March 2021 - Linuxarm - mailweb.openeuler.org

[RFC V2] app/testpmd: support multi-process
by Lijun Ou 05 Mar '21

05 Mar '21

This patch adds multi-process support for testpmd. The test cmd example as follows: the primary cmd: ./testpmd -w xxx --file-prefix=xx -l 0-1 -n 2 -- -i\ --rxq=16 --txq=16 --num-procs=2 --proc-id=0 the secondary cmd: ./testpmd -w xxx --file-prefix=xx -l 2-3 -n 2 -- -i\ --rxq=16 --txq=16 --num-procs=2 --proc-id=1 Signed-off-by: Min Hu (Connor) <humin29(a)huawei.com> Signed-off-by: Lijun Ou <oulijun(a)huawei.com> --- app/test-pmd/cmdline.c | 6 ++- app/test-pmd/config.c | 9 +++- app/test-pmd/parameters.c | 9 ++++ app/test-pmd/testpmd.c | 135 +++++++++++++++++++++++++++++----------------- app/test-pmd/testpmd.h | 7 +++ 5 files changed, 114 insertions(+), 52 deletions(-) diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c index 89034c8..48af5cd 100644 --- a/app/test-pmd/cmdline.c +++ b/app/test-pmd/cmdline.c @@ -71,8 +71,6 @@ #include "cmdline_tm.h" #include "bpf_cmd.h" -static struct cmdline *testpmd_cl; - static void cmd_reconfig_device_queue(portid_t id, uint8_t dev, uint8_t queue); /* *** Help command with introduction. *** */ @@ -17124,6 +17122,10 @@ prompt(void) if (testpmd_cl == NULL) return; cmdline_interact(testpmd_cl); + if (unlikely(f_quit == 1)) { + dup2(testpmd_fd_copy, testpmd_cl->s_in); + close(testpmd_fd_copy); + } cmdline_stdin_exit(testpmd_cl); } diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c index 0e2b9f7..f065008 100644 --- a/app/test-pmd/config.c +++ b/app/test-pmd/config.c @@ -3100,6 +3100,8 @@ rss_fwd_config_setup(void) queueid_t rxq; queueid_t nb_q; streamid_t sm_id; + int start; + int end; nb_q = nb_rxq; if (nb_q > nb_txq) @@ -3117,7 +3119,10 @@ rss_fwd_config_setup(void) init_fwd_streams(); setup_fwd_config_of_each_lcore(&cur_fwd_config); - rxp = 0; rxq = 0; + start = proc_id * nb_q / num_procs; + end = start + nb_q / num_procs; + rxp = 0; + rxq = start; for (sm_id = 0; sm_id < cur_fwd_config.nb_fwd_streams; sm_id++) { struct fwd_stream *fs; @@ -3134,6 +3139,8 @@ rss_fwd_config_setup(void) continue; rxp = 0; rxq++; + if (rxq >= end) + rxq = start; } } diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c index df5eb10..ac63854 100644 --- a/app/test-pmd/parameters.c +++ b/app/test-pmd/parameters.c @@ -45,6 +45,8 @@ #include <rte_flow.h> #include "testpmd.h" +#define PARAM_PROC_ID "proc-id" +#define PARAM_NUM_PROCS "num-procs" static void usage(char* progname) @@ -603,6 +605,8 @@ launch_args_parse(int argc, char** argv) { "rx-mq-mode", 1, 0, 0 }, { "record-core-cycles", 0, 0, 0 }, { "record-burst-stats", 0, 0, 0 }, + { PARAM_NUM_PROCS, 1, 0, 0 }, + { PARAM_PROC_ID, 1, 0, 0 }, { 0, 0, 0, 0 }, }; @@ -1356,6 +1360,11 @@ launch_args_parse(int argc, char** argv) record_core_cycles = 1; if (!strcmp(lgopts[opt_idx].name, "record-burst-stats")) record_burst_stats = 1; + + if (strncmp(lgopts[opt_idx].name, PARAM_NUM_PROCS, 8) == 0) + num_procs = atoi(optarg); + if (strncmp(lgopts[opt_idx].name, PARAM_PROC_ID, 7) == 0) + proc_id = atoi(optarg); break; case 'h': usage(argv[0]); diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index c256e71..3abd080 100644 --- a/app/test-pmd/testpmd.c +++ b/app/test-pmd/testpmd.c @@ -63,6 +63,8 @@ #include "testpmd.h" +int testpmd_fd_copy = 500; /* the copy of STDIN_FILENO */ + #ifndef MAP_HUGETLB /* FreeBSD may not have MAP_HUGETLB (in fact, it probably doesn't) */ #define HUGE_FLAG (0x40000) @@ -125,6 +127,9 @@ uint8_t port_numa[RTE_MAX_ETHPORTS]; */ uint8_t rxring_numa[RTE_MAX_ETHPORTS]; +int proc_id = 0; +unsigned num_procs = 1; + /* * Store specified sockets on which TX ring to be used by ports * is allocated. @@ -978,16 +983,26 @@ mbuf_pool_create(uint16_t mbuf_seg_size, unsigned nb_mbuf, /* wrapper to rte_mempool_create() */ TESTPMD_LOG(INFO, "preferred mempool ops selected: %s\n", rte_mbuf_best_mempool_ops()); - rte_mp = rte_pktmbuf_pool_create(pool_name, nb_mbuf, - mb_mempool_cache, 0, mbuf_seg_size, socket_id); + if (rte_eal_process_type() == RTE_PROC_PRIMARY) + rte_mp = rte_pktmbuf_pool_create(pool_name, + nb_mbuf, mb_mempool_cache, 0, + mbuf_seg_size, socket_id); + else + rte_mp = rte_mempool_lookup(pool_name); + break; } case MP_ALLOC_ANON: { - rte_mp = rte_mempool_create_empty(pool_name, nb_mbuf, - mb_size, (unsigned int) mb_mempool_cache, - sizeof(struct rte_pktmbuf_pool_private), - socket_id, mempool_flags); + if (rte_eal_process_type() == RTE_PROC_PRIMARY) + rte_mp = rte_mempool_create_empty(pool_name, + nb_mbuf, mb_size, + (unsigned int)mb_mempool_cache, + sizeof(struct rte_pktmbuf_pool_private), + socket_id, mempool_flags); + else + rte_mp = rte_mempool_lookup(pool_name); + if (rte_mp == NULL) goto err; @@ -1017,9 +1032,13 @@ mbuf_pool_create(uint16_t mbuf_seg_size, unsigned nb_mbuf, TESTPMD_LOG(INFO, "preferred mempool ops selected: %s\n", rte_mbuf_best_mempool_ops()); - rte_mp = rte_pktmbuf_pool_create(pool_name, nb_mbuf, - mb_mempool_cache, 0, mbuf_seg_size, - heap_socket); + if (rte_eal_process_type() == RTE_PROC_PRIMARY) + rte_mp = rte_pktmbuf_pool_create(pool_name, + nb_mbuf, mb_mempool_cache, 0, + mbuf_seg_size, heap_socket); + else + rte_mp = rte_mempool_lookup(pool_name); + break; } case MP_ALLOC_XBUF: @@ -2503,21 +2522,28 @@ start_port(portid_t pid) return -1; } /* configure port */ - diag = rte_eth_dev_configure(pi, nb_rxq + nb_hairpinq, + if (rte_eal_process_type() == RTE_PROC_PRIMARY) { + diag = rte_eth_dev_configure(pi, + nb_rxq + nb_hairpinq, nb_txq + nb_hairpinq, &(port->dev_conf)); - if (diag != 0) { - if (rte_atomic16_cmpset(&(port->port_status), - RTE_PORT_HANDLING, RTE_PORT_STOPPED) == 0) - printf("Port %d can not be set back " - "to stopped\n", pi); - printf("Fail to configure port %d\n", pi); - /* try to reconfigure port next time */ - port->need_reconfig = 1; - return -1; + if (diag != 0) { + if (rte_atomic16_cmpset( + &(port->port_status), + RTE_PORT_HANDLING, + RTE_PORT_STOPPED) == 0) + printf("Port %d can not be set " + "back to stopped\n", pi); + printf("Fail to configure port %d\n", + pi); + /* try to reconfigure port next time */ + port->need_reconfig = 1; + return -1; + } } } - if (port->need_reconfig_queues > 0) { + if (port->need_reconfig_queues > 0 && + rte_eal_process_type() == RTE_PROC_PRIMARY) { port->need_reconfig_queues = 0; /* setup tx queues */ for (qi = 0; qi < nb_txq; qi++) { @@ -2618,15 +2644,18 @@ start_port(portid_t pid) cnt_pi++; /* start port */ - if (rte_eth_dev_start(pi) < 0) { - printf("Fail to start port %d\n", pi); - - /* Fail to setup rx queue, return */ - if (rte_atomic16_cmpset(&(port->port_status), - RTE_PORT_HANDLING, RTE_PORT_STOPPED) == 0) - printf("Port %d can not be set back to " - "stopped\n", pi); - continue; + if (rte_eal_process_type() == RTE_PROC_PRIMARY) { + diag = rte_eth_dev_start(pi); + if (diag < 0) { + printf("Fail to start port %d\n", pi); + + /* Fail to setup rx queue, return */ + if (rte_atomic16_cmpset(&(port->port_status), + RTE_PORT_HANDLING, RTE_PORT_STOPPED) == 0) + printf("Port %d can not be set back to " + "stopped\n", pi); + continue; + } } if (rte_atomic16_cmpset(&(port->port_status), @@ -2755,7 +2784,7 @@ stop_port(portid_t pid) if (port->flow_list) port_flow_flush(pi); - if (rte_eth_dev_stop(pi) != 0) + if (rte_eal_process_type() == RTE_PROC_PRIMARY && rte_eth_dev_stop(pi) != 0) RTE_LOG(ERR, EAL, "rte_eth_dev_stop failed for port %u\n", pi); @@ -2824,8 +2853,10 @@ close_port(portid_t pid) continue; } - port_flow_flush(pi); - rte_eth_dev_close(pi); + if (rte_eal_process_type() == RTE_PROC_PRIMARY) + port_flow_flush(pi); + if (rte_eal_process_type() == RTE_PROC_PRIMARY) + rte_eth_dev_close(pi); } remove_invalid_ports(); @@ -3089,7 +3120,7 @@ pmd_test_exit(void) } } for (i = 0 ; i < RTE_DIM(mempools) ; i++) { - if (mempools[i]) + if (rte_eal_process_type() == RTE_PROC_PRIMARY && mempools[i]) rte_mempool_free(mempools[i]); } @@ -3537,6 +3568,10 @@ init_port_dcb_config(portid_t pid, int retval; uint16_t i; + if (num_procs > 1) { + printf("The multi-process feature doesn't support dcb.\n"); + return -ENOTSUP; + } rte_port = &ports[pid]; memset(&port_conf, 0, sizeof(struct rte_eth_conf)); @@ -3635,13 +3670,6 @@ init_port(void) } static void -force_quit(void) -{ - pmd_test_exit(); - prompt_exit(); -} - -static void print_stats(void) { uint8_t i; @@ -3672,12 +3700,16 @@ signal_handler(int signum) if (latencystats_enabled != 0) rte_latencystats_uninit(); #endif - force_quit(); /* Set flag to indicate the force termination. */ f_quit = 1; - /* exit with the expected status */ - signal(signum, SIG_DFL); - kill(getpid(), signum); + if (interactive == 1) { + dup2(testpmd_cl->s_in, testpmd_fd_copy); + close(testpmd_cl->s_in); + } else { + dup2(0, testpmd_fd_copy); + close(0); + } + } } @@ -3702,10 +3734,6 @@ main(int argc, char** argv) rte_exit(EXIT_FAILURE, "Cannot init EAL: %s\n", rte_strerror(rte_errno)); - if (rte_eal_process_type() == RTE_PROC_SECONDARY) - rte_exit(EXIT_FAILURE, - "Secondary process type not supported.\n"); - ret = register_eth_event_callback(); if (ret != 0) rte_exit(EXIT_FAILURE, "Cannot register for ethdev events"); @@ -3801,8 +3829,10 @@ main(int argc, char** argv) } } - if (!no_device_start && start_port(RTE_PORT_ALL) != 0) + if (!no_device_start && start_port(RTE_PORT_ALL) != 0) { + pmd_test_exit(); rte_exit(EXIT_FAILURE, "Start ports failed\n"); + } /* set all ports to promiscuous mode by default */ RTE_ETH_FOREACH_DEV(port_id) { @@ -3848,6 +3878,8 @@ main(int argc, char** argv) } prompt(); pmd_test_exit(); + if (unlikely(f_quit == 1)) + prompt_exit(); } else #endif { @@ -3883,6 +3915,11 @@ main(int argc, char** argv) printf("Press enter to exit\n"); rc = read(0, &c, 1); pmd_test_exit(); + if (unlikely(f_quit == 1)) { + dup2(testpmd_fd_copy, 0); + close(testpmd_fd_copy); + prompt_exit(); + } if (rc < 0) return 1; } diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h index 5f23162..8629c57 100644 --- a/app/test-pmd/testpmd.h +++ b/app/test-pmd/testpmd.h @@ -13,6 +13,7 @@ #include <rte_gso.h> #include <cmdline.h> #include <sys/queue.h> +#include "cmdline.h" #define RTE_PORT_ALL (~(portid_t)0x0) @@ -24,6 +25,10 @@ #define RTE_PORT_CLOSED (uint16_t)2 #define RTE_PORT_HANDLING (uint16_t)3 +uint8_t f_quit; +int testpmd_fd_copy; +struct cmdline *testpmd_cl; + /* * It is used to allocate the memory for hash key. * The hash key size is NIC dependent. @@ -421,6 +426,8 @@ extern uint64_t noisy_lkup_mem_sz; extern uint64_t noisy_lkup_num_writes; extern uint64_t noisy_lkup_num_reads; extern uint64_t noisy_lkup_num_reads_writes; +extern int proc_id; +extern unsigned num_procs; extern uint8_t dcb_config; extern uint8_t dcb_test; -- 2.7.4

