From patchwork Tue Sep 4 15:15:47 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Burakov, Anatoly" X-Patchwork-Id: 44278 X-Patchwork-Delegate: thomas@monjalon.net Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id C7AF24CBD; Tue, 4 Sep 2018 17:16:01 +0200 (CEST) Received: from mga06.intel.com (mga06.intel.com [134.134.136.31]) by dpdk.org (Postfix) with ESMTP id EADC62B92 for ; Tue, 4 Sep 2018 17:15:54 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by orsmga104.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 04 Sep 2018 08:15:53 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.53,329,1531810800"; d="scan'208";a="77880039" Received: from irvmail001.ir.intel.com ([163.33.26.43]) by FMSMGA003.fm.intel.com with ESMTP; 04 Sep 2018 08:15:52 -0700 Received: from sivswdev01.ir.intel.com (sivswdev01.ir.intel.com [10.237.217.45]) by irvmail001.ir.intel.com (8.14.3/8.13.6/MailSET/Hub) with ESMTP id w84FFpgO025481; Tue, 4 Sep 2018 16:15:51 +0100 Received: from sivswdev01.ir.intel.com (localhost [127.0.0.1]) by sivswdev01.ir.intel.com with ESMTP id w84FFpoL022293; Tue, 4 Sep 2018 16:15:51 +0100 Received: (from aburakov@localhost) by sivswdev01.ir.intel.com with LOCAL id w84FFphU022285; Tue, 4 Sep 2018 16:15:51 +0100 From: Anatoly Burakov To: dev@dpdk.org Cc: Bruce Richardson , tiwei.bie@intel.com, ray.kinsella@intel.com, zhihong.wang@intel.com, maxime.coquelin@redhat.com, kuralamudhan.ramakrishnan@intel.com Date: Tue, 4 Sep 2018 16:15:47 +0100 Message-Id: <6a24b2f23baccc78b7bab7ecfee84d3ed477ab80.1536073997.git.anatoly.burakov@intel.com> X-Mailer: git-send-email 1.7.0.7 In-Reply-To: References: In-Reply-To: References: Subject: [dpdk-dev] [PATCH v3 6/9] memalloc: add EAL-internal API to get and set segment fd's X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Enable setting and retrieving segment fd's internally. For now, retrieving fd's will not be used anywhere until we get an external API, but it will be useful for things like virtio, where we wish to share segment fd's. Setting segment fd's will not be available as a public API at this time, but internally it is needed for legacy mode, because we're not allocating our hugepages in memalloc in legacy mode case, and we still need to store the fd. Another user of get segment fd API is memseg info dump, to show which pages use which fd's. Not supported on FreeBSD. Signed-off-by: Anatoly Burakov --- lib/librte_eal/bsdapp/eal/eal_memalloc.c | 12 +++++ lib/librte_eal/common/eal_common_memory.c | 8 +-- lib/librte_eal/common/eal_memalloc.h | 6 +++ lib/librte_eal/linuxapp/eal/eal_memalloc.c | 60 +++++++++++++++++----- lib/librte_eal/linuxapp/eal/eal_memory.c | 44 +++++++++++++--- 5 files changed, 109 insertions(+), 21 deletions(-) diff --git a/lib/librte_eal/bsdapp/eal/eal_memalloc.c b/lib/librte_eal/bsdapp/eal/eal_memalloc.c index f7f07abd6..a5fb09f71 100644 --- a/lib/librte_eal/bsdapp/eal/eal_memalloc.c +++ b/lib/librte_eal/bsdapp/eal/eal_memalloc.c @@ -47,6 +47,18 @@ eal_memalloc_sync_with_primary(void) return -1; } +int +eal_memalloc_get_seg_fd(int list_idx, int seg_idx) +{ + return -1; +} + +int +eal_memalloc_set_seg_fd(int list_idx, int seg_idx, int fd) +{ + return -1; +} + int eal_memalloc_init(void) { diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c index fbfb1b055..034c2026a 100644 --- a/lib/librte_eal/common/eal_common_memory.c +++ b/lib/librte_eal/common/eal_common_memory.c @@ -294,7 +294,7 @@ dump_memseg(const struct rte_memseg_list *msl, const struct rte_memseg *ms, void *arg) { struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; - int msl_idx, ms_idx; + int msl_idx, ms_idx, fd; FILE *f = arg; msl_idx = msl - mcfg->memsegs; @@ -305,10 +305,11 @@ dump_memseg(const struct rte_memseg_list *msl, const struct rte_memseg *ms, if (ms_idx < 0) return -1; + fd = eal_memalloc_get_seg_fd(msl_idx, ms_idx); fprintf(f, "Segment %i-%i: IOVA:0x%"PRIx64", len:%zu, " "virt:%p, socket_id:%"PRId32", " "hugepage_sz:%"PRIu64", nchannel:%"PRIx32", " - "nrank:%"PRIx32"\n", + "nrank:%"PRIx32" fd:%i\n", msl_idx, ms_idx, ms->iova, ms->len, @@ -316,7 +317,8 @@ dump_memseg(const struct rte_memseg_list *msl, const struct rte_memseg *ms, ms->socket_id, ms->hugepage_sz, ms->nchannel, - ms->nrank); + ms->nrank, + fd); return 0; } diff --git a/lib/librte_eal/common/eal_memalloc.h b/lib/librte_eal/common/eal_memalloc.h index 36bb1a027..a46c69c72 100644 --- a/lib/librte_eal/common/eal_memalloc.h +++ b/lib/librte_eal/common/eal_memalloc.h @@ -76,6 +76,12 @@ eal_memalloc_mem_alloc_validator_unregister(const char *name, int socket_id); int eal_memalloc_mem_alloc_validate(int socket_id, size_t new_len); +int +eal_memalloc_get_seg_fd(int list_idx, int seg_idx); + +int +eal_memalloc_set_seg_fd(int list_idx, int seg_idx, int fd); + int eal_memalloc_init(void); diff --git a/lib/librte_eal/linuxapp/eal/eal_memalloc.c b/lib/librte_eal/linuxapp/eal/eal_memalloc.c index 7d536350e..b820989e9 100644 --- a/lib/librte_eal/linuxapp/eal/eal_memalloc.c +++ b/lib/librte_eal/linuxapp/eal/eal_memalloc.c @@ -1334,16 +1334,10 @@ secondary_msl_create_walk(const struct rte_memseg_list *msl, } static int -fd_list_create_walk(const struct rte_memseg_list *msl, - void *arg __rte_unused) +alloc_list(int list_idx, int len) { - struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; - unsigned int i, len; - int msl_idx; int *data; - - msl_idx = msl - mcfg->memsegs; - len = msl->memseg_arr.len; + int i; /* ensure we have space to store fd per each possible segment */ data = malloc(sizeof(int) * len); @@ -1355,14 +1349,56 @@ fd_list_create_walk(const struct rte_memseg_list *msl, for (i = 0; i < len; i++) data[i] = -1; - fd_list[msl_idx].fds = data; - fd_list[msl_idx].len = len; - fd_list[msl_idx].count = 0; - fd_list[msl_idx].memseg_list_fd = -1; + fd_list[list_idx].fds = data; + fd_list[list_idx].len = len; + fd_list[list_idx].count = 0; + fd_list[list_idx].memseg_list_fd = -1; return 0; } +static int +fd_list_create_walk(const struct rte_memseg_list *msl, + void *arg __rte_unused) +{ + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; + unsigned int len; + int msl_idx; + + msl_idx = msl - mcfg->memsegs; + len = msl->memseg_arr.len; + + return alloc_list(msl_idx, len); +} + +int +eal_memalloc_set_seg_fd(int list_idx, int seg_idx, int fd) +{ + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; + + /* if list is not allocated, allocate it */ + if (fd_list[list_idx].len == 0) { + int len = mcfg->memsegs[list_idx].memseg_arr.len; + + if (alloc_list(list_idx, len) < 0) + return -1; + } + fd_list[list_idx].fds[seg_idx] = fd; + + return 0; +} + +int +eal_memalloc_get_seg_fd(int list_idx, int seg_idx) +{ + if (internal_config.single_file_segments) + return fd_list[list_idx].memseg_list_fd; + /* list not initialized */ + if (fd_list[list_idx].len == 0) + return -1; + return fd_list[list_idx].fds[seg_idx]; +} + int eal_memalloc_init(void) { diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c index dfb537f59..e3ac24815 100644 --- a/lib/librte_eal/linuxapp/eal/eal_memory.c +++ b/lib/librte_eal/linuxapp/eal/eal_memory.c @@ -772,7 +772,10 @@ remap_segment(struct hugepage_file *hugepages, int seg_start, int seg_end) rte_fbarray_set_used(arr, ms_idx); - close(fd); + /* store segment fd internally */ + if (eal_memalloc_set_seg_fd(msl_idx, ms_idx, fd) < 0) + RTE_LOG(ERR, EAL, "Could not store segment fd: %s\n", + rte_strerror(rte_errno)); } RTE_LOG(DEBUG, EAL, "Allocated %" PRIu64 "M on socket %i\n", (seg_len * page_sz) >> 20, socket_id); @@ -1771,6 +1774,7 @@ getFileSize(int fd) static int eal_legacy_hugepage_attach(void) { + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; struct hugepage_file *hp = NULL; unsigned int num_hp = 0; unsigned int i = 0; @@ -1814,6 +1818,9 @@ eal_legacy_hugepage_attach(void) struct hugepage_file *hf = &hp[i]; size_t map_sz = hf->size; void *map_addr = hf->final_va; + int msl_idx, ms_idx; + struct rte_memseg_list *msl; + struct rte_memseg *ms; /* if size is zero, no more pages left */ if (map_sz == 0) @@ -1831,25 +1838,50 @@ eal_legacy_hugepage_attach(void) if (map_addr == MAP_FAILED) { RTE_LOG(ERR, EAL, "Could not map %s: %s\n", hf->filepath, strerror(errno)); - close(fd); - goto error; + goto fd_error; } /* set shared lock on the file. */ if (flock(fd, LOCK_SH) < 0) { RTE_LOG(DEBUG, EAL, "%s(): Locking file failed: %s\n", __func__, strerror(errno)); - close(fd); - goto error; + goto fd_error; } - close(fd); + /* find segment data */ + msl = rte_mem_virt2memseg_list(map_addr); + if (msl == NULL) { + RTE_LOG(DEBUG, EAL, "%s(): Cannot find memseg list\n", + __func__); + goto fd_error; + } + ms = rte_mem_virt2memseg(map_addr, msl); + if (ms == NULL) { + RTE_LOG(DEBUG, EAL, "%s(): Cannot find memseg\n", + __func__); + goto fd_error; + } + + msl_idx = msl - mcfg->memsegs; + ms_idx = rte_fbarray_find_idx(&msl->memseg_arr, ms); + if (ms_idx < 0) { + RTE_LOG(DEBUG, EAL, "%s(): Cannot find memseg idx\n", + __func__); + goto fd_error; + } + + /* store segment fd internally */ + if (eal_memalloc_set_seg_fd(msl_idx, ms_idx, fd) < 0) + RTE_LOG(ERR, EAL, "Could not store segment fd: %s\n", + rte_strerror(rte_errno)); } /* unmap the hugepage config file, since we are done using it */ munmap(hp, size); close(fd_hugepage); return 0; +fd_error: + close(fd); error: /* map all segments into memory to make sure we get the addrs */ cur_seg = 0;