DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Zhu, TaoX" <taox.zhu@intel.com>
To: "Xing, Beilei" <beilei.xing@intel.com>,
	"Zhang, Qi Z" <qi.z.zhang@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
	"Yang, Qiming" <qiming.yang@intel.com>,
	"Ye, Xiaolong" <xiaolong.ye@intel.com>
Subject: Re: [dpdk-dev] [PATCH v5] net/i40e: add PF MDD event handler
Date: Fri, 17 Jan 2020 03:08:04 +0000	[thread overview]
Message-ID: <60652C6914E08D41B9AA1580751B3CA9C291A5@SHSMSX106.ccr.corp.intel.com> (raw)
In-Reply-To: <20200117112422.7214-1-taox.zhu@intel.com>

Hi ALL,

The name of patch subject has forgotten to be modified. Please ignore this patch and I will resend it.

BR,
Zhu, Tao


> -----Original Message-----
> From: Zhu, TaoX
> Sent: Friday, January 17, 2020 7:24 PM
> To: Xing, Beilei <beilei.xing@intel.com>; Zhang, Qi Z <qi.z.zhang@intel.com>
> Cc: dev@dpdk.org; Yang, Qiming <qiming.yang@intel.com>; Ye, Xiaolong
> <xiaolong.ye@intel.com>; Zhu, TaoX <taox.zhu@intel.com>
> Subject: [PATCH v5] net/i40e: add PF MDD event handler
> 
> From: Zhu Tao <taox.zhu@intel.com>
> 
> Add warning and counter to handle the malicious driver detection event.
> When the hardware determines that a malicious driver on VF, this VF will
> become unworkable, the PF records and gives a warning message.
> 
> Signed-off-by: Zhu Tao <taox.zhu@intel.com>
> Acked-by: Qiming Yang <qiming.yang@intel.com>
> ---
>  doc/guides/nics/i40e.rst               |  1 +
>  doc/guides/rel_notes/release_20_02.rst |  4 +-
>  drivers/net/i40e/i40e_ethdev.c         | 89 +++++++++++++++++++++++++-
>  drivers/net/i40e/i40e_ethdev.h         |  1 +
>  4 files changed, 92 insertions(+), 3 deletions(-)
> 
> v6:
> - Change commit message
> v5:
> - Change commit message
> v4:
> - Change commit message
> - Rebase doc/guides/rel_notes/release_20_02.rst
> v3:
> - Change commit message
> 
> diff --git a/doc/guides/nics/i40e.rst b/doc/guides/nics/i40e.rst index
> c7c34b62f..2bf11e8ca 100644
> --- a/doc/guides/nics/i40e.rst
> +++ b/doc/guides/nics/i40e.rst
> @@ -43,6 +43,7 @@ Features of the i40e PMD are:
>  - Dynamic Device Personalization (DDP)
>  - Queue region configuration
>  - Virtual Function Port Representors
> +- Malicious Device Drive event catch and notify
> 
>  Prerequisites
>  -------------
> diff --git a/doc/guides/rel_notes/release_20_02.rst
> b/doc/guides/rel_notes/release_20_02.rst
> index 1e83e659a..a39f22221 100644
> --- a/doc/guides/rel_notes/release_20_02.rst
> +++ b/doc/guides/rel_notes/release_20_02.rst
> @@ -66,11 +66,13 @@ New Features
> 
>    * Added support for RSS using L3/L4 source/destination only.
> 
> -* **Updated i40e driver to support L2TPv3 over IP flows.**
> +* **Updated i40e driver.**
> 
>    Updated the i40e PMD to support L2TPv3 over IP profiles which can be
>    programmed by the dynamic device personalization (DDP) process.
> 
> +  Added PF support Malicious Device Drive event catch and notify.
> +
>  * **Updated testpmd to support L2TPv3 over IP flows.**
> 
>    Added support for L2TPv3 over IP rte_flow patterns to the testpmd diff --
> git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
> index afb6f554b..95bfed4d9 100644
> --- a/drivers/net/i40e/i40e_ethdev.c
> +++ b/drivers/net/i40e/i40e_ethdev.c
> @@ -6760,6 +6760,87 @@ i40e_dev_handle_aq_msg(struct rte_eth_dev
> *dev)
>  	rte_free(info.msg_buf);
>  }
> 
> +static void
> +i40e_handle_mdd_event(struct rte_eth_dev *dev) {
> +	struct i40e_hw *hw = I40E_DEV_PRIVATE_TO_HW(dev->data-
> >dev_private);
> +	struct i40e_pf *pf = I40E_DEV_PRIVATE_TO_PF(dev->data-
> >dev_private);
> +	bool mdd_detected = false;
> +	struct i40e_pf_vf *vf;
> +	uint32_t reg;
> +	int i;
> +
> +	/* find what triggered the MDD event */
> +	reg = I40E_READ_REG(hw, I40E_GL_MDET_TX);
> +	if (reg & I40E_GL_MDET_TX_VALID_MASK) {
> +		uint8_t pf_num = (reg &
> I40E_GL_MDET_TX_PF_NUM_MASK) >>
> +				I40E_GL_MDET_TX_PF_NUM_SHIFT;
> +		uint16_t vf_num = (reg &
> I40E_GL_MDET_TX_VF_NUM_MASK) >>
> +				I40E_GL_MDET_TX_VF_NUM_SHIFT;
> +		uint8_t event = (reg & I40E_GL_MDET_TX_EVENT_MASK) >>
> +				I40E_GL_MDET_TX_EVENT_SHIFT;
