers/firmware/efi/runtime-wrappers.c | 1 - 5 files changed, 3 insertions(+), 103 deletions(-) -- 2.25.1

2 4

[PATCH OLK-5.10] jbd2: Fix potential data lost in recovering journal raced with synchronizing fs bdev
by Zhihao Cheng 18 Sep '23

18 Sep '23

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I828EV CVE: NA Reference: https://lore.kernel.org/linux-ext4/20230911155822.kbg2xayc7ys24kay@quack3/T… -------------------------------- JBD2 makes sure journal data is fallen on fs device by sync_blockdev(), however, other process could intercept the EIO information from bdev's mapping, which leads journal recovering successful even EIO occurs during data written back to fs device. We found this problem in our product, iscsi + multipath is chosen for block device of ext4. Unstable network may trigger kpartx to rescan partitions in device mapper layer. Detailed process is shown as following: mount kpartx irq jbd2_journal_recover do_one_pass memcpy(nbh->b_data, obh->b_data) // copy data to fs dev from journal mark_buffer_dirty // mark bh dirty vfs_read generic_file_read_iter // dio filemap_write_and_wait_range __filemap_fdatawrite_range do_writepages block_write_full_folio submit_bh_wbc >> EIO occurs in disk << end_buffer_async_write mark_buffer_write_io_error mapping_set_error set_bit(AS_EIO, &mapping->flags) // set! filemap_check_errors test_and_clear_bit(AS_EIO, &mapping->flags) // clear! err2 = sync_blockdev filemap_write_and_wait filemap_check_errors test_and_clear_bit(AS_EIO, &mapping->flags) // false err2 = 0 Filesystem is mounted successfully even data from journal is failed written into disk, and ext4/ocfs2 could become corrupted. Fix it by comparing the wb_err state in fs block device before recovering and after recovering. Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217888 Cc: stable(a)vger.kernel.org Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> --- fs/jbd2/recovery.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 9e4537349380..361c37ef1f8a 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -292,6 +292,8 @@ int jbd2_journal_recover(journal_t *journal) journal_superblock_t * sb; struct recovery_info info; + errseq_t wb_err; + struct address_space *mapping; memset(&info, 0, sizeof(info)); sb = journal->j_superblock; @@ -309,6 +311,8 @@ int jbd2_journal_recover(journal_t *journal) return 0; } + mapping = journal->j_fs_dev->bd_inode->i_mapping; + errseq_check_and_advance(&mapping->wb_err, &wb_err); err = do_one_pass(journal, &info, PASS_SCAN); if (!err) err = do_one_pass(journal, &info, PASS_REVOKE); @@ -327,6 +331,9 @@ int jbd2_journal_recover(journal_t *journal) jbd2_journal_clear_revoke(journal); err2 = sync_blockdev(journal->j_fs_dev); + if (!err) + err = err2; + err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err); if (!err) err = err2; /* Make sure all replayed data is on permanent storage */ -- 2.31.1

2 1

[PATCH v2 openEuler-23.09] ima: fix parser strategy unable to manually import kernel
by Zhou Shuiqing 18 Sep '23

18 Sep '23

euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I822F4 CVE: NA ------------------------------------------------- This patch is to fix parser strategy unable to manually import kernel v2: -fix code indentation Signed-off-by: Zhou Shuiqing <zhoushuiqing2(a)huawei.com> Reviewed-by: Huaxin Lu <luhuaxin1(a)huawei.com> --- security/integrity/ima/ima_policy.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 81a727a3f..80bf1dc80 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1376,7 +1376,7 @@ static bool ima_validate_rule(struct ima_rule_entry *entry) entry->flags & (IMA_DIGSIG_REQUIRED | IMA_MODSIG_ALLOWED | #ifdef CONFIG_IMA_DIGEST_LIST IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS | - IMA_META_IMMUTABLE_REQUIRED | IMA_PARSER)) + IMA_META_IMMUTABLE_REQUIRED)) #else IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS)) #endif @@ -1416,7 +1416,8 @@ static bool ima_validate_rule(struct ima_rule_entry *entry) IMA_FGROUP | IMA_DIGSIG_REQUIRED | IMA_PERMIT_DIRECTIO | IMA_VALIDATE_ALGOS | #ifdef CONFIG_IMA_DIGEST_LIST - IMA_VERITY_REQUIRED | IMA_META_IMMUTABLE_REQUIRED)) + IMA_VERITY_REQUIRED | + IMA_META_IMMUTABLE_REQUIRED | IMA_PARSER)) #else IMA_VERITY_REQUIRED)) #endif -- 2.33.0

2 1

[PATCH openEuler-23.09] ima: modify the CONFIG configuration of x86_64
by Zhou Shuiqing 18 Sep '23

18 Sep '23

euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8264X CVE: NA ------------------------------------------------- This patch is to modify the CONFIG configuration of x86_64. Signed-off-by: Zhou Shuiqing <zhoushuiqing2(a)huawei.com> --- arch/x86/configs/openeuler_defconfig | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 5f4d70de3..5bdd03c9f 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -4368,18 +4368,18 @@ CONFIG_TCG_TIS_SPI=y # CONFIG_TCG_TIS_SPI_CR50 is not set CONFIG_TCG_TIS_I2C=m CONFIG_TCG_TIS_I2C_CR50=m -CONFIG_TCG_TIS_I2C_ATMEL=y -CONFIG_TCG_TIS_I2C_INFINEON=y -CONFIG_TCG_TIS_I2C_NUVOTON=y -CONFIG_TCG_NSC=y -CONFIG_TCG_ATMEL=y -CONFIG_TCG_INFINEON=y +CONFIG_TCG_TIS_I2C_ATMEL=m +CONFIG_TCG_TIS_I2C_INFINEON=m +CONFIG_TCG_TIS_I2C_NUVOTON=m +CONFIG_TCG_NSC=m +CONFIG_TCG_ATMEL=m +CONFIG_TCG_INFINEON=m CONFIG_TCG_XEN=m CONFIG_TCG_CRB=y CONFIG_TCG_VTPM_PROXY=m -CONFIG_TCG_TIS_ST33ZP24=y -CONFIG_TCG_TIS_ST33ZP24_I2C=y -CONFIG_TCG_TIS_ST33ZP24_SPI=y +CONFIG_TCG_TIS_ST33ZP24=m +CONFIG_TCG_TIS_ST33ZP24_I2C=m +CONFIG_TCG_TIS_ST33ZP24_SPI=m CONFIG_TELCLOCK=m CONFIG_XILLYBUS_CLASS=m CONFIG_XILLYBUS=m -- 2.33.0

2 1

[PATCH openEuler-23.09] ima: modify the CONFIG configuration of x86_64
by Zhou Shuiqing 18 Sep '23

18 Sep '23

euleros inclusion category: bugfix bugzilla:https://gitee.com/openeuler/kernel/issues/I8264X CVE: NA ------------------------------------------------- This patch is to modify the CONFIG configuration of x86_64. Signed-off-by: Zhou Shuiqing <zhoushuiqing2(a)huawei.com> --- arch/x86/configs/openeuler_defconfig | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 5f4d70de3..5bdd03c9f 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -4368,18 +4368,18 @@ CONFIG_TCG_TIS_SPI=y # CONFIG_TCG_TIS_SPI_CR50 is not set CONFIG_TCG_TIS_I2C=m CONFIG_TCG_TIS_I2C_CR50=m -CONFIG_TCG_TIS_I2C_ATMEL=y -CONFIG_TCG_TIS_I2C_INFINEON=y -CONFIG_TCG_TIS_I2C_NUVOTON=y -CONFIG_TCG_NSC=y -CONFIG_TCG_ATMEL=y -CONFIG_TCG_INFINEON=y +CONFIG_TCG_TIS_I2C_ATMEL=m +CONFIG_TCG_TIS_I2C_INFINEON=m +CONFIG_TCG_TIS_I2C_NUVOTON=m +CONFIG_TCG_NSC=m +CONFIG_TCG_ATMEL=m +CONFIG_TCG_INFINEON=m CONFIG_TCG_XEN=m CONFIG_TCG_CRB=y CONFIG_TCG_VTPM_PROXY=m -CONFIG_TCG_TIS_ST33ZP24=y -CONFIG_TCG_TIS_ST33ZP24_I2C=y -CONFIG_TCG_TIS_ST33ZP24_SPI=y +CONFIG_TCG_TIS_ST33ZP24=m +CONFIG_TCG_TIS_ST33ZP24_I2C=m +CONFIG_TCG_TIS_ST33ZP24_SPI=m CONFIG_TELCLOCK=m CONFIG_XILLYBUS_CLASS=m CONFIG_XILLYBUS=m -- 2.33.0

