All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jacob Keller <jacob.e.keller@intel.com>
To: Jakub Kicinski <kuba@kernel.org>, David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org,
	Sylwester Dziedziuch <sylwesterx.dziedziuch@intel.com>,
	Mateusz Palczewski <mateusz.palczewski@intel.com>,
	Konrad Jankowski <konrad0.jankowski@intel.com>,
	Jacob Keller <jacob.e.keller@intel.com>
Subject: [PATCH v2 2/3] i40e: Fix VF hang when reset is triggered on another VF
Date: Mon, 24 Oct 2022 03:05:25 -0700	[thread overview]
Message-ID: <20221024100526.1874914-2-jacob.e.keller@intel.com> (raw)
In-Reply-To: <20221024100526.1874914-1-jacob.e.keller@intel.com>

From: Sylwester Dziedziuch <sylwesterx.dziedziuch@intel.com>

When a reset was triggered on one VF with i40e_reset_vf
global PF state __I40E_VF_DISABLE was set on a PF until
the reset finished. If immediately after triggering reset
on one VF there is a request to reset on another
it will cause a hang on VF side because VF will be notified
of incoming reset but the reset will never happen because
of this global state, we will get such error message:

[  +4.890195] iavf 0000:86:02.1: Never saw reset

and VF will hang waiting for the reset to be triggered.

Fix this by introducing new VF state I40E_VF_STATE_RESETTING
that will be set on a VF if it is currently resetting instead of
the global __I40E_VF_DISABLE PF state.

Fixes: 3ba9bcb4b68f ("i40e: add locking around VF reset")
Signed-off-by: Sylwester Dziedziuch <sylwesterx.dziedziuch@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
---
Changes since v1
* Rebased to fix conflicts, sent as series properly
* Added my missing signed-off-by

 .../ethernet/intel/i40e/i40e_virtchnl_pf.c    | 43 ++++++++++++++-----
 .../ethernet/intel/i40e/i40e_virtchnl_pf.h    |  1 +
 2 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 7e9f6a69eb10..72ddcefc45b1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1536,10 +1536,12 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state))
 		return true;
 
-	/* If the VFs have been disabled, this means something else is
-	 * resetting the VF, so we shouldn't continue.
-	 */
-	if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
+	/* Bail out if VFs are disabled. */
+	if (test_bit(__I40E_VF_DISABLE, pf->state))
+		return true;
+
+	/* If VF is being reset already we don't need to continue. */
+	if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
 		return true;
 
 	i40e_trigger_vf_reset(vf, flr);
@@ -1576,7 +1578,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 	i40e_cleanup_reset_vf(vf);
 
 	i40e_flush(hw);
-	clear_bit(__I40E_VF_DISABLE, pf->state);
+	clear_bit(I40E_VF_STATE_RESETTING, &vf->vf_states);
 
 	return true;
 }
@@ -1609,8 +1611,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		return false;
 
 	/* Begin reset on all VFs at once */
-	for (v = 0; v < pf->num_alloc_vfs; v++)
-		i40e_trigger_vf_reset(&pf->vf[v], flr);
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		vf = &pf->vf[v];
+		/* If VF is being reset no need to trigger reset again */
+		if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			i40e_trigger_vf_reset(&pf->vf[v], flr);
+	}
 
 	/* HW requires some time to make sure it can flush the FIFO for a VF
 	 * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
@@ -1626,9 +1632,11 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		 */
 		while (v < pf->num_alloc_vfs) {
 			vf = &pf->vf[v];
-			reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
-			if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
-				break;
+			if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) {
+				reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
+				if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
+					break;
+			}
 
 			/* If the current VF has finished resetting, move on
 			 * to the next VF in sequence.
@@ -1656,6 +1664,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		if (pf->vf[v].lan_vsi_idx == 0)
 			continue;
 
+		/* If VF is reset in another thread just continue */
+		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			continue;
+
 		i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]);
 	}
 
@@ -1667,6 +1679,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 		if (pf->vf[v].lan_vsi_idx == 0)
 			continue;
 
+		/* If VF is reset in another thread just continue */
+		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			continue;
+
 		i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]);
 	}
 
@@ -1676,8 +1692,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
 	mdelay(50);
 
 	/* Finish the reset on each VF */
-	for (v = 0; v < pf->num_alloc_vfs; v++)
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		/* If VF is reset in another thread just continue */
+		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+			continue;
+
 		i40e_cleanup_reset_vf(&pf->vf[v]);
+	}
 
 	i40e_flush(hw);
 	clear_bit(__I40E_VF_DISABLE, pf->state);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index a554d0a0b09b..358bbdb58795 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -39,6 +39,7 @@ enum i40e_vf_states {
 	I40E_VF_STATE_MC_PROMISC,
 	I40E_VF_STATE_UC_PROMISC,
 	I40E_VF_STATE_PRE_ENABLE,
+	I40E_VF_STATE_RESETTING
 };
 
 /* VF capabilities */
-- 
2.38.0.83.gd420dda05763


  reply	other threads:[~2022-10-24 10:05 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-24 10:05 [PATCH v2 1/3] i40e: Fix ethtool rx-flow-hash setting for X722 Jacob Keller
2022-10-24 10:05 ` Jacob Keller [this message]
2022-10-24 10:05 ` [PATCH v2 3/3] i40e: Fix flow-type by setting GL_HASH_INSET registers Jacob Keller
2022-10-24 22:18 ` [PATCH v2 1/3] i40e: Fix ethtool rx-flow-hash setting for X722 Keller, Jacob E
2022-10-25  4:29   ` Jakub Kicinski
2022-10-25 23:30 ` patchwork-bot+netdevbpf

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=20221024100526.1874914-2-jacob.e.keller@intel.com \
    --to=jacob.e.keller@intel.com \
    --cc=davem@davemloft.net \
    --cc=konrad0.jankowski@intel.com \
    --cc=kuba@kernel.org \
    --cc=mateusz.palczewski@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=sylwesterx.dziedziuch@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.