2 2

[PATCH 00/13] Features and bugfixes for hns3
by Lijun Ou 04 Mar '21

04 Mar '21

This series add three features according to the 21.05 roadmap as well as fix some bugs. Chengchang Tang (4): net/hns3: support module EEPROM dump net/hns3: add more registers to dump net/hns3: fix maximum frame size update after buffer alloc net/hns3: fix imprecise statistics Chengwen Feng (2): net/hns3: implement cleanup for Tx done net/hns3: support RXD advanced layout Hongbo Zheng (1): net/hns3: add process for MAC interrupt Huisong Li (4): net/hns3: encapsulate a port shaping interface net/hns3: support PF on electrical net device net/hns3: remove unused parameter from func declaration net/hns3: fix memory leakage for mbuf Min Hu (Connor) (2): net/hns3: add Rx and Tx bytes stats net/hns3: add imissed packet stats doc/guides/nics/features/hns3.ini | 1 + doc/guides/nics/features/hns3_vf.ini | 1 + doc/guides/rel_notes/release_21_05.rst | 5 + drivers/net/hns3/hns3_cmd.c | 8 +- drivers/net/hns3/hns3_cmd.h | 81 +++++++ drivers/net/hns3/hns3_dcb.c | 22 +- drivers/net/hns3/hns3_dcb.h | 2 +- drivers/net/hns3/hns3_ethdev.c | 420 +++++++++++++++++++++++++++++---- drivers/net/hns3/hns3_ethdev.h | 22 ++ drivers/net/hns3/hns3_ethdev_vf.c | 46 ++-- drivers/net/hns3/hns3_intr.c | 20 ++ drivers/net/hns3/hns3_intr.h | 4 + drivers/net/hns3/hns3_regs.c | 171 +++++++++++++- drivers/net/hns3/hns3_regs.h | 1 + drivers/net/hns3/hns3_rxtx.c | 283 ++++++++++++++++++++++ drivers/net/hns3/hns3_rxtx.h | 12 + drivers/net/hns3/hns3_rxtx_vec_neon.h | 15 ++ drivers/net/hns3/hns3_rxtx_vec_sve.c | 11 + drivers/net/hns3/hns3_stats.c | 293 +++++++++++++---------- drivers/net/hns3/hns3_stats.h | 12 +- 20 files changed, 1232 insertions(+), 198 deletions(-) -- 2.7.4

3 66

[PATCH 0/4] Fix the parameter of dma_map_sg()
by chenxiang 04 Mar '21

04 Mar '21

From: Xiang Chen <chenxiang66(a)hisilicon.com> According to Documentation/core-api/dma-api-howto.rst, the parameters of dma_unmap_sg() must be the same as those which are passed in to the scatter/gather mapping API. But for some drivers under crypto, the <nents> parameter of dma_unmap_sg() is number of elements after mapping. So fix them. Part of the document is as follows: To unmap a scatterlist, just call:: dma_unmap_sg(dev, sglist, nents, direction); Again, make sure DMA activity has already finished. .. note:: The 'nents' argument to the dma_unmap_sg call must be the _same_ one you passed into the dma_map_sg call, it should _NOT_ be the 'count' value _returned_ from the dma_map_sg call. chenxiang (4): crypto: amlogic - Fix the parameter of dma_unmap_sg() crypto: cavium - Fix the parameter of dma_unmap_sg() crypto: ux500 - Fix the parameter of dma_unmap_sg() crypto: allwinner - Fix the parameter of dma_unmap_sg() drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c | 9 ++++++--- drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c | 3 ++- drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c | 9 ++++++--- drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c | 3 ++- drivers/crypto/amlogic/amlogic-gxl-cipher.c | 6 +++--- drivers/crypto/cavium/nitrox/nitrox_reqmgr.c | 8 ++++---- drivers/crypto/ux500/cryp/cryp_core.c | 4 ++-- drivers/crypto/ux500/hash/hash_core.c | 2 +- 8 files changed, 26 insertions(+), 18 deletions(-) -- 2.8.1