2 1

[PATCH openEuler-23.09] livepatch: Enable livepatch configs in openeuler_defconfig
by Zheng Yejian 18 Sep '23

18 Sep '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I826DM CVE: NA -------------------------------- Enable the same livepatch configures for x86_64 and arm64 as that in openEuler-22.03-LTS. Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 12 ++++++++++++ arch/x86/configs/openeuler_defconfig | 9 +++++++++ 2 files changed, 21 insertions(+) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 6c6cd4701f92..7e95287b4716 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -332,6 +332,18 @@ CONFIG_ARCH_XGENE=y # CONFIG_ARCH_ZYNQMP is not set # end of Platform selection +CONFIG_HAVE_LIVEPATCH_WO_FTRACE=y + +# +# Enable Livepatch +# +CONFIG_LIVEPATCH=y +CONFIG_LIVEPATCH_WO_FTRACE=y +CONFIG_LIVEPATCH_STOP_MACHINE_CONSISTENCY=y +# CONFIG_LIVEPATCH_STACK is not set +CONFIG_LIVEPATCH_RESTRICT_KPROBE=y +# end of Enable Livepatch + # # Kernel Features # diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 5f4d70de32f9..0f30eb56c31b 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -502,8 +502,17 @@ CONFIG_LEGACY_VSYSCALL_XONLY=y CONFIG_MODIFY_LDT_SYSCALL=y # CONFIG_STRICT_SIGALTSTACK_SIZE is not set CONFIG_HAVE_LIVEPATCH_WO_FTRACE=y + +# +# Enable Livepatch +# CONFIG_LIVEPATCH=y +# CONFIG_LIVEPATCH_FTRACE is not set CONFIG_LIVEPATCH_WO_FTRACE=y +CONFIG_LIVEPATCH_STOP_MACHINE_CONSISTENCY=y +# CONFIG_LIVEPATCH_STACK is not set +CONFIG_LIVEPATCH_RESTRICT_KPROBE=y +# end of Enable Livepatch # end of Processor type and features CONFIG_FUNCTION_PADDING_CFI=11 -- 2.25.1

2 1

[PATCH OLK-5.10] zram: correctly handle all next_arg() cases
by Jinjiang Tu 18 Sep '23

18 Sep '23

From: Sergey Senozhatsky <senozhatsky(a)chromium.org> mainline inclusion from mainline-v6.3-rc1 commit df32de1433412621b92daf1b3369ac053214031e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I822Z8 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------------------- When supplied buffer does not have assignment sign next_arg() sets `val` pointer to NULL, so we cannot dereference it. Add a NULL pointer test to handle `param` case, in addition to `*val` test, which handles cases when param has no value assigned to it: `param=`. Link: https://lkml.kernel.org/r/20230103030119.1496358-1-senozhatsky@chromium.org Signed-off-by: Sergey Senozhatsky <senozhatsky(a)chromium.org> Cc: Minchan Kim <minchan(a)kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- drivers/block/zram/zram_drv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e332b4d55359..955f0c4d358f 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1123,7 +1123,7 @@ static ssize_t recomp_algorithm_store(struct device *dev, while (*args) { args = next_arg(args, &param, &val); - if (!*val) + if (!val || !*val) return -EINVAL; if (!strcmp(param, "algo")) { @@ -1800,7 +1800,7 @@ static ssize_t recompress_store(struct device *dev, while (*args) { args = next_arg(args, &param, &val); - if (!*val) + if (!val || !*val) return -EINVAL; if (!strcmp(param, "type")) { -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS] nvme-pci: fix mempool alloc size
by Yong Hu 18 Sep '23

18 Sep '23

From: Keith Busch <kbusch(a)kernel.org> stable inclusion from stable-v5.10.163 commit dfb6d54893d544151e7f480bc44cfe7823f5ad23 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7PZZC Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit c89a529e823d51dd23c7ec0c047c7a454a428541 ] Convert the max size to bytes to match the units of the divisor that calculates the worst-case number of PRP entries. The result is used to determine how many PRP Lists are required. The code was previously rounding this to 1 list, but we can require 2 in the worst case. In that scenario, the driver would corrupt memory beyond the size provided by the mempool. While unlikely to occur (you'd need a 4MB in exactly 127 phys segments on a queue that doesn't support SGLs), this memory corruption has been observed by kfence. Cc: Jens Axboe <axboe(a)kernel.dk> Fixes: 943e942e6266f ("nvme-pci: limit max IO size and segments to avoid high order allocations") Signed-off-by: Keith Busch <kbusch(a)kernel.org> Reviewed-by: Jens Axboe <axboe(a)kernel.dk> Reviewed-by: Kanchan Joshi <joshi.k(a)samsung.com> Reviewed-by: Chaitanya Kulkarni <kch(a)nvidia.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yong Hu <yong.hu(a)windriver.com> --- drivers/nvme/host/pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index bbf6ce4b82ac..e805a9813628 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -371,8 +371,8 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, */ static int nvme_pci_npages_prp(void) { - unsigned nprps = DIV_ROUND_UP(NVME_MAX_KB_SZ + NVME_CTRL_PAGE_SIZE, - NVME_CTRL_PAGE_SIZE); + unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; + unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8); } -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP2] nvme-pci: fix timeout request state check
by Yong Hu 18 Sep '23

18 Sep '23

From: Keith Busch <kbusch(a)kernel.org> stable inclusion from stable-v5.10.166 commit 5f10f7efe0fc97c0ee2112a1032914f6fb2f940c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7R4BC CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 1c5842085851f786eba24a39ecd02650ad892064 ] Polling the completion can progress the request state to IDLE, either inline with the completion, or through softirq. Either way, the state may not be COMPLETED, so don't check for that. We only care if the state isn't IN_FLIGHT. This is fixing an issue where the driver aborts an IO that we just completed. Seeing the "aborting" message instead of "polled" is very misleading as to where the timeout problem resides. Fixes: bf392a5dc02a9b ("nvme-pci: Remove tag from process cq") Signed-off-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yong Hu <yong.hu(a)windriver.com> --- drivers/nvme/host/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ac5745d8dd2b..f1ac50c7a1d6 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1292,7 +1292,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) else nvme_poll_irqdisable(nvmeq); - if (blk_mq_request_completed(req)) { + if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) { dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, completion polled\n", req->tag, nvmeq->qid); -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS] nvme-pci: fix timeout request state check
by Yong Hu 18 Sep '23

