From patchwork Sun Sep 30 14:16:25 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Guo, Jia" X-Patchwork-Id: 45716 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 22F1B5F28; Sun, 30 Sep 2018 16:12:47 +0200 (CEST) Received: from mga12.intel.com (mga12.intel.com [192.55.52.136]) by dpdk.org (Postfix) with ESMTP id C88B75F20 for ; Sun, 30 Sep 2018 16:12:44 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 30 Sep 2018 07:12:44 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,324,1534834800"; d="scan'208";a="261661863" Received: from jeffguo-s2600wt2.sh.intel.com (HELO localhost.localdomain) ([10.67.110.10]) by orsmga005.jf.intel.com with ESMTP; 30 Sep 2018 07:12:40 -0700 From: Jeff Guo To: stephen@networkplumber.org, bruce.richardson@intel.com, ferruh.yigit@intel.com, konstantin.ananyev@intel.com, gaetan.rivet@6wind.com, jingjing.wu@intel.com, thomas@monjalon.net, motih@mellanox.com, matan@mellanox.com, harry.van.haaren@intel.com, qi.z.zhang@intel.com, shaopeng.he@intel.com, bernard.iremonger@intel.com, arybchenko@solarflare.com, anatoly.burakov@intel.com Cc: jblunck@infradead.org, shreyansh.jain@nxp.com, dev@dpdk.org, jia.guo@intel.com, helin.zhang@intel.com Date: Sun, 30 Sep 2018 22:16:25 +0800 Message-Id: <1538316988-128382-2-git-send-email-jia.guo@intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1538316988-128382-1-git-send-email-jia.guo@intel.com> References: <1534503091-31910-1-git-send-email-jia.guo@intel.com> <1538316988-128382-1-git-send-email-jia.guo@intel.com> Subject: [dpdk-dev] [PATCH v2 1/4] eal: add a new req notifier to eal interrupt 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" Add a new req notifier in eal interrupt for enable vfio hotplug. Signed-off-by: Jeff Guo --- v2->v1: no change --- lib/librte_eal/common/include/rte_eal_interrupts.h | 1 + lib/librte_eal/linuxapp/eal/eal_interrupts.c | 71 ++++++++++++++++++++++ 2 files changed, 72 insertions(+) diff --git a/lib/librte_eal/common/include/rte_eal_interrupts.h b/lib/librte_eal/common/include/rte_eal_interrupts.h index 6eb4932..2c47738 100644 --- a/lib/librte_eal/common/include/rte_eal_interrupts.h +++ b/lib/librte_eal/common/include/rte_eal_interrupts.h @@ -35,6 +35,7 @@ enum rte_intr_handle_type { RTE_INTR_HANDLE_EXT, /**< external handler */ RTE_INTR_HANDLE_VDEV, /**< virtual device */ RTE_INTR_HANDLE_DEV_EVENT, /**< device event handle */ + RTE_INTR_HANDLE_VFIO_REQ, /**< vfio device handle (req) */ RTE_INTR_HANDLE_MAX /**< count of elements */ }; diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c index 4076c6d..7f611b3 100644 --- a/lib/librte_eal/linuxapp/eal/eal_interrupts.c +++ b/lib/librte_eal/linuxapp/eal/eal_interrupts.c @@ -308,6 +308,64 @@ vfio_disable_msix(const struct rte_intr_handle *intr_handle) { return ret; } + +/* enable req notifier */ +static int +vfio_enable_req(const struct rte_intr_handle *intr_handle) +{ + int len, ret; + char irq_set_buf[IRQ_SET_BUF_LEN]; + struct vfio_irq_set *irq_set; + int *fd_ptr; + + len = sizeof(irq_set_buf); + + irq_set = (struct vfio_irq_set *) irq_set_buf; + irq_set->argsz = len; + irq_set->count = 1; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_PCI_REQ_IRQ_INDEX; + irq_set->start = 0; + fd_ptr = (int *) &irq_set->data; + *fd_ptr = intr_handle->fd; + + ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); + + if (ret) { + RTE_LOG(ERR, EAL, "Error enabling req interrupts for fd %d\n", + intr_handle->fd); + return -1; + } + + return 0; +} + +/* disable req notifier */ +static int +vfio_disable_req(const struct rte_intr_handle *intr_handle) +{ + struct