4 10

[PATCH for-next] RDMA/hns: Add support for XRC on HIP09
by Weihang Li 04 Mar '21

04 Mar '21

From: Wenpeng Liang <liangwenpeng(a)huawei.com> The HIP09 supports XRC transport service, it greatly saves the number of QPs required to connect all processes in a large cluster. Signed-off-by: Wenpeng Liang <liangwenpeng(a)huawei.com> Signed-off-by: Weihang Li <liweihang(a)huawei.com> --- drivers/infiniband/hw/hns/hns_roce_alloc.c | 3 + drivers/infiniband/hw/hns/hns_roce_device.h | 25 +++++ drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 147 +++++++++++++++++++--------- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 + drivers/infiniband/hw/hns/hns_roce_main.c | 32 +++++- drivers/infiniband/hw/hns/hns_roce_pd.c | 51 ++++++++++ drivers/infiniband/hw/hns/hns_roce_qp.c | 63 ++++++++---- drivers/infiniband/hw/hns/hns_roce_srq.c | 3 + include/uapi/rdma/hns-abi.h | 2 + 9 files changed, 258 insertions(+), 70 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c index 4bcaaa05..5d389ed 100644 --- a/drivers/infiniband/hw/hns/hns_roce_alloc.c +++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c @@ -304,6 +304,9 @@ int hns_roce_get_umem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs, void hns_roce_cleanup_bitmap(struct hns_roce_dev *hr_dev) { + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC) + hns_roce_cleanup_xrcd_table(hr_dev); + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ) hns_roce_cleanup_srq_table(hr_dev); hns_roce_cleanup_qp_table(hr_dev); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 3d6b7a2d..f74db0f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -137,6 +137,7 @@ enum { SERV_TYPE_UC, SERV_TYPE_RD, SERV_TYPE_UD, + SERV_TYPE_XRC = 5, }; enum hns_roce_qp_state { @@ -168,6 +169,8 @@ enum hns_roce_event { HNS_ROCE_EVENT_TYPE_DB_OVERFLOW = 0x12, HNS_ROCE_EVENT_TYPE_MB = 0x13, HNS_ROCE_EVENT_TYPE_FLR = 0x15, + HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION = 0x16, + HNS_ROCE_EVENT_TYPE_INVALID_XRCETH = 0x17, }; #define HNS_ROCE_CAP_FLAGS_EX_SHIFT 12 @@ -179,6 +182,7 @@ enum { HNS_ROCE_CAP_FLAG_RECORD_DB = BIT(3), HNS_ROCE_CAP_FLAG_SQ_RECORD_DB = BIT(4), HNS_ROCE_CAP_FLAG_SRQ = BIT(5), + HNS_ROCE_CAP_FLAG_XRC = BIT(6), HNS_ROCE_CAP_FLAG_MW = BIT(7), HNS_ROCE_CAP_FLAG_FRMR = BIT(8), HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL = BIT(9), @@ -244,6 +248,11 @@ struct hns_roce_pd { unsigned long pdn; }; +struct hns_roce_xrcd { + struct ib_xrcd ibxrcd; + unsigned long xrcdn; +}; + struct hns_roce_bitmap { /* Bitmap Traversal last a bit which is 1 */ unsigned long last; @@ -467,6 +476,7 @@ struct hns_roce_srq { u32 rsv_sge; int wqe_shift; u32 cqn; + u32 xrcdn; void __iomem *db_reg_l; atomic_t refcount; @@ -640,6 +650,8 @@ struct hns_roce_qp { enum hns_roce_event event_type); unsigned long qpn; + unsigned long xrcdn; + atomic_t refcount; struct completion free; @@ -766,6 +778,8 @@ struct hns_roce_caps { int reserved_uars; int num_pds; int reserved_pds; + int num_xrcds; + int reserved_xrcds; u32 mtt_entry_sz; u32 cqe_sz; u32 page_size_cap; @@ -963,6 +977,7 @@ struct hns_roce_dev { struct hns_roce_cmdq cmd; struct hns_roce_bitmap pd_bitmap; + struct hns_roce_bitmap xrcd_bitmap; struct hns_roce_uar_table uar_table; struct hns_roce_mr_table mr_table; struct hns_roce_cq_table cq_table; @@ -1004,6 +1019,11 @@ static inline struct hns_roce_pd *to_hr_pd(struct ib_pd *ibpd) return container_of(ibpd, struct hns_roce_pd, ibpd); } +static inline struct hns_roce_xrcd *to_hr_xrcd(struct ib_xrcd *ibxrcd) +{ + return container_of(ibxrcd, struct hns_roce_xrcd, ibxrcd); +} + static inline struct hns_roce_ah *to_hr_ah(struct ib_ah *ibah) { return container_of(ibah, struct hns_roce_ah, ibah); @@ -1136,6 +1156,7 @@ int hns_roce_init_mr_table(struct hns_roce_dev *hr_dev); void hns_roce_init_cq_table(struct hns_roce_dev *hr_dev); int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev); int hns_roce_init_srq_table(struct hns_roce_dev *hr_dev); +int hns_roce_init_xrcd_table(struct hns_roce_dev *hr_dev); void hns_roce_cleanup_pd_table(struct hns_roce_dev *hr_dev); void hns_roce_cleanup_mr_table(struct hns_roce_dev *hr_dev); @@ -1143,6 +1164,7 @@ void hns_roce_cleanup_eq_table(struct hns_roce_dev *hr_dev); void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev); void hns_roce_cleanup_qp_table(struct hns_roce_dev *hr_dev); void hns_roce_cleanup_srq_table(struct hns_roce_dev *hr_dev); +void hns_roce_cleanup_xrcd_table(struct hns_roce_dev *hr_dev); int hns_roce_bitmap_alloc(struct hns_roce_bitmap *bitmap, unsigned long *obj); void hns_roce_bitmap_free(struct hns_roce_bitmap *bitmap, unsigned long obj, @@ -1207,6 +1229,9 @@ int hns_roce_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr, struct ib_udata *udata); int hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata); +int hns_roce_alloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata); +int hns_roce_dealloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata); + struct ib_qp *hns_roce_create_qp(struct ib_pd *ib_pd, struct ib_qp_init_attr *init_attr, struct ib_udata *udata); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index c3934ab..593acf1 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1829,6 +1829,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev) caps->num_srqwqe_segs = HNS_ROCE_V2_MAX_SRQWQE_SEGS; caps->num_idx_segs = HNS_ROCE_V2_MAX_IDX_SEGS; caps->num_pds = HNS_ROCE_V2_MAX_PD_NUM; + caps->num_xrcds = HNS_ROCE_V2_MAX_XRCD_NUM; caps->max_qp_init_rdma = HNS_ROCE_V2_MAX_QP_INIT_RDMA; caps->max_qp_dest_rdma = HNS_ROCE_V2_MAX_QP_DEST_RDMA; caps->max_sq_desc_sz = HNS_ROCE_V2_MAX_SQ_DESC_SZ; @@ -1846,6 +1847,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev) caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED; caps->reserved_lkey = 0; caps->reserved_pds = 0; + caps->reserved_xrcds = HNS_ROCE_V2_RSV_XRCD_NUM; caps->reserved_mrws = 1; caps->reserved_uars = 0; caps->reserved_cqs = 0; @@ -1900,7 +1902,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev) caps->flags |= HNS_ROCE_CAP_FLAG_ATOMIC | HNS_ROCE_CAP_FLAG_MW | HNS_ROCE_CAP_FLAG_SRQ | HNS_ROCE_CAP_FLAG_FRMR | - HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL; + HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL | HNS_ROCE_CAP_FLAG_XRC; caps->num_qpc_timer = HNS_ROCE_V2_MAX_QPC_TIMER_NUM; caps->qpc_timer_entry_sz = HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ; @@ -2131,6 +2133,8 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) caps->num_mtt_segs = HNS_ROCE_V2_MAX_MTT_SEGS; caps->ceqe_size = HNS_ROCE_CEQE_SIZE; caps->aeqe_size = HNS_ROCE_AEQE_SIZE; + caps->num_xrcds = HNS_ROCE_V2_MAX_XRCD_NUM; + caps->reserved_xrcds = HNS_ROCE_V2_RSV_XRCD_NUM; caps->mtt_ba_pg_sz = 0; caps->num_cqe_segs = HNS_ROCE_V2_MAX_CQE_SEGS; caps->num_srqwqe_segs = HNS_ROCE_V2_MAX_SRQWQE_SEGS; @@ -3909,6 +3913,16 @@ static void set_qpc_wqe_cnt(struct hns_roce_qp *hr_qp, ilog2(hr_qp->rq.wqe_cnt)); } +static inline int get_cqn(struct ib_cq *ib_cq) +{ + return ib_cq ? to_hr_cq(ib_cq)->cqn : 0; +} + +static inline int get_pdn(struct ib_pd *ib_pd) +{ + return ib_pd ? to_hr_pd(ib_pd)->pdn : 0; +} + static void modify_qp_reset_to_init(struct ib_qp *ibqp, const struct ib_qp_attr *attr, int attr_mask, @@ -3925,13 +3939,13 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp, * 0 at the same time, else set them to 0x1. */ roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_TST_M, - V2_QPC_BYTE_4_TST_S, to_hr_qp_type(hr_qp->ibqp.qp_type)); + V2_QPC_BYTE_4_TST_S, to_hr_qp_type(ibqp->qp_type)); roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_SQPN_M, V2_QPC_BYTE_4_SQPN_S, hr_qp->qpn); roce_set_field(context->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M, - V2_QPC_BYTE_16_PD_S, to_hr_pd(ibqp->pd)->pdn); + V2_QPC_BYTE_16_PD_S, get_pdn(ibqp->pd)); roce_set_field(context->byte_20_smac_sgid_idx, V2_QPC_BYTE_20_RQWS_M, V2_QPC_BYTE_20_RQWS_S, ilog2(hr_qp->rq.max_gs)); @@ -3942,6 +3956,9 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp, roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_VLAN_ID_M, V2_QPC_BYTE_24_VLAN_ID_S, 0xfff); + if (ibqp->qp_type == IB_QPT_XRC_TGT) + context->qkey_xrcd = cpu_to_le32(hr_qp->xrcdn); + if (hr_qp->en_flags & HNS_ROCE_QP_CAP_RQ_RECORD_DB) roce_set_bit(context->byte_68_rq_db, V2_QPC_BYTE_68_RQ_RECORD_EN_S, 1); @@ -3956,19 +3973,20 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp, (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) ? 1 : 0); roce_set_field(context->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M, - V2_QPC_BYTE_80_RX_CQN_S, to_hr_cq(ibqp->recv_cq)->cqn); + V2_QPC_BYTE_80_RX_CQN_S, get_cqn(ibqp->recv_cq)); + if (ibqp->srq) { + roce_set_bit(context->byte_76_srqn_op_en, + V2_QPC_BYTE_76_SRQ_EN_S, 1); roce_set_field(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_SRQN_M, V2_QPC_BYTE_76_SRQN_S, to_hr_srq(ibqp->srq)->srqn); - roce_set_bit(context->byte_76_srqn_op_en, - V2_QPC_BYTE_76_SRQ_EN_S, 1); } roce_set_bit(context->byte_172_sq_psn, V2_QPC_BYTE_172_FRE_S, 1); roce_set_field(context->byte_252_err_txcqn, V2_QPC_BYTE_252_TX_CQN_M, - V2_QPC_BYTE_252_TX_CQN_S, to_hr_cq(ibqp->send_cq)->cqn); + V2_QPC_BYTE_252_TX_CQN_S, get_cqn(ibqp->send_cq)); if (hr_dev->caps.qpc_sz < HNS_ROCE_V3_QPC_SZ) return; @@ -3991,22 +4009,28 @@ static void modify_qp_init_to_init(struct ib_qp *ibqp, * 0 at the same time, else set them to 0x1. */ roce_set_field(context->byte_4_sqpn_tst, V2_QPC_BYTE_4_TST_M, - V2_QPC_BYTE_4_TST_S, to_hr_qp_type(hr_qp->ibqp.qp_type)); + V2_QPC_BYTE_4_TST_S, to_hr_qp_type(ibqp->qp_type)); roce_set_field(qpc_mask->byte_4_sqpn_tst, V2_QPC_BYTE_4_TST_M, V2_QPC_BYTE_4_TST_S, 0); + if (ibqp->qp_type == IB_QPT_XRC_TGT) { + context->qkey_xrcd = cpu_to_le32(hr_qp->xrcdn); + qpc_mask->qkey_xrcd = 0; + } + roce_set_field(context->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M, - V2_QPC_BYTE_16_PD_S, to_hr_pd(ibqp->pd)->pdn); + V2_QPC_BYTE_16_PD_S, get_pdn(ibqp->pd)); + roce_set_field(qpc_mask->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M, V2_QPC_BYTE_16_PD_S, 0); roce_set_field(context->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M, - V2_QPC_BYTE_80_RX_CQN_S, to_hr_cq(ibqp->recv_cq)->cqn); + V2_QPC_BYTE_80_RX_CQN_S, get_cqn(ibqp->recv_cq)); roce_set_field(qpc_mask->byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_RX_CQN_M, V2_QPC_BYTE_80_RX_CQN_S, 0); roce_set_field(context->byte_252_err_txcqn, V2_QPC_BYTE_252_TX_CQN_M, - V2_QPC_BYTE_252_TX_CQN_S, to_hr_cq(ibqp->send_cq)->cqn); + V2_QPC_BYTE_252_TX_CQN_S, get_cqn(ibqp->send_cq)); roce_set_field(qpc_mask->byte_252_err_txcqn, V2_QPC_BYTE_252_TX_CQN_M, V2_QPC_BYTE_252_TX_CQN_S, 0); @@ -4685,7 +4709,6 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp, V2_QPC_BYTE_244_RNR_CNT_S, 0); } - /* RC&UC&UD required attr */ if (attr_mask & IB_QP_SQ_PSN) { roce_set_field(context->byte_172_sq_psn, V2_QPC_BYTE_172_SQ_CUR_PSN_M, @@ -4763,7 +4786,6 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp, V2_QPC_BYTE_80_MIN_RNR_TIME_S, 0); } - /* RC&UC required attr */ if (attr_mask & IB_QP_RQ_PSN) { roce_set_field(context->byte_108_rx_reqepsn, V2_QPC_BYTE_108_RX_REQ_EPSN_M, @@ -4806,6 +4828,29 @@ static void hns_roce_v2_record_opt_fields(struct ib_qp *ibqp, } } +static void clear_qp(struct hns_roce_qp *hr_qp) +{ + struct ib_qp *ibqp = &hr_qp->ibqp; + + if (ibqp->send_cq) + hns_roce_v2_cq_clean(to_hr_cq(ibqp->send_cq), + hr_qp->qpn, NULL); + + if (ibqp->recv_cq && ibqp->recv_cq != ibqp->send_cq) + hns_roce_v2_cq_clean(to_hr_cq(ibqp->recv_cq), + hr_qp->qpn, ibqp->srq ? + to_hr_srq(ibqp->srq) : NULL); + + if (hr_qp->rq.wqe_cnt) + *hr_qp->rdb.db_record = 0; + + hr_qp->rq.head = 0; + hr_qp->rq.tail = 0; + hr_qp->sq.head = 0; + hr_qp->sq.tail = 0; + hr_qp->next_sge = 0; +} + static int hns_roce_v2_modify_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, int attr_mask, enum ib_qp_state cur_state, @@ -4840,19 +4885,23 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp, /* When QP state is err, SQ and RQ WQE should be flushed */ if (new_state == IB_QPS_ERR) { - spin_lock_irqsave(&hr_qp->sq.lock, sq_flag); - hr_qp->state = IB_QPS_ERR; - roce_set_field(context->byte_160_sq_ci_pi, - V2_QPC_BYTE_160_SQ_PRODUCER_IDX_M, - V2_QPC_BYTE_160_SQ_PRODUCER_IDX_S, - hr_qp->sq.head); - roce_set_field(qpc_mask->byte_160_sq_ci_pi, - V2_QPC_BYTE_160_SQ_PRODUCER_IDX_M, - V2_QPC_BYTE_160_SQ_PRODUCER_IDX_S, 0); - spin_unlock_irqrestore(&hr_qp->sq.lock, sq_flag); - - if (!ibqp->srq) { + if (ibqp->qp_type != IB_QPT_XRC_TGT) { + spin_lock_irqsave(&hr_qp->sq.lock, sq_flag); + hr_qp->state = IB_QPS_ERR; + roce_set_field(context->byte_160_sq_ci_pi, + V2_QPC_BYTE_160_SQ_PRODUCER_IDX_M, + V2_QPC_BYTE_160_SQ_PRODUCER_IDX_S, + hr_qp->sq.head); + roce_set_field(qpc_mask->byte_160_sq_ci_pi, + V2_QPC_BYTE_160_SQ_PRODUCER_IDX_M, + V2_QPC_BYTE_160_SQ_PRODUCER_IDX_S, 0); + spin_unlock_irqrestore(&hr_qp->sq.lock, sq_flag); + } + + if (!ibqp->srq && ibqp->qp_type != IB_QPT_XRC_INI && + ibqp->qp_type != IB_QPT_XRC_TGT) { spin_lock_irqsave(&hr_qp->rq.lock, rq_flag); + hr_qp->state = IB_QPS_ERR; roce_set_field(context->byte_84_rq_ci_pi, V2_QPC_BYTE_84_RQ_PRODUCER_IDX_M, V2_QPC_BYTE_84_RQ_PRODUCER_IDX_S, @@ -4871,7 +4920,8 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp, goto out; roce_set_bit(context->byte_108_rx_reqepsn, V2_QPC_BYTE_108_INV_CREDIT_S, - ibqp->srq ? 1 : 0); + ((to_hr_qp_type(hr_qp->ibqp.qp_type) == SERV_TYPE_XRC) || + ibqp->srq) ? 1 : 0); roce_set_bit(qpc_mask->byte_108_rx_reqepsn, V2_QPC_BYTE_108_INV_CREDIT_S, 0); @@ -4892,21 +4942,8 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp, hns_roce_v2_record_opt_fields(ibqp, attr, attr_mask); - if (new_state == IB_QPS_RESET && !ibqp->uobject) { - hns_roce_v2_cq_clean(to_hr_cq(ibqp->recv_cq), hr_qp->qpn, - ibqp->srq ? to_hr_srq(ibqp->srq) : NULL); - if (ibqp->send_cq != ibqp->recv_cq) - hns_roce_v2_cq_clean(to_hr_cq(ibqp->send_cq), - hr_qp->qpn, NULL); - - hr_qp->rq.head = 0; - hr_qp->rq.tail = 0; - hr_qp->sq.head = 0; - hr_qp->sq.tail = 0; - hr_qp->next_sge = 0; - if (hr_qp->rq.wqe_cnt) - *hr_qp->rdb.db_record = 0; - } + if (new_state == IB_QPS_RESET && !ibqp->uobject) + clear_qp(hr_qp); out: return ret; @@ -5017,7 +5054,9 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, V2_QPC_BYTE_76_ATE_S)) << V2_QP_ATE_S); if (hr_qp->ibqp.qp_type == IB_QPT_RC || - hr_qp->ibqp.qp_type == IB_QPT_UC) { + hr_qp->ibqp.qp_type == IB_QPT_UC || + hr_qp->ibqp.qp_type == IB_QPT_XRC_INI || + hr_qp->ibqp.qp_type == IB_QPT_XRC_TGT) { struct ib_global_route *grh = rdma_ah_retrieve_grh(&qp_attr->ah_attr); @@ -5049,6 +5088,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->max_dest_rd_atomic = 1 << roce_get_field(context.byte_140_raq, V2_QPC_BYTE_140_RR_MAX_M, V2_QPC_BYTE_140_RR_MAX_S); + qp_attr->min_rnr_timer = (u8)roce_get_field(context.byte_80_rnr_rx_cqn, V2_QPC_BYTE_80_MIN_RNR_TIME_M, V2_QPC_BYTE_80_MIN_RNR_TIME_S); @@ -5083,6 +5123,15 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, return ret; } +static inline int modify_qp_is_ok(struct hns_roce_qp *hr_qp) +{ + return ((hr_qp->ibqp.qp_type == IB_QPT_RC || + hr_qp->ibqp.qp_type == IB_QPT_UD || + hr_qp->ibqp.qp_type == IB_QPT_XRC_INI || + hr_qp->ibqp.qp_type == IB_QPT_XRC_TGT) && + hr_qp->state != IB_QPS_RESET); +} + static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, struct ib_udata *udata) @@ -5092,9 +5141,7 @@ static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev, unsigned long flags; int ret = 0; - if ((hr_qp->ibqp.qp_type == IB_QPT_RC || - hr_qp->ibqp.qp_type == IB_QPT_UD) && - hr_qp->state != IB_QPS_RESET) { + if (modify_qp_is_ok(hr_qp)) { /* Modify qp to reset before destroying qp */ ret = hns_roce_v2_modify_qp(&hr_qp->ibqp, NULL, 0, hr_qp->state, IB_QPS_RESET); @@ -5275,7 +5322,7 @@ static int hns_roce_v2_write_srqc(struct hns_roce_srq *srq, void *mb_buf) hr_reg_write(ctx, SRQC_SRQ_ST, 1); hr_reg_write(ctx, SRQC_PD, to_hr_pd(srq->ibsrq.pd)->pdn); hr_reg_write(ctx, SRQC_SRQN, srq->srqn); - hr_reg_write(ctx, SRQC_XRCD, 0); + hr_reg_write(ctx, SRQC_XRCD, srq->xrcdn); hr_reg_write(ctx, SRQC_XRC_CQN, srq->cqn); hr_reg_write(ctx, SRQC_SHIFT, ilog2(srq->wqe_cnt)); hr_reg_write(ctx, SRQC_RQWS, @@ -5479,6 +5526,12 @@ static void hns_roce_irq_work_handle(struct work_struct *work) case HNS_ROCE_EVENT_TYPE_FLR: ibdev_warn(ibdev, "Function level reset.\n"); break; + case HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION: + ibdev_err(ibdev, "xrc domain violation error.\n"); + break; + case HNS_ROCE_EVENT_TYPE_INVALID_XRCETH: + ibdev_err(ibdev, "invalid xrceth error.\n"); + break; default: break; } @@ -5579,6 +5632,8 @@ static int hns_roce_v2_aeq_int(struct hns_roce_dev *hr_dev, case HNS_ROCE_EVENT_TYPE_SRQ_LAST_WQE_REACH: case HNS_ROCE_EVENT_TYPE_INV_REQ_LOCAL_WQ_ERROR: case HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR: + case HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION: + case HNS_ROCE_EVENT_TYPE_INVALID_XRCETH: hns_roce_qp_event(hr_dev, queue_num, event_type); break; case HNS_ROCE_EVENT_TYPE_SRQ_LIMIT_REACH: diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 39621fb..ffdae15 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -74,6 +74,8 @@ #define HNS_ROCE_V2_MAX_SRQWQE_SEGS 0x1000000 #define HNS_ROCE_V2_MAX_IDX_SEGS 0x1000000 #define HNS_ROCE_V2_MAX_PD_NUM 0x1000000 +#define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 +#define HNS_ROCE_V2_RSV_XRCD_NUM 0 #define HNS_ROCE_V2_MAX_QP_INIT_RDMA 128 #define HNS_ROCE_V2_MAX_QP_DEST_RDMA 128 #define HNS_ROCE_V2_MAX_SQ_DESC_SZ 64 diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index c9c0836..1a747f7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -207,6 +207,9 @@ static int hns_roce_query_device(struct ib_device *ib_dev, props->max_fast_reg_page_list_len = HNS_ROCE_FRMR_MAX_PA; } + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC) + props->device_cap_flags |= IB_DEVICE_XRC; + return 0; } @@ -300,6 +303,7 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx, return -EAGAIN; resp.qp_tab_size = hr_dev->caps.num_qps; + resp.srq_tab_size = hr_dev->caps.num_srqs; ret = hns_roce_uar_alloc(hr_dev, &context->uar); if (ret) @@ -461,6 +465,13 @@ static const struct ib_device_ops hns_roce_dev_srq_ops = { INIT_RDMA_OBJ_SIZE(ib_srq, hns_roce_srq, ibsrq), }; +static const struct ib_device_ops hns_roce_dev_xrcd_ops = { + .alloc_xrcd = hns_roce_alloc_xrcd, + .dealloc_xrcd = hns_roce_dealloc_xrcd, + + INIT_RDMA_OBJ_SIZE(ib_xrcd, hns_roce_xrcd, ibxrcd), +}; + static int hns_roce_register_device(struct hns_roce_dev *hr_dev) { int ret; @@ -484,20 +495,20 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev) if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_REREG_MR) ib_set_device_ops(ib_dev, &hns_roce_dev_mr_ops); - /* MW */ if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_MW) ib_set_device_ops(ib_dev, &hns_roce_dev_mw_ops); - /* FRMR */ if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_FRMR) ib_set_device_ops(ib_dev, &hns_roce_dev_frmr_ops); - /* SRQ */ if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ) { ib_set_device_ops(ib_dev, &hns_roce_dev_srq_ops); ib_set_device_ops(ib_dev, hr_dev->hw->hns_roce_dev_srq_ops); } + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC) + ib_set_device_ops(ib_dev, &hns_roce_dev_xrcd_ops); + ib_set_device_ops(ib_dev, hr_dev->hw->hns_roce_dev_ops); ib_set_device_ops(ib_dev, &hns_roce_dev_ops); for (i = 0; i < hr_dev->caps.num_ports; i++) { @@ -727,10 +738,19 @@ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev) goto err_uar_alloc_free; } + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC) { + ret = hns_roce_init_xrcd_table(hr_dev); + if (ret) { + dev_err(dev, "failed to init xrcd table, ret = %d.\n", + ret); + goto err_pd_table_free; + } + } + ret = hns_roce_init_mr_table(hr_dev); if (ret) { dev_err(dev, "Failed to init memory region table.\n"); - goto err_pd_table_free; + goto err_xrcd_table_free; } hns_roce_init_cq_table(hr_dev); @@ -759,6 +779,10 @@ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev) hns_roce_cleanup_cq_table(hr_dev); hns_roce_cleanup_mr_table(hr_dev); +err_xrcd_table_free: + if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC) + hns_roce_cleanup_xrcd_table(hr_dev); + err_pd_table_free: hns_roce_cleanup_pd_table(hr_dev); diff --git a/drivers/infiniband/hw/hns/hns_roce_pd.c b/drivers/infiniband/hw/hns/hns_roce_pd.c index cca818d..9dbd21a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_pd.c +++ b/drivers/infiniband/hw/hns/hns_roce_pd.c @@ -137,3 +137,54 @@ void hns_roce_cleanup_uar_table(struct hns_roce_dev *hr_dev) { hns_roce_bitmap_cleanup(&hr_dev->uar_table.bitmap); } + +static int hns_roce_xrcd_alloc(struct hns_roce_dev *hr_dev, + unsigned long *xrcdn) +{ + return hns_roce_bitmap_alloc(&hr_dev->xrcd_bitmap, xrcdn); +} + +static void hns_roce_xrcd_free(struct hns_roce_dev *hr_dev, + unsigned long xrcdn) +{ + hns_roce_bitmap_free(&hr_dev->xrcd_bitmap, xrcdn, BITMAP_NO_RR); +} + +int hns_roce_init_xrcd_table(struct hns_roce_dev *hr_dev) +{ + return hns_roce_bitmap_init(&hr_dev->xrcd_bitmap, + hr_dev->caps.num_xrcds, + hr_dev->caps.num_xrcds - 1, + hr_dev->caps.reserved_xrcds, 0); +} + +void hns_roce_cleanup_xrcd_table(struct hns_roce_dev *hr_dev) +{ + hns_roce_bitmap_cleanup(&hr_dev->xrcd_bitmap); +} + +int hns_roce_alloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ib_xrcd->device); + struct hns_roce_xrcd *xrcd = to_hr_xrcd(ib_xrcd); + int ret; + + if (!(hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)) + return -EINVAL; + + ret = hns_roce_xrcd_alloc(hr_dev, &xrcd->xrcdn); + if (ret) { + dev_err(hr_dev->dev, "failed to alloc xrcdn, ret = %d.\n", ret); + return ret; + } + + return 0; +} + +int hns_roce_dealloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata) +{ + hns_roce_xrcd_free(to_hr_dev(ib_xrcd->device), + to_hr_xrcd(ib_xrcd)->xrcdn); + + return 0; +} diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 004aca9..9169225 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -98,7 +98,9 @@ void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type) if (hr_dev->hw_rev != HNS_ROCE_HW_VER1 && (event_type == HNS_ROCE_EVENT_TYPE_WQ_CATAS_ERROR || event_type == HNS_ROCE_EVENT_TYPE_INV_REQ_LOCAL_WQ_ERROR || - event_type == HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR)) { + event_type == HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR || + event_type == HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION || + event_type == HNS_ROCE_EVENT_TYPE_INVALID_XRCETH)) { qp->state = IB_QPS_ERR; if (!test_and_set_bit(HNS_ROCE_FLUSH_FLAG, &qp->flush_flag)) init_flush_work(hr_dev, qp); @@ -142,6 +144,8 @@ static void hns_roce_ib_qp_event(struct hns_roce_qp *hr_qp, event.event = IB_EVENT_QP_REQ_ERR; break; case HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR: + case HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION: + case HNS_ROCE_EVENT_TYPE_INVALID_XRCETH: event.event = IB_EVENT_QP_ACCESS_ERR; break; default: @@ -366,8 +370,13 @@ void hns_roce_qp_remove(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) unsigned long flags; list_del(&hr_qp->node); - list_del(&hr_qp->sq_node); - list_del(&hr_qp->rq_node); + + if (hr_qp->ibqp.qp_type != IB_QPT_XRC_TGT) + list_del(&hr_qp->sq_node); + + if (hr_qp->ibqp.qp_type != IB_QPT_XRC_INI && + hr_qp->ibqp.qp_type != IB_QPT_XRC_TGT) + list_del(&hr_qp->rq_node); xa_lock_irqsave(xa, flags); __xa_erase(xa, hr_qp->qpn & (hr_dev->caps.num_qps - 1)); @@ -1100,11 +1109,16 @@ static int check_qp_type(struct hns_roce_dev *hr_dev, enum ib_qp_type type, bool is_user) { switch (type) { + case IB_QPT_XRC_INI: + case IB_QPT_XRC_TGT: + if (!(hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)) + goto out; + break; case IB_QPT_UD: if (hr_dev->pci_dev->revision <= PCI_REVISION_ID_HIP08 && is_user) goto out; - fallthrough; + break; case IB_QPT_RC: case IB_QPT_GSI: break; @@ -1124,8 +1138,8 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr, struct ib_udata *udata) { - struct hns_roce_dev *hr_dev = to_hr_dev(pd->device); - struct ib_device *ibdev = &hr_dev->ib_dev; + struct ib_device *ibdev = pd ? pd->device : init_attr->xrcd->device; + struct hns_roce_dev *hr_dev = to_hr_dev(ibdev); struct hns_roce_qp *hr_qp; int ret; @@ -1137,6 +1151,15 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd, if (!hr_qp) return ERR_PTR(-ENOMEM); + if (init_attr->qp_type == IB_QPT_XRC_INI) + init_attr->recv_cq = NULL; + + if (init_attr->qp_type == IB_QPT_XRC_TGT) { + hr_qp->xrcdn = to_hr_xrcd(init_attr->xrcd)->xrcdn; + init_attr->recv_cq = NULL; + init_attr->send_cq = NULL; + } + if (init_attr->qp_type == IB_QPT_GSI) { hr_qp->port = init_attr->port_num - 1; hr_qp->phy_port = hr_dev->iboe.phy_port[hr_qp->port]; @@ -1156,20 +1179,20 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd, int to_hr_qp_type(int qp_type) { - int transport_type; - - if (qp_type == IB_QPT_RC) - transport_type = SERV_TYPE_RC; - else if (qp_type == IB_QPT_UC) - transport_type = SERV_TYPE_UC; - else if (qp_type == IB_QPT_UD) - transport_type = SERV_TYPE_UD; - else if (qp_type == IB_QPT_GSI) - transport_type = SERV_TYPE_UD; - else - transport_type = -1; - - return transport_type; + switch (qp_type) { + case IB_QPT_RC: + return SERV_TYPE_RC; + case IB_QPT_UC: + return SERV_TYPE_UC; + case IB_QPT_UD: + case IB_QPT_GSI: + return SERV_TYPE_UD; + case IB_QPT_XRC_INI: + case IB_QPT_XRC_TGT: + return SERV_TYPE_XRC; + default: + return -1; + } } static int check_mtu_validate(struct hns_roce_dev *hr_dev, diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index d5a6de0..f71459a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -314,6 +314,9 @@ static void set_srq_ext_param(struct hns_roce_srq *srq, { srq->cqn = ib_srq_has_cq(init_attr->srq_type) ? to_hr_cq(init_attr->ext.cq)->cqn : 0; + + srq->xrcdn = (init_attr->srq_type == IB_SRQT_XRC) ? + to_hr_xrcd(init_attr->ext.xrc.xrcd)->xrcdn : 0; } static int set_srq_param(struct hns_roce_srq *srq, diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index 90b739d..42b1776 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -86,6 +86,8 @@ struct hns_roce_ib_create_qp_resp { struct hns_roce_ib_alloc_ucontext_resp { __u32 qp_tab_size; __u32 cqe_size; + __u32 srq_tab_size; + __u32 reserved; }; struct hns_roce_ib_alloc_pd_resp { -- 2.8.1