> +		uint16_t queue = ((reg &
> I40E_GL_MDET_TX_QUEUE_MASK) >>
> +				I40E_GL_MDET_TX_QUEUE_SHIFT) -
> +					hw->func_caps.base_queue;
> +		PMD_DRV_LOG(WARNING, "Malicious Driver Detection
> event 0x%02x on TX "
> +			"queue %d PF number 0x%02x VF number 0x%02x
> device %s\n",
> +				event, queue, pf_num, vf_num, dev->data-
> >name);
> +		I40E_WRITE_REG(hw, I40E_GL_MDET_TX, 0xffffffff);
> +		mdd_detected = true;
> +	}
> +	reg = I40E_READ_REG(hw, I40E_GL_MDET_RX);
> +	if (reg & I40E_GL_MDET_RX_VALID_MASK) {
> +		uint8_t func = (reg &
> I40E_GL_MDET_RX_FUNCTION_MASK) >>
> +				I40E_GL_MDET_RX_FUNCTION_SHIFT;
> +		uint8_t event = (reg & I40E_GL_MDET_RX_EVENT_MASK) >>
> +				I40E_GL_MDET_RX_EVENT_SHIFT;
> +		uint16_t queue = ((reg &
> I40E_GL_MDET_RX_QUEUE_MASK) >>
> +				I40E_GL_MDET_RX_QUEUE_SHIFT) -
> +					hw->func_caps.base_queue;
> +
> +		PMD_DRV_LOG(WARNING, "Malicious Driver Detection
> event 0x%02x on RX "
> +				"queue %d of function 0x%02x device %s\n",
> +					event, queue, func, dev->data-
> >name);
> +		I40E_WRITE_REG(hw, I40E_GL_MDET_RX, 0xffffffff);
> +		mdd_detected = true;
> +	}
> +
> +	if (mdd_detected) {
> +		reg = I40E_READ_REG(hw, I40E_PF_MDET_TX);
> +		if (reg & I40E_PF_MDET_TX_VALID_MASK) {
> +			I40E_WRITE_REG(hw, I40E_PF_MDET_TX, 0xFFFF);
> +			PMD_DRV_LOG(WARNING, "TX driver issue
> detected on PF\n");
> +		}
> +		reg = I40E_READ_REG(hw, I40E_PF_MDET_RX);
> +		if (reg & I40E_PF_MDET_RX_VALID_MASK) {
> +			I40E_WRITE_REG(hw, I40E_PF_MDET_RX, 0xFFFF);
> +			PMD_DRV_LOG(WARNING, "RX driver issue
> detected on PF\n");
> +		}
> +	}
> +
> +	/* see if one of the VFs needs its hand slapped */
> +	for (i = 0; i < pf->vf_num && mdd_detected; i++) {
> +		vf = &pf->vfs[i];
> +		reg = I40E_READ_REG(hw, I40E_VP_MDET_TX(i));
> +		if (reg & I40E_VP_MDET_TX_VALID_MASK) {
> +			I40E_WRITE_REG(hw, I40E_VP_MDET_TX(i), 0xFFFF);
> +			vf->num_mdd_events++;
> +			PMD_DRV_LOG(WARNING, "TX driver issue
> detected on VF %d %-"
> +					PRIu64 "times\n",
> +					i, vf->num_mdd_events);
> +		}
> +
> +		reg = I40E_READ_REG(hw, I40E_VP_MDET_RX(i));
> +		if (reg & I40E_VP_MDET_RX_VALID_MASK) {
> +			I40E_WRITE_REG(hw, I40E_VP_MDET_RX(i), 0xFFFF);
> +			vf->num_mdd_events++;
> +			PMD_DRV_LOG(WARNING, "RX driver issue
> detected on VF %d %-"
> +					PRIu64 "times\n",
> +					i, vf->num_mdd_events);
> +		}
> +	}
> +}
> +
>  /**
>   * Interrupt handler triggered by NIC  for handling
>   * specific interrupt.
> @@ -6792,8 +6873,10 @@ i40e_dev_interrupt_handler(void *param)
>  	}
>  	if (icr0 & I40E_PFINT_ICR0_ECC_ERR_MASK)
>  		PMD_DRV_LOG(ERR, "ICR0: unrecoverable ECC error");
> -	if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK)
> +	if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) {
>  		PMD_DRV_LOG(ERR, "ICR0: malicious programming
> detected");
> +		i40e_handle_mdd_event(dev);
> +	}
>  	if (icr0 & I40E_PFINT_ICR0_GRST_MASK)
>  		PMD_DRV_LOG(INFO, "ICR0: global reset requested");
>  	if (icr0 & I40E_PFINT_ICR0_PCI_EXCEPTION_MASK)
> @@ -6837,8 +6920,10 @@ i40e_dev_alarm_handler(void *param)
>  		goto done;
>  	if (icr0 & I40E_PFINT_ICR0_ECC_ERR_MASK)
>  		PMD_DRV_LOG(ERR, "ICR0: unrecoverable ECC error");
> -	if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK)
> +	if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) {
>  		PMD_DRV_LOG(ERR, "ICR0: malicious programming
> detected");
> +		i40e_handle_mdd_event(dev);
> +	}
>  	if (icr0 & I40E_PFINT_ICR0_GRST_MASK)
>  		PMD_DRV_LOG(INFO, "ICR0: global reset requested");
>  	if (icr0 & I40E_PFINT_ICR0_PCI_EXCEPTION_MASK)
> diff --git a/drivers/net/i40e/i40e_ethdev.h
> b/drivers/net/i40e/i40e_ethdev.h index bba2b83b4..370e6298f 100644
> --- a/drivers/net/i40e/i40e_ethdev.h
> +++ b/drivers/net/i40e/i40e_ethdev.h
> @@ -426,6 +426,7 @@ struct i40e_pf_vf {
>  	/* version of the virtchnl from VF */
>  	struct virtchnl_version_info version;
>  	uint32_t request_caps; /* offload caps requested from VF */
> +	uint64_t num_mdd_events; /* num of mdd events detected */
> 
>  	/*
>  	 * Variables for store the arrival timestamp of VF messages.
> --
> 2.17.1


  reply	other threads:[~2020-01-17  3:08 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-09 13:59 [dpdk-dev] [PATCH] " taox.zhu
2019-12-09 17:23 ` [dpdk-dev] [DPDK v2] " taox.zhu
2020-01-14 19:43 ` [dpdk-dev] [PATCH v3] " taox.zhu
2020-01-14 11:06   ` Yang, Qiming
2020-01-15 18:47 ` [dpdk-dev] [PATCH v4] " taox.zhu
2020-01-16  2:38   ` Ye Xiaolong
2020-01-16 12:08 ` [dpdk-dev] [PATCH v5] " taox.zhu
2020-01-17 11:24 ` taox.zhu
2020-01-17  3:08   ` Zhu, TaoX [this message]
2020-01-17 11:54 ` [dpdk-dev] [PATCH v7] " taox.zhu
2020-01-17 14:35 ` [dpdk-dev] [PATCH v8] " taox.zhu
2020-01-17  6:33   ` Ye Xiaolong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=60652C6914E08D41B9AA1580751B3CA9C291A5@SHSMSX106.ccr.corp.intel.com \
    --to=taox.zhu@intel.com \
    --cc=beilei.xing@intel.com \
    --cc=dev@dpdk.org \
    --cc=qi.z.zhang@intel.com \
    --cc=qiming.yang@intel.com \
    --cc=xiaolong.ye@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).