vfio_irq_set *irq_set; + char irq_set_buf[IRQ_SET_BUF_LEN]; + int len, ret; + + len = sizeof(struct vfio_irq_set); + + irq_set = (struct vfio_irq_set *) irq_set_buf; + irq_set->argsz = len; + irq_set->count = 0; + irq_set->flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_PCI_REQ_IRQ_INDEX; + irq_set->start = 0; + + ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); + + if (ret) + RTE_LOG(ERR, EAL, "Error disabling req interrupts for fd %d\n", + intr_handle->fd); + + return ret; +} #endif static int @@ -556,6 +614,10 @@ rte_intr_enable(const struct rte_intr_handle *intr_handle) if (vfio_enable_intx(intr_handle)) return -1; break; + case RTE_INTR_HANDLE_VFIO_REQ: + if (vfio_enable_req(intr_handle)) + return -1; + break; #endif /* not used at this moment */ case RTE_INTR_HANDLE_DEV_EVENT: @@ -606,6 +668,11 @@ rte_intr_disable(const struct rte_intr_handle *intr_handle) if (vfio_disable_intx(intr_handle)) return -1; break; + case RTE_INTR_HANDLE_VFIO_REQ: + if (vfio_disable_req(intr_handle)) + return -1; + break; + #endif /* not used at this moment */ case RTE_INTR_HANDLE_DEV_EVENT: @@ -682,6 +749,10 @@ eal_intr_process_interrupts(struct epoll_event *events, int nfds) bytes_read = 0; call = true; break; + case RTE_INTR_HANDLE_VFIO_REQ: + bytes_read = 0; + call = true; + break; default: bytes_read = 1; break; From patchwork Sun Sep 30 14:16:26 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Guo, Jia" X-Patchwork-Id: 45717 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 1C14C5F34; Sun, 30 Sep 2018 16:12:50 +0200 (CEST) Received: from mga12.intel.com (mga12.intel.com [192.55.52.136]) by dpdk.org (Postfix) with ESMTP id 3B6AB5F2E for ; Sun, 30 Sep 2018 16:12:48 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 30 Sep 2018 07:12:47 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,324,1534834800"; d="scan'208";a="261661884" Received: from jeffguo-s2600wt2.sh.intel.com (HELO localhost.localdomain) ([10.67.110.10]) by orsmga005.jf.intel.com with ESMTP; 30 Sep 2018 07:12:44 -0700 From: Jeff Guo To: stephen@networkplumber.org, bruce.richardson@intel.com, ferruh.yigit@intel.com, konstantin.ananyev@intel.com, gaetan.rivet@6wind.com, jingjing.wu@intel.com, thomas@monjalon.net, motih@mellanox.com, matan@mellanox.com, harry.van.haaren@intel.com, qi.z.zhang@intel.com, shaopeng.he@intel.com, bernard.iremonger@intel.com, arybchenko@solarflare.com, anatoly.burakov@intel.com Cc: jblunck@infradead.org, shreyansh.jain@nxp.com, dev@dpdk.org, jia.guo@intel.com, helin.zhang@intel.com Date: Sun, 30 Sep 2018 22:16:26 +0800 Message-Id: <1538316988-128382-3-git-send-email-jia.guo@intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1538316988-128382-1-git-send-email-jia.guo@intel.com> References: <1534503091-31910-1-git-send-email-jia.guo@intel.com> <1538316988-128382-1-git-send-email-jia.guo@intel.com> Subject: [dpdk-dev] [PATCH v2 2/4] eal: modify device event callback process func 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" This patch modify the device event callback process function name to be more explicit, change the variable to be const and exposure the API out from private eal. The bus drivers and eal device would directly use this API to process device event callback. Signed-off-by: Jeff Guo --- v2->v1: change the rte_dev_event_callback_prcess from internal to external api for bus or app usage. --- app/test-pmd/testpmd.c | 4 ++-- lib/librte_eal/bsdapp/eal/eal_dev.c | 8 ++++++++ lib/librte_eal/common/eal_common_dev.c | 5 +++-- lib/librte_eal/common/eal_private.h | 12 ------------ lib/librte_eal/common/include/rte_dev.h | 18 +++++++++++++++++- lib/librte_eal/linuxapp/eal/eal_dev.c | 2 +- lib/librte_eal/rte_eal_version.map | 1 + 7 files changed, 32 insertions(+), 18 deletions(-) diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index bfef483..1313100 100644 --- a/app/test-pmd/testpmd.c +++ b/app/test-pmd/testpmd.c @@ -431,7 +431,7 @@ static void check_all_ports_link_status(uint32_t port_mask); static int eth_event_callback(portid_t port_id, enum rte_eth_event_type type, void *param, void *ret_param); -static void eth_dev_event_callback(char *device_name, +static void eth_dev_event_callback(const char *device_name, enum rte_dev_event_type type, void *param); static int eth_dev_event_callback_register(void); @@ -2249,7 +2249,7 @@ eth_event_callback(portid_t port_id, enum rte_eth_event_type type, void *param, /* This function is used by the interrupt thread */ static void -eth_dev_event_callback(char *device_name, enum rte_dev_event_type type, +eth_dev_event_callback(const char *device_name, enum rte_dev_event_type type, __rte_unused void *arg) { uint16_t port_id; diff --git a/lib/librte_eal/bsdapp/eal/eal_dev.c b/lib/librte_eal/bsdapp/eal/eal_dev.c index ae1c558..374e737 100644 --- a/lib/librte_eal/bsdapp/eal/eal_dev.c +++ b/lib/librte_eal/bsdapp/eal/eal_dev.c @@ -33,3 +33,11 @@ rte_dev_hotplug_handle_disable(void) RTE_LOG(ERR, EAL, "Device event is not supported for FreeBSD\n"); return -1; } + +void __rte_experimental +rte_dev_event_callback_process(const char *device_name, + enum rte_dev_event_type event) +{ + RTE_LOG(ERR, EAL, "Device event callback process is not supported " + "for FreeBSD\n"); +} diff --git a/lib/librte_eal/common/eal_common_dev.c b/lib/librte_eal/common/eal_common_dev.c index 678dbca..2d610a4 100644 --- a/lib/librte_eal/common/eal_common_dev.c +++ b/lib/librte_eal/common/eal_common_dev.c @@ -342,8 +342,9 @@ rte_dev_event_callback_unregister(const char *device_name, return ret; } -void -dev_callback_process(char *device_name, enum rte_dev_event_type event) +void __rte_experimental +rte_dev_event_callback_process(const char *device_name, + enum rte_dev_event_type event) { struct dev_event_callback *cb_lst; diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h index 637f20d..47e8a33 100644 --- a/lib/librte_eal/common/eal_private.h +++ b/lib/librte_eal/common/eal_private.h @@ -259,18 +259,6 @@ struct rte_bus *rte_bus_find_by_device_name(const char *str); int rte_mp_channel_init(void); /** - * Internal Executes all the user application registered callbacks for - * the specific device. It is for DPDK internal user only. User - * application should not call it directly. - * - * @param device_name - * The device name. - * @param event - * the device event type. - */ -void dev_callback_process(char *device_name, enum rte_dev_event_type event); - -/** * @internal * Parse a device string and store its information in an * rte_devargs structure. diff --git a/lib/librte_eal/common/include/rte_dev.h b/lib/librte_eal/common/include/rte_dev.h index ff580a0..58fab43 100644 --- a/lib/librte_eal/common/include/rte_dev.h +++ b/lib/librte_eal/common/include/rte_dev.h @@ -39,7 +39,7 @@ struct rte_dev_event { char *devname; /**< device name */ }; -typedef void (*rte_dev_event_cb_fn)(char *device_name, +typedef void (*rte_dev_event_cb_fn)(const char *device_name, enum rte_dev_event_type event, void *cb_arg); @@ -438,6 +438,22 @@ rte_dev_event_callback_unregister(const char *device_name, * @warning * @b EXPERIMENTAL: this API may change without prior notice * + * Executes all the user application