18 Sep '23

From: Keith Busch <kbusch(a)kernel.org> stable inclusion from stable-v5.10.166 commit 5f10f7efe0fc97c0ee2112a1032914f6fb2f940c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7R4BC CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 1c5842085851f786eba24a39ecd02650ad892064 ] Polling the completion can progress the request state to IDLE, either inline with the completion, or through softirq. Either way, the state may not be COMPLETED, so don't check for that. We only care if the state isn't IN_FLIGHT. This is fixing an issue where the driver aborts an IO that we just completed. Seeing the "aborting" message instead of "polled" is very misleading as to where the timeout problem resides. Fixes: bf392a5dc02a9b ("nvme-pci: Remove tag from process cq") Signed-off-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yong Hu <yong.hu(a)windriver.com> --- drivers/nvme/host/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fbbbfdea076a..bbf6ce4b82ac 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1291,7 +1291,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) else nvme_poll_irqdisable(nvmeq); - if (blk_mq_request_completed(req)) { + if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) { dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, completion polled\n", req->tag, nvmeq->qid); -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] netfilter: nftables: exthdr: fix 4-byte stack OOB write
by Guo Mengqi 18 Sep '23

18 Sep '23

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v6.6-rc1 commit fd94d9dadee58e09b49075240fe83423eb1dcd36 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I80I0G CVE: CVE-2023-4881 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- If priv->len is a multiple of 4, then dst[len / 4] can write past the destination array which leads to stack corruption. This construct is necessary to clean the remainder of the register in case ->len is NOT a multiple of the register size, so make it conditional just like nft_payload.c does. The bug was added in 4.1 cycle and then copied/inherited when tcp/sctp and ip option support was added. Bug reported by Zero Day Initiative project (ZDI-CAN-21950, ZDI-CAN-21951, ZDI-CAN-21961). Fixes: 49499c3e6e18 ("netfilter: nf_tables: switch registers to 32 bit addressing") Fixes: 935b7f643018 ("netfilter: nft_exthdr: add TCP option matching") Fixes: 133dc203d77d ("netfilter: nft_exthdr: Support SCTP chunks") Fixes: dbb5281a1f84 ("netfilter: nf_tables: add support for matching IPv4 options") Signed-off-by: Florian Westphal <fw(a)strlen.de> Conflicts: net/netfilter/nft_exthdr.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/netfilter/nft_exthdr.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 670dd146fb2b..ca268293cfa1 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -33,6 +33,14 @@ static unsigned int optlen(const u8 *opt, unsigned int offset) return opt[offset + 1]; } +static int nft_skb_copy_to_reg(const struct sk_buff *skb, int offset, u32 *dest, unsigned int len) +{ + if (len % NFT_REG32_SIZE) + dest[len / NFT_REG32_SIZE] = 0; + + return skb_copy_bits(skb, offset, dest, len); +} + static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -54,8 +62,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, } offset += priv->offset; - dest[priv->len / NFT_REG32_SIZE] = 0; - if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0) + if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0) goto err; return; err: @@ -151,8 +158,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr, } offset += priv->offset; - dest[priv->len / NFT_REG32_SIZE] = 0; - if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0) + if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0) goto err; return; err: @@ -208,7 +214,8 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr, if (priv->flags & NFT_EXTHDR_F_PRESENT) { *dest = 1; } else { - dest[priv->len / NFT_REG32_SIZE] = 0; + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; memcpy(dest, opt + offset, priv->len); } -- 2.17.1

2 1

[PATCH openEuler-23.09] ima: fix parser strategy unable to manually import kernel
by Zhou Shuiqing 18 Sep '23

18 Sep '23

From: zhoushuiqing <zhoushuiqing2(a)huawei.com> euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I822F4 CVE: NA ------------------------------------------------- This patch is to fix parser strategy unable to manually import kernel Signed-off-by: Zhou Shuiqing <zhoushuiqing2(a)huawei.com> Reviewed-by: Huaxin Lu <luhuaxin1(a)huawei.com> --- security/integrity/ima/ima_policy.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 81a727a3f..ca87605e5 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1376,7 +1376,7 @@ static bool ima_validate_rule(struct ima_rule_entry *entry) entry->flags & (IMA_DIGSIG_REQUIRED | IMA_MODSIG_ALLOWED | #ifdef CONFIG_IMA_DIGEST_LIST IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS | - IMA_META_IMMUTABLE_REQUIRED | IMA_PARSER)) + IMA_META_IMMUTABLE_REQUIRED)) #else IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS)) #endif @@ -1416,7 +1416,8 @@ static bool ima_validate_rule(struct ima_rule_entry *entry) IMA_FGROUP | IMA_DIGSIG_REQUIRED | IMA_PERMIT_DIRECTIO | IMA_VALIDATE_ALGOS | #ifdef CONFIG_IMA_DIGEST_LIST - IMA_VERITY_REQUIRED | IMA_META_IMMUTABLE_REQUIRED)) + IMA_VERITY_REQUIRED | + IMA_META_IMMUTABLE_REQUIRED | IMA_PARSER)) #else IMA_VERITY_REQUIRED)) #endif -- 2.33.0

2 1

[PATCH OLK-5.10] livepatch/core: Fix possible issue that old function is not checked
by Zheng Yejian 18 Sep '23

18 Sep '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZH67 CVE: NA -------------------------------- After patch being enabled, the first few instructions would be modified to jump to the new function, then callers of old function would jump to new function but always through the old function. Therefore when enabling a new patch or disable a patch on the old function, we should always consider that old function is running. Otherwise, there may be situations where old functions are being modified before jumping to new function and cause issues. Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> --- arch/arm/kernel/livepatch.c | 24 +++++++++++++++++++++--- arch/arm64/kernel/livepatch.c | 24 +++++++++++++++++++++--- arch/powerpc/kernel/livepatch_32.c | 24 +++++++++++++++++++++--- arch/x86/kernel/livepatch.c | 25 +++++++++++++++++++++---- 4 files changed, 84 insertions(+), 13 deletions(-) diff --git a/arch/arm/kernel/livepatch.c b/arch/arm/kernel/livepatch.c index b4d26474ba33..b1711d947dfe 100644 --- a/arch/arm/kernel/livepatch.c +++ b/arch/arm/kernel/livepatch.c @@ -134,12 +134,17 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, struct klp_object *obj; struct klp_func_node *func_node; struct klp_func *func; - unsigned long func_addr, func_size; + unsigned long func_addr = 0; + unsigned long func_size; struct klp_func_list *pcheck = NULL; for (obj = patch->objs; obj->funcs; obj++) { for (func = obj->funcs; func->old_name; func++) { + unsigned long old_func = (unsigned long)func->old_func; + if (enable) { + bool need_check_old = false; + if (func->patched || func->force == KLP_ENFORCEMENT) continue; /* @@ -153,7 +158,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, * No patched on this function * [ the origin one ] */ - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { /* @@ -184,6 +189,13 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func->old_name, func->force); if (ret) return ret; + need_check_old = (func_addr != old_func); + } + if (need_check_old) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, func->force); + if (ret) + return ret; } } else { /* @@ -203,7 +215,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, * the stack. */ if (list_is_singular(&func_node->func_stack)) { - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { struct klp_func *prev; @@ -219,6 +231,12 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func->old_name, 0); if (ret) return ret; + if (func_addr != old_func) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, 0); + if (ret) + return ret; + } #endif func_addr = (unsigned long)func->new_func; func_size = func->new_size; diff --git a/arch/arm64/kernel/livepatch.c b/arch/arm64/kernel/livepatch.c index 6b5bcb491125..5b0171254820 100644 --- a/arch/arm64/kernel/livepatch.c +++ b/arch/arm64/kernel/livepatch.c @@ -126,13 +126,18 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, int ret; struct klp_object *obj; struct klp_func *func; - unsigned long func_addr, func_size; + unsigned long func_addr = 0; + unsigned long func_size; struct klp_func_node *func_node; struct klp_func_list *pcheck = NULL; for (obj = patch->objs; obj->funcs; obj++) { for (func = obj->funcs; func->old_name; func++) { + unsigned long old_func = (unsigned long)func->old_func; + if (enable) { + bool need_check_old = false; + if (func->patched || func->force == KLP_ENFORCEMENT) continue; /* @@ -142,7 +147,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func_node = klp_find_func_node(func->old_func); if (!func_node || list_empty(&func_node->func_stack)) { - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { /* @@ -173,6 +178,13 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func->old_name, func->force); if (ret) return ret; + need_check_old = (func_addr != old_func); + } + if (need_check_old) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, func->force); + if (ret) + return ret; } } else { /* @@ -193,7 +205,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, * the stack. */ if (list_is_singular(&func_node->func_stack)) { - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { struct klp_func *prev; @@ -209,6 +221,12 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func->old_name, 0); if (ret) return ret; + if (func_addr != old_func) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, 0); + if (ret) + return ret; + } #endif func_addr = (unsigned long)func->new_func; diff --git a/arch/powerpc/kernel/livepatch_32.c b/arch/powerpc/kernel/livepatch_32.c index 7b4ed23bf2ca..3fe4f3c5790b 100644 --- a/arch/powerpc/kernel/livepatch_32.c +++ b/arch/powerpc/kernel/livepatch_32.c @@ -123,13 +123,18 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, int ret; struct klp_object *obj; struct klp_func *func; - unsigned long func_addr, func_size; + unsigned long func_addr = 0; + unsigned long func_size; struct klp_func_node *func_node; struct klp_func_list *pcheck = NULL; for (obj = patch->objs; obj->funcs; obj++) { for (func = obj->funcs; func->old_name; func++) { + unsigned long old_func = (unsigned long)func->old_func; + if (enable) { + bool need_check_old = false; + if (func->patched || func->force == KLP_ENFORCEMENT) continue; /* @@ -143,7 +148,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, * No patched on this function * [ the origin one ] */ - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { /* @@ -174,6 +179,13 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func->old_name, func->force); if (ret) return ret; + need_check_old = (func_addr != old_func); + } + if (need_check_old) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, func->force); + if (ret) + return ret; } } else { /* @@ -193,7 +205,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, * the stack. */ if (list_is_singular(&func_node->func_stack)) { - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { struct klp_func *prev; @@ -208,6 +220,12 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func_size, func->old_name, 0); if (ret) return ret; + if (func_addr != old_func) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, 0); + if (ret) + return ret; + } #endif func_addr = (unsigned long)func->new_func; func_size = func->new_size; diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c index 0241e560bd2e..43404fc1fdbb 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -120,16 +120,20 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, int ret; struct klp_object *obj; struct klp_func *func; - unsigned long func_addr, func_size; + unsigned long func_addr = 0; + unsigned long func_size; struct klp_func_node *func_node = NULL; struct klp_func_list *pcheck = NULL; for (obj = patch->objs; obj->funcs; obj++) { for (func = obj->funcs; func->old_name; func++) { - func_node = klp_find_func_node(func->old_func); + unsigned long old_func = (unsigned long)func->old_func; + func_node = klp_find_func_node(func->old_func); /* Check func address in stack */ if (enable) { + bool need_check_old = false; + if (func->patched || func->force == KLP_ENFORCEMENT) continue; /* @@ -138,7 +142,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, */ if (!func_node || list_empty(&func_node->func_stack)) { - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { /* @@ -169,6 +173,13 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func->old_name, func->force); if (ret) return ret; + need_check_old = (func_addr != old_func); + } + if (need_check_old) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, func->force); + if (ret) + return ret; } } else { /* @@ -186,7 +197,7 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, * the stack. */ if (list_is_singular(&func_node->func_stack)) { - func_addr = (unsigned long)func->old_func; + func_addr = old_func; func_size = func->old_size; } else { struct klp_func *prev; @@ -201,6 +212,12 @@ static int klp_check_activeness_func(struct klp_patch *patch, int enable, func_size, func->old_name, 0); if (ret) return ret; + if (func_addr != old_func) { + ret = add_func_to_list(check_funcs, &pcheck, old_func, + func->old_size, func->old_name, 0); + if (ret) + return ret; + } #endif func_addr = (unsigned long)func->new_func; -- 2.25.1

2 1

[PATCH openEuler-23.09] mm: gmem: Use find_vma_intersection to find overlap vma
by Wupeng Ma 18 Sep '23

18 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7WLVX --------------------------------------------- Use find_vma_intersection instead of find_vma to find overlapping vma. Fixes: 848492f233ce ("mm: gmem: Introduce vm_object for gmem") Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- mm/mmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mmap.c b/mm/mmap.c index eb24efdba25d..2aef07b8a85e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2701,7 +2701,7 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, struct vm_area_struct *vma; if (gmem_is_enabled()) { - vma = find_vma(mm, start); + vma = find_vma_intersection(mm, start, start + len); if (!vma) return 0; if (vma_is_peer_shared(vma)) { -- 2.25.1

2 1

[PATCH openEuler-23.09] ima: fix the PGP certificate failure to load into the kernel
by Zhou Shuiqing 15 Sep '23

15 Sep '23

euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I81RYU CVE: NA ------------------------------------------------- This patch is to fix the PGP certificate failure to load into the kernel, PGP certificates are used to verify the IMA digest list. Signed-off-by: Zhou Shuiqing <zhoushuiqing2(a)huawei.com> --- certs/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/certs/Makefile b/certs/Makefile index ab6da6f4e..49f8101cc 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -67,7 +67,7 @@ $(obj)/system_certificates.o: $(obj)/signing_key.x509 ifdef CONFIG_PGP_PRELOAD_PUBLIC_KEYS ifeq ($(shell ls $(srctree)/certs/pubring.gpg 2> /dev/null), $(srctree)/certs/pubring.gpg) -system_certificates.o += -DHAVE_PUBRING_GPG +AFLAGS_system_certificates.o += -DHAVE_PUBRING_GPG $(obj)/system_certificates.o: $(srctree)/certs/pubring.gpg endif endif -- 2.33.0

2 1

[PATCH openEuler-23.09] ima: fix the PGP certificate failure to load into the kernel
by Zhou Shuiqing 15 Sep '23

15 Sep '23

euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I81RYU CVE: NA ------------------------------------------------- This patch is to fix the PGP certificate failure to load into the kernel, PGP certificates are used to verify the IMA digest list. Signed-off-by: Zhou Shuiqing <zhoushuiqing2(a)huawei.com> --- certs/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/certs/Makefile b/certs/Makefile index ab6da6f4e..49f8101cc 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -67,7 +67,7 @@ $(obj)/system_certificates.o: $(obj)/signing_key.x509 ifdef CONFIG_PGP_PRELOAD_PUBLIC_KEYS ifeq ($(shell ls $(srctree)/certs/pubring.gpg 2> /dev/null), $(srctree)/certs/pubring.gpg) -system_certificates.o += -DHAVE_PUBRING_GPG +AFLAGS_system_certificates.o += -DHAVE_PUBRING_GPG $(obj)/system_certificates.o: $(srctree)/certs/pubring.gpg endif endif -- 2.33.0

2 1

[PATCH openEuler-1.0-LTS] sched/qos: Fix warning in CPU hotplug scenarios
by Xia Fukun 15 Sep '23

15 Sep '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7ZMCB CVE: NA -------------------------------- CPU hotplug callbacks race against distribute_cfs_runtime(), when the QOS_SCHED feature is enabled, there may be situations where the cfs_rq-> runtime_remaining == 1 and cfs_rq is QOS_THROTTLED. Turn off the Qos_throttle when the CPU is offline. No longer allocate time to cfs_rq in this scenario to fix the warning. Fixes: fbea24f5894e ("sched/qos: Don't unthrottle cfs_rq when cfs_rq is throttled by qos") Signed-off-by: Xia Fukun <xiafukun(a)huawei.com> --- kernel/sched/fair.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e9afb1e6ca4c..1c78e2f29901 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4783,6 +4783,19 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) if (!cfs_rq_throttled(cfs_rq)) goto next; + /* + * CPU hotplug callbacks race against distribute_cfs_runtime() + * when the QOS_SCHED feature is enabled, there may be + * situations where the runtime_remaining > 0. + * Qos_sched does not care whether the cfs_rq has time left, + * so no longer allocate time to cfs_rq in this scenario. + */ +#ifdef CONFIG_QOS_SCHED + if (cfs_rq->throttled == QOS_THROTTLED && + cfs_rq->runtime_remaining > 0) + goto next; +#endif + /* By the above check, this should never be true */ SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); @@ -7754,6 +7767,10 @@ static bool check_qos_cfs_rq(struct cfs_rq *cfs_rq) if (unlikely(cfs_rq && cfs_rq->tg->qos_level < 0 && !sched_idle_cpu(smp_processor_id()) && cfs_rq->h_nr_running == cfs_rq->idle_h_nr_running)) { + + if (!rq_of(cfs_rq)->online) + return false; + throttle_qos_cfs_rq(cfs_rq); return true; } -- 2.34.1

2 1

[PATCH OLK-5.10] ata: libahci: clear pending interrupt status
by Xingui Yang 15 Sep '23

15 Sep '23

From: Szuying Chen <chensiying21(a)gmail.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I81M63 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata.git/commit/?… ------------------------------------------------------------ When a CRC error occurs, the HBA asserts an interrupt to indicate an interface fatal error (PxIS.IFS). The ISR clears PxIE and PxIS, then does error recovery. If the adapter receives another SDB FIS with an error (PxIS.TFES) from the device before the start of the EH recovery process, the interrupt signaling the new SDB cannot be serviced as PxIE was cleared already. This in turn results in the HBA inability to issue any command during the error recovery process after setting PxCMD.ST to 1 because PxIS.TFES is still set. According to AHCI 1.3.1 specifications section 6.2.2, fatal errors notified by setting PxIS.HBFS, PxIS.HBDS, PxIS.IFS or PxIS.TFES will cause the HBA to enter the ERR:Fatal state. In this state, the HBA shall not issue any new commands. To avoid this situation, introduce the function ahci_port_clear_pending_irq() to clear pending interrupts before executing a COMRESET. This follows the AHCI 1.3.1 - section 6.2.2.2 specification. Signed-off-by: Szuying Chen <Chloe_Chen(a)asmedia.com.tw> Fixes: e0bfd149973d ("[PATCH] ahci: stop engine during hard reset") Cc: stable(a)vger.kernel.org Reviewed-by: Niklas Cassel <niklas.cassel(a)wdc.com> Signed-off-by: Damien Le Moal <dlemoal(a)kernel.org> Signed-off-by: Xingui Yang <yangxingui(a)huawei.com> --- drivers/ata/libahci.c | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 4514f3f28..160400a2a 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1205,6 +1205,26 @@ static ssize_t ahci_activity_show(struct ata_device *dev, char *buf) return sprintf(buf, "%d\n", emp->blink_policy); } +static void ahci_port_clear_pending_irq(struct ata_port *ap) +{ + struct ahci_host_priv *hpriv = ap->host->private_data; + void __iomem *port_mmio = ahci_port_base(ap); + u32 tmp; + + /* clear SError */ + tmp = readl(port_mmio + PORT_SCR_ERR); + dev_dbg(ap->host->dev, "PORT_SCR_ERR 0x%x\n", tmp); + writel(tmp, port_mmio + PORT_SCR_ERR); + + /* clear port IRQ */ + tmp = readl(port_mmio + PORT_IRQ_STAT); + dev_dbg(ap->host->dev, "PORT_IRQ_STAT 0x%x\n", tmp); + if (tmp) + writel(tmp, port_mmio + PORT_IRQ_STAT); + + writel(1 << ap->port_no, hpriv->mmio + HOST_IRQ_STAT); +} + static void ahci_port_init(struct device *dev, struct ata_port *ap, int port_no, void __iomem *mmio, void __iomem *port_mmio) @@ -1219,18 +1239,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, if (rc) dev_warn(dev, "%s (%d)\n", emsg, rc); - /* clear SError */ - tmp = readl(port_mmio + PORT_SCR_ERR); - VPRINTK("PORT_SCR_ERR 0x%x\n", tmp); - writel(tmp, port_mmio + PORT_SCR_ERR); - - /* clear port IRQ */ - tmp = readl(port_mmio + PORT_IRQ_STAT); - VPRINTK("PORT_IRQ_STAT 0x%x\n", tmp); - if (tmp) - writel(tmp, port_mmio + PORT_IRQ_STAT); - - writel(1 << port_no, mmio + HOST_IRQ_STAT); + ahci_port_clear_pending_irq(ap); /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); @@ -1560,6 +1569,8 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class, tf.command = ATA_BUSY; ata_tf_to_fis(&tf, 0, 0, d2h_fis); + ahci_port_clear_pending_irq(ap); + rc = sata_link_hardreset(link, timing, deadline, online, ahci_check_ready); -- 2.17.1

2 1

[PATCH OLK-5.10] net: sched: sch_qfq: Fix UAF in qfq_dequeue()
by Liu Jian 15 Sep '23

15 Sep '23

From: valis <sec(a)valis.email> mainline inclusion from mainline-v6.6-rc1 commit 8fc134fee27f2263988ae38920bc03da416b03d8 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I80USB CVE: CVE-2023-4921 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- When the plug qdisc is used as a class of the qfq qdisc it could trigger a UAF. This issue can be reproduced with following commands: tc qdisc add dev lo root handle 1: qfq tc class add dev lo parent 1: classid 1:1 qfq weight 1 maxpkt 512 tc qdisc add dev lo parent 1:1 handle 2: plug tc filter add dev lo parent 1: basic classid 1:1 ping -c1 127.0.0.1 and boom: [ 285.353793] BUG: KASAN: slab-use-after-free in qfq_dequeue+0xa7/0x7f0 [ 285.354910] Read of size 4 at addr ffff8880bad312a8 by task ping/144 [ 285.355903] [ 285.356165] CPU: 1 PID: 144 Comm: ping Not tainted 6.5.0-rc3+ #4 [ 285.357112] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 [ 285.358376] Call Trace: [ 285.358773] <IRQ> [ 285.359109] dump_stack_lvl+0x44/0x60 [ 285.359708] print_address_description.constprop.0+0x2c/0x3c0 [ 285.360611] kasan_report+0x10c/0x120 [ 285.361195] ? qfq_dequeue+0xa7/0x7f0 [ 285.361780] qfq_dequeue+0xa7/0x7f0 [ 285.362342] __qdisc_run+0xf1/0x970 [ 285.362903] net_tx_action+0x28e/0x460 [ 285.363502] __do_softirq+0x11b/0x3de [ 285.364097] do_softirq.part.0+0x72/0x90 [ 285.364721] </IRQ> [ 285.365072] <TASK> [ 285.365422] __local_bh_enable_ip+0x77/0x90 [ 285.366079] __dev_queue_xmit+0x95f/0x1550 [ 285.366732] ? __pfx_csum_and_copy_from_iter+0x10/0x10 [ 285.367526] ? __pfx___dev_queue_xmit+0x10/0x10 [ 285.368259] ? __build_skb_around+0x129/0x190 [ 285.368960] ? ip_generic_getfrag+0x12c/0x170 [ 285.369653] ? __pfx_ip_generic_getfrag+0x10/0x10 [ 285.370390] ? csum_partial+0x8/0x20 [ 285.370961] ? raw_getfrag+0xe5/0x140 [ 285.371559] ip_finish_output2+0x539/0xa40 [ 285.372222] ? __pfx_ip_finish_output2+0x10/0x10 [ 285.372954] ip_output+0x113/0x1e0 [ 285.373512] ? __pfx_ip_output+0x10/0x10 [ 285.374130] ? icmp_out_count+0x49/0x60 [ 285.374739] ? __pfx_ip_finish_output+0x10/0x10 [ 285.375457] ip_push_pending_frames+0xf3/0x100 [ 285.376173] raw_sendmsg+0xef5/0x12d0 [ 285.376760] ? do_syscall_64+0x40/0x90 [ 285.377359] ? __static_call_text_end+0x136578/0x136578 [ 285.378173] ? do_syscall_64+0x40/0x90 [ 285.378772] ? kasan_enable_current+0x11/0x20 [ 285.379469] ? __pfx_raw_sendmsg+0x10/0x10 [ 285.380137] ? __sock_create+0x13e/0x270 [ 285.380673] ? __sys_socket+0xf3/0x180 [ 285.381174] ? __x64_sys_socket+0x3d/0x50 [ 285.381725] ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.382425] ? __rcu_read_unlock+0x48/0x70 [ 285.382975] ? ip4_datagram_release_cb+0xd8/0x380 [ 285.383608] ? __pfx_ip4_datagram_release_cb+0x10/0x10 [ 285.384295] ? preempt_count_sub+0x14/0xc0 [ 285.384844] ? __list_del_entry_valid+0x76/0x140 [ 285.385467] ? _raw_spin_lock_bh+0x87/0xe0 [ 285.386014] ? __pfx__raw_spin_lock_bh+0x10/0x10 [ 285.386645] ? release_sock+0xa0/0xd0 [ 285.387148] ? preempt_count_sub+0x14/0xc0 [ 285.387712] ? freeze_secondary_cpus+0x348/0x3c0 [ 285.388341] ? aa_sk_perm+0x177/0x390 [ 285.388856] ? __pfx_aa_sk_perm+0x10/0x10 [ 285.389441] ? check_stack_object+0x22/0x70 [ 285.390032] ? inet_send_prepare+0x2f/0x120 [ 285.390603] ? __pfx_inet_sendmsg+0x10/0x10 [ 285.391172] sock_sendmsg+0xcc/0xe0 [ 285.391667] __sys_sendto+0x190/0x230 [ 285.392168] ? __pfx___sys_sendto+0x10/0x10 [ 285.392727] ? kvm_clock_get_cycles+0x14/0x30 [ 285.393328] ? set_normalized_timespec64+0x57/0x70 [ 285.393980] ? _raw_spin_unlock_irq+0x1b/0x40 [ 285.394578] ? __x64_sys_clock_gettime+0x11c/0x160 [ 285.395225] ? __pfx___x64_sys_clock_gettime+0x10/0x10 [ 285.395908] ? _copy_to_user+0x3e/0x60 [ 285.396432] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.397086] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.397734] ? do_syscall_64+0x71/0x90 [ 285.398258] __x64_sys_sendto+0x74/0x90 [ 285.398786] do_syscall_64+0x64/0x90 [ 285.399273] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.399949] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.400605] ? do_syscall_64+0x71/0x90 [ 285.401124] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.401807] RIP: 0033:0x495726 [ 285.402233] Code: ff ff ff f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 11 b8 2c 00 00 00 0f 09 [ 285.404683] RSP: 002b:00007ffcc25fb618 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 285.405677] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 0000000000495726 [ 285.406628] RDX: 0000000000000040 RSI: 0000000002518750 RDI: 0000000000000000 [ 285.407565] RBP: 00000000005205ef R08: 00000000005f8838 R09: 000000000000001c [ 285.408523] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000002517634 [ 285.409460] R13: 00007ffcc25fb6f0 R14: 0000000000000003 R15: 0000000000000000 [ 285.410403] </TASK> [ 285.410704] [ 285.410929] Allocated by task 144: [ 285.411402] kasan_save_stack+0x1e/0x40 [ 285.411926] kasan_set_track+0x21/0x30 [ 285.412442] __kasan_slab_alloc+0x55/0x70 [ 285.412973] kmem_cache_alloc_node+0x187/0x3d0 [ 285.413567] __alloc_skb+0x1b4/0x230 [ 285.414060] __ip_append_data+0x17f7/0x1b60 [ 285.414633] ip_append_data+0x97/0xf0 [ 285.415144] raw_sendmsg+0x5a8/0x12d0 [ 285.415640] sock_sendmsg+0xcc/0xe0 [ 285.416117] __sys_sendto+0x190/0x230 [ 285.416626] __x64_sys_sendto+0x74/0x90 [ 285.417145] do_syscall_64+0x64/0x90 [ 285.417624] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.418306] [ 285.418531] Freed by task 144: [ 285.418960] kasan_save_stack+0x1e/0x40 [ 285.419469] kasan_set_track+0x21/0x30 [ 285.419988] kasan_save_free_info+0x27/0x40 [ 285.420556] ____kasan_slab_free+0x109/0x1a0 [ 285.421146] kmem_cache_free+0x1c2/0x450 [ 285.421680] __netif_receive_skb_core+0x2ce/0x1870 [ 285.422333] __netif_receive_skb_one_core+0x97/0x140 [ 285.423003] process_backlog+0x100/0x2f0 [ 285.423537] __napi_poll+0x5c/0x2d0 [ 285.424023] net_rx_action+0x2be/0x560 [ 285.424510] __do_softirq+0x11b/0x3de [ 285.425034] [ 285.425254] The buggy address belongs to the object at ffff8880bad31280 [ 285.425254] which belongs to the cache skbuff_head_cache of size 224 [ 285.426993] The buggy address is located 40 bytes inside of [ 285.426993] freed 224-byte region [ffff8880bad31280, ffff8880bad31360) [ 285.428572] [ 285.428798] The buggy address belongs to the physical page: [ 285.429540] page:00000000f4b77674 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbad31 [ 285.430758] flags: 0x100000000000200(slab|node=0|zone=1) [ 285.431447] page_type: 0xffffffff() [ 285.431934] raw: 0100000000000200 ffff88810094a8c0 dead000000000122 0000000000000000 [ 285.432757] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 [ 285.433562] page dumped because: kasan: bad access detected [ 285.434144] [ 285.434320] Memory state around the buggy address: [ 285.434828] ffff8880bad31180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.435580] ffff8880bad31200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.436264] >ffff8880bad31280: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 285.436777] ^ [ 285.437106] ffff8880bad31300: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 285.437616] ffff8880bad31380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.438126] ================================================================== [ 285.438662] Disabling lock debugging due to kernel taint Fix this by: 1. Changing sch_plug's .peek handler to qdisc_peek_dequeued(), a function compatible with non-work-conserving qdiscs 2. Checking the return value of qdisc_dequeue_peeked() in sch_qfq. Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Reported-by: valis <sec(a)valis.email> Signed-off-by: valis <sec(a)valis.email> Signed-off-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Link: https://lore.kernel.org/r/20230901162237.11525-1-jhs@mojatatu.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/sched/sch_plug.c | 2 +- net/sched/sch_qfq.c | 22 +++++++++++++++++----- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index cbc2ebca4548..339990bb5981 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -210,7 +210,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .priv_size = sizeof(struct plug_sched_data), .enqueue = plug_enqueue, .dequeue = plug_dequeue, - .peek = qdisc_peek_head, + .peek = qdisc_peek_dequeued, .init = plug_init, .change = plug_change, .reset = qdisc_reset_queue, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 1aa9e71a1d76..9447f486141d 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -976,10 +976,13 @@ static void qfq_update_eligible(struct qfq_sched *q) } /* Dequeue head packet of the head class in the DRR queue of the aggregate. */ -static void agg_dequeue(struct qfq_aggregate *agg, - struct qfq_class *cl, unsigned int len) +static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, + struct qfq_class *cl, unsigned int len) { - qdisc_dequeue_peeked(cl->qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc); + + if (!skb) + return NULL; cl->deficit -= (int) len; @@ -989,6 +992,8 @@ static void agg_dequeue(struct qfq_aggregate *agg, cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } + + return skb; } static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, @@ -1134,11 +1139,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) if (!skb) return NULL; - qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; + + skb = agg_dequeue(in_serv_agg, cl, len); + + if (!skb) { + sch->q.qlen++; + return NULL; + } + + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); - agg_dequeue(in_serv_agg, cl, len); /* If lmax is lowered, through qfq_change_class, for a class * owning pending packets with larger size than the new value * of lmax, then the following condition may hold. -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] net: sched: sch_qfq: Fix UAF in qfq_dequeue()
by Liu Jian 15 Sep '23

15 Sep '23

From: valis <sec(a)valis.email> mainline inclusion from mainline-v6.6-rc1 commit 8fc134fee27f2263988ae38920bc03da416b03d8 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I80USB CVE: CVE-2023-4921 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- When the plug qdisc is used as a class of the qfq qdisc it could trigger a UAF. This issue can be reproduced with following commands: tc qdisc add dev lo root handle 1: qfq tc class add dev lo parent 1: classid 1:1 qfq weight 1 maxpkt 512 tc qdisc add dev lo parent 1:1 handle 2: plug tc filter add dev lo parent 1: basic classid 1:1 ping -c1 127.0.0.1 and boom: [ 285.353793] BUG: KASAN: slab-use-after-free in qfq_dequeue+0xa7/0x7f0 [ 285.354910] Read of size 4 at addr ffff8880bad312a8 by task ping/144 [ 285.355903] [ 285.356165] CPU: 1 PID: 144 Comm: ping Not tainted 6.5.0-rc3+ #4 [ 285.357112] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 [ 285.358376] Call Trace: [ 285.358773] <IRQ> [ 285.359109] dump_stack_lvl+0x44/0x60 [ 285.359708] print_address_description.constprop.0+0x2c/0x3c0 [ 285.360611] kasan_report+0x10c/0x120 [ 285.361195] ? qfq_dequeue+0xa7/0x7f0 [ 285.361780] qfq_dequeue+0xa7/0x7f0 [ 285.362342] __qdisc_run+0xf1/0x970 [ 285.362903] net_tx_action+0x28e/0x460 [ 285.363502] __do_softirq+0x11b/0x3de [ 285.364097] do_softirq.part.0+0x72/0x90 [ 285.364721] </IRQ> [ 285.365072] <TASK> [ 285.365422] __local_bh_enable_ip+0x77/0x90 [ 285.366079] __dev_queue_xmit+0x95f/0x1550 [ 285.366732] ? __pfx_csum_and_copy_from_iter+0x10/0x10 [ 285.367526] ? __pfx___dev_queue_xmit+0x10/0x10 [ 285.368259] ? __build_skb_around+0x129/0x190 [ 285.368960] ? ip_generic_getfrag+0x12c/0x170 [ 285.369653] ? __pfx_ip_generic_getfrag+0x10/0x10 [ 285.370390] ? csum_partial+0x8/0x20 [ 285.370961] ? raw_getfrag+0xe5/0x140 [ 285.371559] ip_finish_output2+0x539/0xa40 [ 285.372222] ? __pfx_ip_finish_output2+0x10/0x10 [ 285.372954] ip_output+0x113/0x1e0 [ 285.373512] ? __pfx_ip_output+0x10/0x10 [ 285.374130] ? icmp_out_count+0x49/0x60 [ 285.374739] ? __pfx_ip_finish_output+0x10/0x10 [ 285.375457] ip_push_pending_frames+0xf3/0x100 [ 285.376173] raw_sendmsg+0xef5/0x12d0 [ 285.376760] ? do_syscall_64+0x40/0x90 [ 285.377359] ? __static_call_text_end+0x136578/0x136578 [ 285.378173] ? do_syscall_64+0x40/0x90 [ 285.378772] ? kasan_enable_current+0x11/0x20 [ 285.379469] ? __pfx_raw_sendmsg+0x10/0x10 [ 285.380137] ? __sock_create+0x13e/0x270 [ 285.380673] ? __sys_socket+0xf3/0x180 [ 285.381174] ? __x64_sys_socket+0x3d/0x50 [ 285.381725] ? entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.382425] ? __rcu_read_unlock+0x48/0x70 [ 285.382975] ? ip4_datagram_release_cb+0xd8/0x380 [ 285.383608] ? __pfx_ip4_datagram_release_cb+0x10/0x10 [ 285.384295] ? preempt_count_sub+0x14/0xc0 [ 285.384844] ? __list_del_entry_valid+0x76/0x140 [ 285.385467] ? _raw_spin_lock_bh+0x87/0xe0 [ 285.386014] ? __pfx__raw_spin_lock_bh+0x10/0x10 [ 285.386645] ? release_sock+0xa0/0xd0 [ 285.387148] ? preempt_count_sub+0x14/0xc0 [ 285.387712] ? freeze_secondary_cpus+0x348/0x3c0 [ 285.388341] ? aa_sk_perm+0x177/0x390 [ 285.388856] ? __pfx_aa_sk_perm+0x10/0x10 [ 285.389441] ? check_stack_object+0x22/0x70 [ 285.390032] ? inet_send_prepare+0x2f/0x120 [ 285.390603] ? __pfx_inet_sendmsg+0x10/0x10 [ 285.391172] sock_sendmsg+0xcc/0xe0 [ 285.391667] __sys_sendto+0x190/0x230 [ 285.392168] ? __pfx___sys_sendto+0x10/0x10 [ 285.392727] ? kvm_clock_get_cycles+0x14/0x30 [ 285.393328] ? set_normalized_timespec64+0x57/0x70 [ 285.393980] ? _raw_spin_unlock_irq+0x1b/0x40 [ 285.394578] ? __x64_sys_clock_gettime+0x11c/0x160 [ 285.395225] ? __pfx___x64_sys_clock_gettime+0x10/0x10 [ 285.395908] ? _copy_to_user+0x3e/0x60 [ 285.396432] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.397086] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.397734] ? do_syscall_64+0x71/0x90 [ 285.398258] __x64_sys_sendto+0x74/0x90 [ 285.398786] do_syscall_64+0x64/0x90 [ 285.399273] ? exit_to_user_mode_prepare+0x1a/0x120 [ 285.399949] ? syscall_exit_to_user_mode+0x22/0x50 [ 285.400605] ? do_syscall_64+0x71/0x90 [ 285.401124] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.401807] RIP: 0033:0x495726 [ 285.402233] Code: ff ff ff f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 11 b8 2c 00 00 00 0f 09 [ 285.404683] RSP: 002b:00007ffcc25fb618 EFLAGS: 00000246 ORIG_RAX: 000000000000002c [ 285.405677] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 0000000000495726 [ 285.406628] RDX: 0000000000000040 RSI: 0000000002518750 RDI: 0000000000000000 [ 285.407565] RBP: 00000000005205ef R08: 00000000005f8838 R09: 000000000000001c [ 285.408523] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000002517634 [ 285.409460] R13: 00007ffcc25fb6f0 R14: 0000000000000003 R15: 0000000000000000 [ 285.410403] </TASK> [ 285.410704] [ 285.410929] Allocated by task 144: [ 285.411402] kasan_save_stack+0x1e/0x40 [ 285.411926] kasan_set_track+0x21/0x30 [ 285.412442] __kasan_slab_alloc+0x55/0x70 [ 285.412973] kmem_cache_alloc_node+0x187/0x3d0 [ 285.413567] __alloc_skb+0x1b4/0x230 [ 285.414060] __ip_append_data+0x17f7/0x1b60 [ 285.414633] ip_append_data+0x97/0xf0 [ 285.415144] raw_sendmsg+0x5a8/0x12d0 [ 285.415640] sock_sendmsg+0xcc/0xe0 [ 285.416117] __sys_sendto+0x190/0x230 [ 285.416626] __x64_sys_sendto+0x74/0x90 [ 285.417145] do_syscall_64+0x64/0x90 [ 285.417624] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 285.418306] [ 285.418531] Freed by task 144: [ 285.418960] kasan_save_stack+0x1e/0x40 [ 285.419469] kasan_set_track+0x21/0x30 [ 285.419988] kasan_save_free_info+0x27/0x40 [ 285.420556] ____kasan_slab_free+0x109/0x1a0 [ 285.421146] kmem_cache_free+0x1c2/0x450 [ 285.421680] __netif_receive_skb_core+0x2ce/0x1870 [ 285.422333] __netif_receive_skb_one_core+0x97/0x140 [ 285.423003] process_backlog+0x100/0x2f0 [ 285.423537] __napi_poll+0x5c/0x2d0 [ 285.424023] net_rx_action+0x2be/0x560 [ 285.424510] __do_softirq+0x11b/0x3de [ 285.425034] [ 285.425254] The buggy address belongs to the object at ffff8880bad31280 [ 285.425254] which belongs to the cache skbuff_head_cache of size 224 [ 285.426993] The buggy address is located 40 bytes inside of [ 285.426993] freed 224-byte region [ffff8880bad31280, ffff8880bad31360) [ 285.428572] [ 285.428798] The buggy address belongs to the physical page: [ 285.429540] page:00000000f4b77674 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbad31 [ 285.430758] flags: 0x100000000000200(slab|node=0|zone=1) [ 285.431447] page_type: 0xffffffff() [ 285.431934] raw: 0100000000000200 ffff88810094a8c0 dead000000000122 0000000000000000 [ 285.432757] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 [ 285.433562] page dumped because: kasan: bad access detected [ 285.434144] [ 285.434320] Memory state around the buggy address: [ 285.434828] ffff8880bad31180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.435580] ffff8880bad31200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.436264] >ffff8880bad31280: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 285.436777] ^ [ 285.437106] ffff8880bad31300: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 285.437616] ffff8880bad31380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 285.438126] ================================================================== [ 285.438662] Disabling lock debugging due to kernel taint Fix this by: 1. Changing sch_plug's .peek handler to qdisc_peek_dequeued(), a function compatible with non-work-conserving qdiscs 2. Checking the return value of qdisc_dequeue_peeked() in sch_qfq. Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Reported-by: valis <sec(a)valis.email> Signed-off-by: valis <sec(a)valis.email> Signed-off-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Link: https://lore.kernel.org/r/20230901162237.11525-1-jhs@mojatatu.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/sched/sch_plug.c | 2 +- net/sched/sch_qfq.c | 22 +++++++++++++++++----- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 5619d2eb17b6..4ddb4af61d10 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -214,7 +214,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .priv_size = sizeof(struct plug_sched_data), .enqueue = plug_enqueue, .dequeue = plug_dequeue, - .peek = qdisc_peek_head, + .peek = qdisc_peek_dequeued, .init = plug_init, .change = plug_change, .reset = qdisc_reset_queue, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index a08579a5f75e..5b7b149a2b9f 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -989,10 +989,13 @@ static void qfq_update_eligible(struct qfq_sched *q) } /* Dequeue head packet of the head class in the DRR queue of the aggregate. */ -static void agg_dequeue(struct qfq_aggregate *agg, - struct qfq_class *cl, unsigned int len) +static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, + struct qfq_class *cl, unsigned int len) { - qdisc_dequeue_peeked(cl->qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc); + + if (!skb) + return NULL; cl->deficit -= (int) len; @@ -1002,6 +1005,8 @@ static void agg_dequeue(struct qfq_aggregate *agg, cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } + + return skb; } static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, @@ -1147,11 +1152,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) if (!skb) return NULL; - qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; + + skb = agg_dequeue(in_serv_agg, cl, len); + + if (!skb) { + sch->q.qlen++; + return NULL; + } + + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); - agg_dequeue(in_serv_agg, cl, len); /* If lmax is lowered, through qfq_change_class, for a class * owning pending packets with larger size than the new value * of lmax, then the following condition may hold. -- 2.34.1