3 2

[PATCH rdma-core 0/5] libhns: Support XRC on HIP09
by Weihang Li 02 Mar '21

02 Mar '21

The HIP09 supports XRC transport service, it greatly saves the number of QPs required to connect all processes in a large cluster. This series first adds support of ibv_create_qp/srq_ex which are necessary interfaces for XRC, fixes an issue about CQ locks that is also required, then XRC is fully supported at last. Lang Cheng (1): libhns: Support ibv_create_qp_ex Weihang Li (2): Update kernel headers libhns: Avoid accessing NULL pointer when locking/unlocking CQ Wenpeng Liang (2): libhns: Support ibv_create_srq_ex libhns: Add support for XRC for HIP09 kernel-headers/rdma/hns-abi.h | 2 + providers/hns/hns_roce_u.c | 28 ++- providers/hns/hns_roce_u.h | 40 +++- providers/hns/hns_roce_u_abi.h | 11 +- providers/hns/hns_roce_u_hw_v1.c | 18 +- providers/hns/hns_roce_u_hw_v2.c | 159 +++++++++----- providers/hns/hns_roce_u_hw_v2.h | 1 + providers/hns/hns_roce_u_verbs.c | 455 +++++++++++++++++++++++++++++++-------- 8 files changed, 546 insertions(+), 168 deletions(-) -- 2.8.1

1 5

[PATCH v4] sched/topology: fix the issue groups don't span domain->span for NUMA diameter > 2
by Barry Song 02 Mar '21

02 Mar '21

As long as NUMA diameter > 2, building sched_domain by sibling's child domain will definitely create a sched_domain with sched_group which will span out of the sched_domain: +------+ +------+ +-------+ +------+ | node | 12 |node | 20 | node | 12 |node | | 0 +---------+1 +--------+ 2 +-------+3 | +------+ +------+ +-------+ +------+ domain0 node0 node1 node2 node3 domain1 node0+1 node0+1 node2+3 node2+3 + domain2 node0+1+2 | group: node0+1 | group:node2+3 <-------------------+ when node2 is added into the domain2 of node0, kernel is using the child domain of node2's domain2, which is domain1(node2+3). Node 3 is outside the span of the domain including node0+1+2. This will make load_balance() run based on screwed avg_load and group_type in the sched_group spanning out of the sched_domain, and it also makes select_task_rq_fair() pick an idle CPU outside the sched_domain. Real servers which suffer from this problem include Kunpeng920 and 8-node Sun Fire X4600-M2, at least. Here we move to use the *child* domain of the *child* domain of node2's domain2 as the new added sched_group. At the same, we re-use the lower level sgc directly. +------+ +------+ +-------+ +------+ | node | 12 |node | 20 | node | 12 |node | | 0 +---------+1 +--------+ 2 +-------+3 | +------+ +------+ +-------+ +------+ domain0 node0 node1 +- node2 node3 | domain1 node0+1 node0+1 | node2+3 node2+3 | domain2 node0+1+2 | group: node0+1 | group:node2 <-------------------+ While the lower level sgc is re-used, this patch only changes the remote sched_groups for those sched_domains playing grandchild trick, therefore, sgc->next_update is still safe since it's only touched by CPUs that have the group span as local group. And sgc->imbalance is also safe because sd_parent remains the same in load_balance and LB only tries other CPUs from the local group. Moreover, since local groups are not touched, they are still getting roughly equal size in a TL. And should_we_balance() only matters with local groups, so the pull probability of those groups are still roughly equal. Tested by the below topology: qemu-system-aarch64 -M virt -nographic \ -smp cpus=8 \ -numa node,cpus=0-1,nodeid=0 \ -numa node,cpus=2-3,nodeid=1 \ -numa node,cpus=4-5,nodeid=2 \ -numa node,cpus=6-7,nodeid=3 \ -numa dist,src=0,dst=1,val=12 \ -numa dist,src=0,dst=2,val=20 \ -numa dist,src=0,dst=3,val=22 \ -numa dist,src=1,dst=2,val=22 \ -numa dist,src=2,dst=3,val=12 \ -numa dist,src=1,dst=3,val=24 \ -m 4G -cpu cortex-a57 -kernel arch/arm64/boot/Image w/o patch, we get lots of "groups don't span domain->span": [ 0.802139] CPU0 attaching sched-domain(s): [ 0.802193] domain-0: span=0-1 level=MC [ 0.802443] groups: 0:{ span=0 cap=1013 }, 1:{ span=1 cap=979 } [ 0.802693] domain-1: span=0-3 level=NUMA [ 0.802731] groups: 0:{ span=0-1 cap=1992 }, 2:{ span=2-3 cap=1943 } [ 0.802811] domain-2: span=0-5 level=NUMA [ 0.802829] groups: 0:{ span=0-3 cap=3935 }, 4:{ span=4-7 cap=3937 } [ 0.802881] ERROR: groups don't span domain->span [ 0.803058] domain-3: span=0-7 level=NUMA [ 0.803080] groups: 0:{ span=0-5 mask=0-1 cap=5843 }, 6:{ span=4-7 mask=6-7 cap=4077 } [ 0.804055] CPU1 attaching sched-domain(s): [ 0.804072] domain-0: span=0-1 level=MC [ 0.804096] groups: 1:{ span=1 cap=979 }, 0:{ span=0 cap=1013 } [ 0.804152] domain-1: span=0-3 level=NUMA [ 0.804170] groups: 0:{ span=0-1 cap=1992 }, 2:{ span=2-3 cap=1943 } [ 0.804219] domain-2: span=0-5 level=NUMA [ 0.804236] groups: 0:{ span=0-3 cap=3935 }, 4:{ span=4-7 cap=3937 } [ 0.804302] ERROR: groups don't span domain->span [ 0.804520] domain-3: span=0-7 level=NUMA [ 0.804546] groups: 0:{ span=0-5 mask=0-1 cap=5843 }, 6:{ span=4-7 mask=6-7 cap=4077 } [ 0.804677] CPU2 attaching sched-domain(s): [ 0.804687] domain-0: span=2-3 level=MC [ 0.804705] groups: 2:{ span=2 cap=934 }, 3:{ span=3 cap=1009 } [ 0.804754] domain-1: span=0-3 level=NUMA [ 0.804772] groups: 2:{ span=2-3 cap=1943 }, 0:{ span=0-1 cap=1992 } [ 0.804820] domain-2: span=0-5 level=NUMA [ 0.804836] groups: 2:{ span=0-3 mask=2-3 cap=3991 }, 4:{ span=0-1,4-7 mask=4-5 cap=5985 } [ 0.804944] ERROR: groups don't span domain->span [ 0.805108] domain-3: span=0-7 level=NUMA [ 0.805134] groups: 2:{ span=0-5 mask=2-3 cap=5899 }, 6:{ span=0-1,4-7 mask=6-7 cap=6125 } [ 0.805223] CPU3 attaching sched-domain(s): [ 0.805232] domain-0: span=2-3 level=MC [ 0.805249] groups: 3:{ span=3 cap=1009 }, 2:{ span=2 cap=934 } [ 0.805319] domain-1: span=0-3 level=NUMA [ 0.805336] groups: 2:{ span=2-3 cap=1943 }, 0:{ span=0-1 cap=1992 } [ 0.805383] domain-2: span=0-5 level=NUMA [ 0.805399] groups: 2:{ span=0-3 mask=2-3 cap=3991 }, 4:{ span=0-1,4-7 mask=4-5 cap=5985 } [ 0.805458] ERROR: groups don't span domain->span [ 0.805605] domain-3: span=0-7 level=NUMA [ 0.805626] groups: 2:{ span=0-5 mask=2-3 cap=5899 }, 6:{ span=0-1,4-7 mask=6-7 cap=6125 } [ 0.805712] CPU4 attaching sched-domain(s): [ 0.805721] domain-0: span=4-5 level=MC [ 0.805738] groups: 4:{ span=4 cap=984 }, 5:{ span=5 cap=924 } [ 0.805787] domain-1: span=4-7 level=NUMA [ 0.805803] groups: 4:{ span=4-5 cap=1908 }, 6:{ span=6-7 cap=2029 } [ 0.805851] domain-2: span=0-1,4-7 level=NUMA [ 0.805867] groups: 4:{ span=4-7 cap=3937 }, 0:{ span=0-3 cap=3935 } [ 0.805915] ERROR: groups don't span domain->span [ 0.806108] domain-3: span=0-7 level=NUMA [ 0.806130] groups: 4:{ span=0-1,4-7 mask=4-5 cap=5985 }, 2:{ span=0-3 mask=2-3 cap=3991 } [ 0.806214] CPU5 attaching sched-domain(s): [ 0.806222] domain-0: span=4-5 level=MC [ 0.806240] groups: 5:{ span=5 cap=924 }, 4:{ span=4 cap=984 } [ 0.806841] domain-1: span=4-7 level=NUMA [ 0.806866] groups: 4:{ span=4-5 cap=1908 }, 6:{ span=6-7 cap=2029 } [ 0.806934] domain-2: span=0-1,4-7 level=NUMA [ 0.806953] groups: 4:{ span=4-7 cap=3937 }, 0:{ span=0-3 cap=3935 } [ 0.807004] ERROR: groups don't span domain->span [ 0.807312] domain-3: span=0-7 level=NUMA [ 0.807386] groups: 4:{ span=0-1,4-7 mask=4-5 cap=5985 }, 2:{ span=0-3 mask=2-3 cap=3991 } [ 0.807686] CPU6 attaching sched-domain(s): [ 0.807710] domain-0: span=6-7 level=MC [ 0.807750] groups: 6:{ span=6 cap=1017 }, 7:{ span=7 cap=1012 } [ 0.807840] domain-1: span=4-7 level=NUMA [ 0.807870] groups: 6:{ span=6-7 cap=2029 }, 4:{ span=4-5 cap=1908 } [ 0.807952] domain-2: span=0-1,4-7 level=NUMA [ 0.807985] groups: 6:{ span=4-7 mask=6-7 cap=4077 }, 0:{ span=0-5 mask=0-1 cap=5843 } [ 0.808045] ERROR: groups don't span domain->span [ 0.808257] domain-3: span=0-7 level=NUMA [ 0.808571] groups: 6:{ span=0-1,4-7 mask=6-7 cap=6125 }, 2:{ span=0-5 mask=2-3 cap=5899 } [ 0.808848] CPU7 attaching sched-domain(s): [ 0.808860] domain-0: span=6-7 level=MC [ 0.808880] groups: 7:{ span=7 cap=1012 }, 6:{ span=6 cap=1017 } [ 0.808953] domain-1: span=4-7 level=NUMA [ 0.808974] groups: 6:{ span=6-7 cap=2029 }, 4:{ span=4-5 cap=1908 } [ 0.809034] domain-2: span=0-1,4-7 level=NUMA [ 0.809055] groups: 6:{ span=4-7 mask=6-7 cap=4077 }, 0:{ span=0-5 mask=0-1 cap=5843 } [ 0.809128] ERROR: groups don't span domain->span [ 0.810361] domain-3: span=0-7 level=NUMA [ 0.810400] groups: 6:{ span=0-1,4-7 mask=6-7 cap=5961 }, 2:{ span=0-5 mask=2-3 cap=5903 } w/ patch, we don't get "groups don't span domain->span" any more: [ 1.486271] CPU0 attaching sched-domain(s): [ 1.486820] domain-0: span=0-1 level=MC [ 1.500924] groups: 0:{ span=0 cap=980 }, 1:{ span=1 cap=994 } [ 1.515717] domain-1: span=0-3 level=NUMA [ 1.515903] groups: 0:{ span=0-1 cap=1974 }, 2:{ span=2-3 cap=1989 } [ 1.516989] domain-2: span=0-5 level=NUMA [ 1.517124] groups: 0:{ span=0-3 cap=3963 }, 4:{ span=4-5 cap=1949 } [ 1.517369] domain-3: span=0-7 level=NUMA [ 1.517423] groups: 0:{ span=0-5 mask=0-1 cap=5912 }, 6:{ span=4-7 mask=6-7 cap=4054 } [ 1.520027] CPU1 attaching sched-domain(s): [ 1.520097] domain-0: span=0-1 level=MC [ 1.520184] groups: 1:{ span=1 cap=994 }, 0:{ span=0 cap=980 } [ 1.520429] domain-1: span=0-3 level=NUMA [ 1.520487] groups: 0:{ span=0-1 cap=1974 }, 2:{ span=2-3 cap=1989 } [ 1.520687] domain-2: span=0-5 level=NUMA [ 1.520744] groups: 0:{ span=0-3 cap=3963 }, 4:{ span=4-5 cap=1949 } [ 1.520948] domain-3: span=0-7 level=NUMA [ 1.521038] groups: 0:{ span=0-5 mask=0-1 cap=5912 }, 6:{ span=4-7 mask=6-7 cap=4054 } [ 1.522068] CPU2 attaching sched-domain(s): [ 1.522348] domain-0: span=2-3 level=MC [ 1.522606] groups: 2:{ span=2 cap=1003 }, 3:{ span=3 cap=986 } [ 1.522832] domain-1: span=0-3 level=NUMA [ 1.522885] groups: 2:{ span=2-3 cap=1989 }, 0:{ span=0-1 cap=1974 } [ 1.523043] domain-2: span=0-5 level=NUMA [ 1.523092] groups: 2:{ span=0-3 mask=2-3 cap=4037 }, 4:{ span=4-5 cap=1949 } [ 1.523302] domain-3: span=0-7 level=NUMA [ 1.523352] groups: 2:{ span=0-5 mask=2-3 cap=5986 }, 6:{ span=0-1,4-7 mask=6-7 cap=6102 } [ 1.523748] CPU3 attaching sched-domain(s): [ 1.523774] domain-0: span=2-3 level=MC [ 1.523825] groups: 3:{ span=3 cap=986 }, 2:{ span=2 cap=1003 } [ 1.524009] domain-1: span=0-3 level=NUMA [ 1.524086] groups: 2:{ span=2-3 cap=1989 }, 0:{ span=0-1 cap=1974 } [ 1.524281] domain-2: span=0-5 level=NUMA [ 1.524331] groups: 2:{ span=0-3 mask=2-3 cap=4037 }, 4:{ span=4-5 cap=1949 } [ 1.524534] domain-3: span=0-7 level=NUMA [ 1.524586] groups: 2:{ span=0-5 mask=2-3 cap=5986 }, 6:{ span=0-1,4-7 mask=6-7 cap=6102 } [ 1.524847] CPU4 attaching sched-domain(s): [ 1.524873] domain-0: span=4-5 level=MC [ 1.524954] groups: 4:{ span=4 cap=958 }, 5:{ span=5 cap=991 } [ 1.525105] domain-1: span=4-7 level=NUMA [ 1.525153] groups: 4:{ span=4-5 cap=1949 }, 6:{ span=6-7 cap=2006 } [ 1.525368] domain-2: span=0-1,4-7 level=NUMA [ 1.525428] groups: 4:{ span=4-7 cap=3955 }, 0:{ span=0-1 cap=1974 } [ 1.532726] domain-3: span=0-7 level=NUMA [ 1.532811] groups: 4:{ span=0-1,4-7 mask=4-5 cap=6003 }, 2:{ span=0-3 mask=2-3 cap=4037 } [ 1.534125] CPU5 attaching sched-domain(s): [ 1.534159] domain-0: span=4-5 level=MC [ 1.534303] groups: 5:{ span=5 cap=991 }, 4:{ span=4 cap=958 } [ 1.534490] domain-1: span=4-7 level=NUMA [ 1.534572] groups: 4:{ span=4-5 cap=1949 }, 6:{ span=6-7 cap=2006 } [ 1.534734] domain-2: span=0-1,4-7 level=NUMA [ 1.534783] groups: 4:{ span=4-7 cap=3955 }, 0:{ span=0-1 cap=1974 } [ 1.536057] domain-3: span=0-7 level=NUMA [ 1.536430] groups: 4:{ span=0-1,4-7 mask=4-5 cap=6003 }, 2:{ span=0-3 mask=2-3 cap=3896 } [ 1.536815] CPU6 attaching sched-domain(s): [ 1.536846] domain-0: span=6-7 level=MC [ 1.536934] groups: 6:{ span=6 cap=1005 }, 7:{ span=7 cap=1001 } [ 1.537144] domain-1: span=4-7 level=NUMA [ 1.537262] groups: 6:{ span=6-7 cap=2006 }, 4:{ span=4-5 cap=1949 } [ 1.537553] domain-2: span=0-1,4-7 level=NUMA [ 1.537613] groups: 6:{ span=4-7 mask=6-7 cap=4054 }, 0:{ span=0-1 cap=1805 } [ 1.537872] domain-3: span=0-7 level=NUMA [ 1.537998] groups: 6:{ span=0-1,4-7 mask=6-7 cap=6102 }, 2:{ span=0-5 mask=2-3 cap=5845 } [ 1.538448] CPU7 attaching sched-domain(s): [ 1.538505] domain-0: span=6-7 level=MC [ 1.538586] groups: 7:{ span=7 cap=1001 }, 6:{ span=6 cap=1005 } [ 1.538746] domain-1: span=4-7 level=NUMA [ 1.538798] groups: 6:{ span=6-7 cap=2006 }, 4:{ span=4-5 cap=1949 } [ 1.539048] domain-2: span=0-1,4-7 level=NUMA [ 1.539111] groups: 6:{ span=4-7 mask=6-7 cap=4054 }, 0:{ span=0-1 cap=1805 } [ 1.539571] domain-3: span=0-7 level=NUMA [ 1.539610] groups: 6:{ span=0-1,4-7 mask=6-7 cap=6102 }, 2:{ span=0-5 mask=2-3 cap=5845 } Reported-by: Valentin Schneider <valentin.schneider(a)arm.com> Tested-by: Meelis Roos <mroos(a)linux.ee> Reviewed-by: Valentin Schneider <valentin.schneider(a)arm.com> Signed-off-by: Barry Song <song.bao.hua(a)hisilicon.com> --- -v4: no code changed; mainly rewrote changelog: * add Reviewed-by of Valentin; While the grandchild approach was started by me, Valentin contributed the most useful edit; * add description about sgc->imbalance and next_update according to the comment of Vincent; * add description about the equal size of local group to address Peter's comment kernel/sched/topology.c | 91 +++++++++++++++++++++++++++-------------- 1 file changed, 61 insertions(+), 30 deletions(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 09d35044bd88..12f80587e127 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -723,35 +723,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) for (tmp = sd; tmp; tmp = tmp->parent) numa_distance += !!(tmp->flags & SD_NUMA); - /* - * FIXME: Diameter >=3 is misrepresented. - * - * Smallest diameter=3 topology is: - * - * node 0 1 2 3 - * 0: 10 20 30 40 - * 1: 20 10 20 30 - * 2: 30 20 10 20 - * 3: 40 30 20 10 - * - * 0 --- 1 --- 2 --- 3 - * - * NUMA-3 0-3 N/A N/A 0-3 - * groups: {0-2},{1-3} {1-3},{0-2} - * - * NUMA-2 0-2 0-3 0-3 1-3 - * groups: {0-1},{1-3} {0-2},{2-3} {1-3},{0-1} {2-3},{0-2} - * - * NUMA-1 0-1 0-2 1-3 2-3 - * groups: {0},{1} {1},{2},{0} {2},{3},{1} {3},{2} - * - * NUMA-0 0 1 2 3 - * - * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the - * group span isn't a subset of the domain span. - */ - WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n"); - sched_domain_debug(sd, cpu); rq_attach_root(rq, rd); @@ -982,6 +953,31 @@ static void init_overlap_sched_group(struct sched_domain *sd, sg->sgc->max_capacity = SCHED_CAPACITY_SCALE; } +static struct sched_domain * +find_descended_sibling(struct sched_domain *sd, struct sched_domain *sibling) +{ + /* + * The proper descendant would be the one whose child won't span out + * of sd + */ + while (sibling->child && + !cpumask_subset(sched_domain_span(sibling->child), + sched_domain_span(sd))) + sibling = sibling->child; + + /* + * As we are referencing sgc across different topology level, we need + * to go down to skip those sched_domains which don't contribute to + * scheduling because they will be degenerated in cpu_attach_domain + */ + while (sibling->child && + cpumask_equal(sched_domain_span(sibling->child), + sched_domain_span(sibling))) + sibling = sibling->child; + + return sibling; +} + static int build_overlap_sched_groups(struct sched_domain *sd, int cpu) { @@ -1015,6 +1011,41 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) if (!cpumask_test_cpu(i, sched_domain_span(sibling))) continue; + /* + * Usually we build sched_group by sibling's child sched_domain + * But for machines whose NUMA diameter are 3 or above, we move + * to build sched_group by sibling's proper descendant's child + * domain because sibling's child sched_domain will span out of + * the sched_domain being built as below. + * + * Smallest diameter=3 topology is: + * + * node 0 1 2 3 + * 0: 10 20 30 40 + * 1: 20 10 20 30 + * 2: 30 20 10 20 + * 3: 40 30 20 10 + * + * 0 --- 1 --- 2 --- 3 + * + * NUMA-3 0-3 N/A N/A 0-3 + * groups: {0-2},{1-3} {1-3},{0-2} + * + * NUMA-2 0-2 0-3 0-3 1-3 + * groups: {0-1},{1-3} {0-2},{2-3} {1-3},{0-1} {2-3},{0-2} + * + * NUMA-1 0-1 0-2 1-3 2-3 + * groups: {0},{1} {1},{2},{0} {2},{3},{1} {3},{2} + * + * NUMA-0 0 1 2 3 + * + * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the + * group span isn't a subset of the domain span. + */ + if (sibling->child && + !cpumask_subset(sched_domain_span(sibling->child), span)) + sibling = find_descended_sibling(sd, sibling); + sg = build_group_from_child_sched_domain(sibling, cpu); if (!sg) goto fail; @@ -1022,7 +1053,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) sg_span = sched_group_span(sg); cpumask_or(covered, covered, sg_span); - init_overlap_sched_group(sd, sg); + init_overlap_sched_group(sibling, sg); if (!first) first = sg; -- 2.25.1

2 1

[RFC net-next 0/9] net: hns3: refactor and new features for flow director
by Huazhong Tan 02 Mar '21

02 Mar '21

This patchset refactor some functions and add some new features for flow director. patch 1~3: refactor large functions patch 4, 7: add traffic class and user-def field support for ethtool patch 5: use asynchronously configuration patch 6: clean up for hns3_del_all_fd_entries() patch 8, 9: add support for queue bonding mode Jian Shen (9): net: hns3: refactor out hclge_add_fd_entry() net: hns3: refactor out hclge_fd_get_tuple() net: hns3: refactor for function hclge_fd_convert_tuple net: hns3: add support for traffic class tuple support for flow director by ethtool net: hns3: refactor flow director configuration net: hns3: refine for hns3_del_all_fd_entries() net: hns3: add support for user-def data of flow director net: hns3: add support for queue bonding mode of flow director net: hns3: add queue bonding mode support for VF drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h | 8 + drivers/net/ethernet/hisilicon/hns3/hnae3.h | 9 +- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 4 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 91 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 14 +- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 13 +- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 2 + .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 21 + .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 1564 ++++++++++++++------ .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 63 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 2 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 74 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 7 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 16 + 14 files changed, 1407 insertions(+), 481 deletions(-) -- 2.7.4

1 9

[PATCH V2 net] net: phy: fix save wrong speed and duplex problem if autoneg is on
by Huazhong Tan 02 Mar '21

02 Mar '21

From: Guangbin Huang <huangguangbin2(a)huawei.com> If phy uses generic driver and autoneg is on, enter command "ethtool -s eth0 speed 50" will not change phy speed actually, but command "ethtool eth0" shows speed is 50Mb/s because phydev->speed has been set to 50 and no update later. And duplex setting has same problem too. However, if autoneg is on, phy only changes speed and duplex according to phydev->advertising, but not phydev->speed and phydev->duplex. So in this case, phydev->speed and phydev->duplex don't need to be set in function phy_ethtool_ksettings_set() if autoneg is on. Fixes: 51e2a3846eab ("PHY: Avoid unnecessary aneg restarts") Signed-off-by: Guangbin Huang <huangguangbin2(a)huawei.com> Signed-off-by: Huazhong Tan <tanhuazhong(a)huawei.com> --- V1->V2: add a Fixes tag --- drivers/net/phy/phy.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 1be07e4..fc2e7cb 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -276,14 +276,16 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, phydev->autoneg = autoneg; - phydev->speed = speed; + if (autoneg == AUTONEG_DISABLE) { + phydev->speed = speed; + phydev->duplex = duplex; + } linkmode_copy(phydev->advertising, advertising); linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->advertising, autoneg == AUTONEG_ENABLE); - phydev->duplex = duplex; phydev->master_slave_set = cmd->base.master_slave_cfg; phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl; -- 2.7.4

2 1

[PATCH 5.4 178/340] perf vendor events arm64: Fix Ampere eMag event typo
by Greg Kroah-Hartman 02 Mar '21

02 Mar '21

From: John Garry <john.garry(a)huawei.com> [ Upstream commit 2bf797be81fa808f05f1a7a65916619132256a27 ] The "briefdescription" for event 0x35 has a typo - fix it. Fixes: d35c595bf005 ("perf vendor events arm64: Revise core JSON events for eMAG") Signed-off-by: John Garry <john.garry(a)huawei.com> Acked-by: Will Deacon <will(a)kernel.org> Cc: James Clark <james.clark(a)arm.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Nakamura, Shunsuke/中村俊介 <nakamura.shun(a)fujitsu.com> Cc: linux-arm-kernel(a)lists.infradead.org Cc: linuxarm(a)openeuler.org Link: https://lore.kernel.org/r/1611835236-34696-2-git-send-email-john.garry@huaw… Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json index df9201434cb6a..b0a10a219b50d 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json @@ -114,7 +114,7 @@ "PublicDescription": "Level 2 access to instruciton TLB that caused a page table walk. This event counts on any instruciton access which causes L2I_TLB_REFILL to count", "EventCode": "0x35", "EventName": "L2I_TLB_ACCESS", - "BriefDescription": "L2D TLB access" + "BriefDescription": "L2I TLB access" }, { "PublicDescription": "Branch target buffer misprediction", -- 2.27.0

1 0

[PATCH 5.10 344/663] perf vendor events arm64: Fix Ampere eMag event typo
by Greg Kroah-Hartman 02 Mar '21

02 Mar '21

From: John Garry <john.garry(a)huawei.com> [ Upstream commit 2bf797be81fa808f05f1a7a65916619132256a27 ] The "briefdescription" for event 0x35 has a typo - fix it. Fixes: d35c595bf005 ("perf vendor events arm64: Revise core JSON events for eMAG") Signed-off-by: John Garry <john.garry(a)huawei.com> Acked-by: Will Deacon <will(a)kernel.org> Cc: James Clark <james.clark(a)arm.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Nakamura, Shunsuke/中村俊介 <nakamura.shun(a)fujitsu.com> Cc: linux-arm-kernel(a)lists.infradead.org Cc: linuxarm(a)openeuler.org Link: https://lore.kernel.org/r/1611835236-34696-2-git-send-email-john.garry@huaw… Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json index 40010a8724b3a..ce6e7e7960579 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json @@ -114,7 +114,7 @@ "PublicDescription": "Level 2 access to instruciton TLB that caused a page table walk. This event counts on any instruciton access which causes L2I_TLB_REFILL to count", "EventCode": "0x35", "EventName": "L2I_TLB_ACCESS", - "BriefDescription": "L2D TLB access" + "BriefDescription": "L2I TLB access" }, { "PublicDescription": "Branch target buffer misprediction", -- 2.27.0

1 0

2024

2023

2022

2021

2020

Linuxarm March 2021