registered callbacks for + * the specific device. + * + * @param device_name + * The device name. + * @param event + * the device event type. + */ +void __rte_experimental +rte_dev_event_callback_process(const char *device_name, + enum rte_dev_event_type event); + +/** + * @warning + * @b EXPERIMENTAL: this API may change without prior notice + * * Start the device event monitoring. * * @return diff --git a/lib/librte_eal/linuxapp/eal/eal_dev.c b/lib/librte_eal/linuxapp/eal/eal_dev.c index 9f9e1cf..01e3a04 100644 --- a/lib/librte_eal/linuxapp/eal/eal_dev.c +++ b/lib/librte_eal/linuxapp/eal/eal_dev.c @@ -271,7 +271,7 @@ dev_uev_handler(__rte_unused void *param) return; } } - dev_callback_process(uevent.devname, uevent.type); + rte_dev_event_callback_process(uevent.devname, uevent.type); } } diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map index a3255aa..b96da50 100644 --- a/lib/librte_eal/rte_eal_version.map +++ b/lib/librte_eal/rte_eal_version.map @@ -277,6 +277,7 @@ EXPERIMENTAL { rte_class_register; rte_class_unregister; rte_ctrl_thread_create; + rte_dev_event_callback_process; rte_dev_event_callback_register; rte_dev_event_callback_unregister; rte_dev_event_monitor_start; From patchwork Sun Sep 30 14:16:27 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Guo, Jia" X-Patchwork-Id: 45718 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 9E3305F57; Sun, 30 Sep 2018 16:12:53 +0200 (CEST) Received: from mga12.intel.com (mga12.intel.com [192.55.52.136]) by dpdk.org (Postfix) with ESMTP id 254875F4D for ; Sun, 30 Sep 2018 16:12:51 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 30 Sep 2018 07:12:51 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,324,1534834800"; d="scan'208";a="261661894" Received: from jeffguo-s2600wt2.sh.intel.com (HELO localhost.localdomain) ([10.67.110.10]) by orsmga005.jf.intel.com with ESMTP; 30 Sep 2018 07:12:48 -0700 From: Jeff Guo To: stephen@networkplumber.org, bruce.richardson@intel.com, ferruh.yigit@intel.com, konstantin.ananyev@intel.com, gaetan.rivet@6wind.com, jingjing.wu@intel.com, thomas@monjalon.net, motih@mellanox.com, matan@mellanox.com, harry.van.haaren@intel.com, qi.z.zhang@intel.com, shaopeng.he@intel.com, bernard.iremonger@intel.com, arybchenko@solarflare.com, anatoly.burakov@intel.com Cc: jblunck@infradead.org, shreyansh.jain@nxp.com, dev@dpdk.org, jia.guo@intel.com, helin.zhang@intel.com Date: Sun, 30 Sep 2018 22:16:27 +0800 Message-Id: <1538316988-128382-4-git-send-email-jia.guo@intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1538316988-128382-1-git-send-email-jia.guo@intel.com> References: <1534503091-31910-1-git-send-email-jia.guo@intel.com> <1538316988-128382-1-git-send-email-jia.guo@intel.com> Subject: [dpdk-dev] [PATCH v2 3/4] pci: add req handler field to generic pci device 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" There are some extended interrupt types in vfio pci device except from the existing interrupts, such as err and req notifier, they could be useful for device error monitoring. And these corresponding interrupt handler is different from the other interrupt handler that register in PMDs, so a new interrupt handler should be added. This patch will add specific req handler in generic pci device. Signed-off-by: Jeff Guo --- v2->v1: no change --- drivers/bus/pci/rte_bus_pci.