2 1

[PATCH openEuler-23.09] mm: gmem: Check overflow for prefetch/eagerfree
by Wupeng Ma 15 Sep '23

15 Sep '23

From: Ma Wupeng <mawupeng1(a)huawei.com> euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7WLVX --------------------------------------------- Add overflow check for gmem prefetch/eagerfree. Fixes: 3e01aec2b2e8 ("mm: gmem: Introduce hmadvise") Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- mm/gmem.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/mm/gmem.c b/mm/gmem.c index a710869d04a9..90a5b5fda284 100644 --- a/mm/gmem.c +++ b/mm/gmem.c @@ -622,12 +622,25 @@ static int hmadvise_do_prefetch(gm_dev_t *dev, unsigned long addr, size_t size) struct prefetch_data *data; struct vm_area_struct *vma; int res = GM_RET_SUCCESS; + unsigned long old_start; + + /* overflow */ + if (check_add_overflow(addr, size, &end)) + return -EINVAL; + + old_start = end; /* Align addr by rounding outward to make page cover addr. */ - end = round_up(addr + size, page_size); + end = round_up(end, page_size); start = round_down(addr, page_size); size = end - start; + if (!end && old_start) + return -EINVAL; + + if (size == 0) + return 0; + mmap_read_lock(current->mm); vma = find_vma(current->mm, start); if (!vma || start < vma->vm_start || end > vma->vm_end) { @@ -675,19 +688,30 @@ static int hmadvise_do_eagerfree(unsigned long addr, size_t size) .size = page_size, .copy = false, }; + unsigned long old_start; vm_object_t *obj; + /* overflow */ + if (check_add_overflow(addr, size, &end)) + return -EINVAL; + + old_start = addr; + /* Align addr by rounding inward to avoid excessive page release. */ - end = round_down(addr + size, page_size); + end = round_down(end, page_size); start = round_up(addr, page_size); if (start >= end) return ret; + /* Check to see whether len was rounded up from small -ve to zero */ + if (old_start && !start) + return -EINVAL; + mmap_read_lock(current->mm); do { vma = find_vma(current->mm, start); if (!vma || !vma_is_peer_shared(vma)) { - pr_err("gmem: not peer-shared vma, skip dontneed\n"); + pr_info_ratelimited("gmem: not peer-shared vma, skip dontneed\n"); continue; } obj = vma->vm_obj; -- 2.25.1

2 1

[PATCH openEuler-23.09] kernel: Fix compile failure out of the srctree
by Wang Wensheng 14 Sep '23

14 Sep '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I81E6X --------------------------------------------- Build the kernel Image out of the srctree with the following command: $ mkdir build $ cd build $ make -C ../ O=`pwd` openeuler_defconfig $ make Image -j64 would get the following error message: ../Makefile:1315: Makefile.oever: No such file or directory make: *** No rule to make target 'Makefile.oever'. Stop. Add a directory path for the included file to fix this. Fixes: 0177b043eb4e ("kernel: add OPENEULER_VERSION_CODE to version.h") Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5b2b3ad42a2d..5061718274f0 100644 --- a/Makefile +++ b/Makefile @@ -1312,7 +1312,7 @@ uapi-asm-generic: # --------------------------------------------------------------------------- # openEuler version variables -include Makefile.oever +include $(srctree)/Makefile.oever # KERNELRELEASE can change from a few different places, meaning version.h # needs to be updated, so this check is forced on all builds -- 2.17.1

2 1

[PATCH OLK-5.10 0/2] Fix the two problems when using binutil 2.41.
by Hongchen Zhang 14 Sep '23

14 Sep '23

LoongArch: Fix the write_fcsr() macro LoongArch: Fix module relocation error with binutils 2.41 arch/loongarch/Makefile | 2 ++ arch/loongarch/include/asm/loongarch.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) -- 2.33.0

2 3