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bus/pci/rte_bus_pci.h b/drivers/bus/pci/rte_bus_pci.h index 0d1955f..c45a820 100644 --- a/drivers/bus/pci/rte_bus_pci.h +++ b/drivers/bus/pci/rte_bus_pci.h @@ -66,6 +66,7 @@ struct rte_pci_device { uint16_t max_vfs; /**< sriov enable if not zero */ enum rte_kernel_driver kdrv; /**< Kernel driver passthrough */ char name[PCI_PRI_STR_SIZE+1]; /**< PCI location (ASCII) */ + struct rte_intr_handle req_notifier_handler;/**< Req notifier handle */ }; /** From patchwork Sun Sep 30 14:16:28 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Guo, Jia" X-Patchwork-Id: 45719 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 3735A683E; Sun, 30 Sep 2018 16:12:57 +0200 (CEST) Received: from mga12.intel.com (mga12.intel.com [192.55.52.136]) by dpdk.org (Postfix) with ESMTP id DCE775F65 for ; Sun, 30 Sep 2018 16:12:55 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 30 Sep 2018 07:12:55 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,324,1534834800"; d="scan'208";a="261661902" Received: from jeffguo-s2600wt2.sh.intel.com (HELO localhost.localdomain) ([10.67.110.10]) by orsmga005.jf.intel.com with ESMTP; 30 Sep 2018 07:12:51 -0700 From: Jeff Guo To: stephen@networkplumber.org, bruce.richardson@intel.com, ferruh.yigit@intel.com, konstantin.ananyev@intel.com, gaetan.rivet@6wind.com, jingjing.wu@intel.com, thomas@monjalon.net, motih@mellanox.com, matan@mellanox.com, harry.van.haaren@intel.com, qi.z.zhang@intel.com, shaopeng.he@intel.com, bernard.iremonger@intel.com, arybchenko@solarflare.com, anatoly.burakov@intel.com Cc: jblunck@infradead.org, shreyansh.jain@nxp.com, dev@dpdk.org, jia.guo@intel.com, helin.zhang@intel.com Date: Sun, 30 Sep 2018 22:16:28 +0800 Message-Id: <1538316988-128382-5-git-send-email-jia.guo@intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1538316988-128382-1-git-send-email-jia.guo@intel.com> References: <1534503091-31910-1-git-send-email-jia.guo@intel.com> <1538316988-128382-1-git-send-email-jia.guo@intel.com> Subject: [dpdk-dev] [PATCH v2 4/4] vfio: enable vfio hotplug by req notifier handler 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" When device is be hot-unplugged, the vfio kernel module will sent req notifier to request user space to release the allocated resources at first. After that, vfio kernel module will detect the device disappear, and then delete the device in kernel. This patch aim to add req notifier processing to enable hotplug for vfio. By enable the req notifier monitoring and register the notifier callback, when device be hot-unplugged, the hot-unplug handler will be called to process hotplug for vfio. Signed-off-by: Jeff Guo --- v2->v1: refine some code logic. --- drivers/bus/pci/linux/pci_vfio.c | 95 ++++++++++++++++++++++++++++++++++++++++ drivers/bus/pci/pci_common.c | 10 +++++ 2 files changed, 105 insertions(+) diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c index 686386d..c780860 100644 --- a/drivers/bus/pci/linux/pci_vfio.c +++ b/drivers/bus/pci/linux/pci_vfio.c @@ -17,6 +17,8 @@ #include #include #include +#include +#include #include "eal_filesystem.h" @@ -277,6 +279,89 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd) return -1; } +static void +pci_vfio_req_handler(void *param) +{ + struct rte_bus *bus; + int ret; + struct rte_device *device = (struct rte_device *)param; + + bus = rte_bus_find_by_device(device); + if (bus == NULL) { + RTE_LOG(ERR, EAL, "Cannot find bus for device (%s)\n", + device->name); + return; + } + + /** + * vfio kernel module request user space to release allocated + * resources before device be deleted in kernel, so it can directly + * call the vfio bus hot-unplug handler to process it. + */ + ret = bus->hot_unplug_handler(device); + if (ret) + RTE_LOG(ERR, EAL, "Can not handle hot-unplug for " + "device (%s)\n", device->name); +} + +/* enable notifier (only enable req now) */ +static int +pci_vfio_enable_notifier(struct rte_pci_device *dev, int vfio_dev_fd) +{ + int ret; + int fd = -1; + + /* set up an eventfd for req notifier */ + fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC); + if (fd < 0) { + RTE_LOG(ERR, EAL, "Cannot set up eventfd, " + "error %i (%s)\n", errno, strerror(errno)); + return -1; + } + + dev->req_notifier_handler.fd = fd; + dev->req_notifier_handler.type = RTE_INTR_HANDLE_VFIO_REQ; + dev->req_notifier_handler.vfio_dev_fd = vfio_dev_fd; + ret = rte_intr_callback_register(&dev->req_notifier_handler, + pci_vfio_req_handler, + (void *)&dev->device); + if (ret) { + RTE_LOG(ERR, EAL, "Fail to register req notifier handler.\n"); + return -1; + } + + ret = rte_intr_enable(&dev->req_notifier_handler); + if (ret) { + RTE_LOG(ERR, EAL, "Fail to enable req notifier.\n"); + return -1; + } + + return 0; +} + +/*disable notifier (only disable req now) */ +static int +pci_vfio_disable_notifier(struct rte_pci_device *dev) +{ + int ret; + + ret = rte_intr_disable(&dev->req_notifier_handler); + if (ret) { + RTE_LOG(ERR, EAL, "fail to disable req notifier.\n"); + return -1; + } + + ret = rte_intr_callback_unregister(&dev->req_notifier_handler, + pci_vfio_req_handler, + (void *)&dev->device); + if (ret) { + RTE_LOG(ERR, EAL, + "fail to unregister req notifier handler.\n"); + return -1; + } + return 0; +} + static int pci_vfio_is_ioport_bar(int vfio_dev_fd, int bar_index) { @@ -430,6 +515,7 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev) struct pci_map *maps; dev->intr_handle.fd = -1; + dev->req_notifier_handler.fd = -1; /* store PCI address string */ snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT, @@ -521,6 +607,11 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev) goto err_vfio_res; } + if (pci_vfio_enable_notifier(dev, vfio_dev_fd) != 0) { + RTE_LOG(ERR, EAL, "Error setting up notifier!\n"); + return -1; + } + TAILQ_INSERT_TAIL(vfio_res_list, vfio_res, next); return 0; @@ -546,6 +637,7 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev) struct pci_map *maps; dev->intr_handle.fd = -1; + dev->req_notifier_handler.fd = -1; /* store PCI address string */ snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT, @@ -586,6 +678,7 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev) /* we need save vfio_dev_fd, so it can be used during release */ dev->intr_handle.vfio_dev_fd = vfio_dev_fd; + dev->req_notifier_handler.vfio_dev_fd = vfio_dev_fd; return 0; err_vfio_dev_fd: @@ -658,6 +751,8 @@ pci_vfio_unmap_resource_primary(struct rte_pci_device *dev) snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT, loc->domain, loc->bus, loc->devid, loc->function); + pci_vfio_disable_notifier(dev); + if (close(dev->intr_handle.fd) < 0) { RTE_LOG(INFO, EAL, "Error when closing eventfd file descriptor for %s\n", pci_addr); diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_common.c index f313fe9..2a8e5e9 100644 --- a/drivers/bus/pci/pci_common.c +++ b/drivers/bus/pci/pci_common.c @@ -446,6 +446,16 @@ pci_hot_unplug_handler(struct rte_device *dev) return -1; switch (pdev->kdrv) { + case RTE_KDRV_VFIO: + /** + * vfio kernel module guaranty the pci device would not be + * deleted until the user space release the resource, so no + * need to remap BARs resource here, just directly notify + * the req event to the user space to handle it. + */ + rte_dev_event_callback_process(dev->name, + RTE_DEV_EVENT_REMOVE); + break; case RTE_KDRV_IGB_UIO: case RTE_KDRV_UIO_GENERIC: case RTE_KDRV_NIC_UIO: