linux-kernel - [PATCH 4.4 082/312] net/mlx5: Fix wait_vital for VFs and remove fixed sleep

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Fri,  8 May 2020 14:31:13 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Daniel Jurgens <danielj@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>,
        "David S. Miller" <davem@...emloft.net>
Subject: [PATCH 4.4 082/312] net/mlx5: Fix wait_vital for VFs and remove fixed sleep

From: Daniel Jurgens <danielj@...lanox.com>

commit d57847dc4177c6fd8d950cb533f5edf0eab45b11 upstream.

The device ID for VFs is in a different location than PFs. This results
in the poll always timing out for VFs. There's no good way to read the
VF device ID without using the PF's configuration space.  Switch to waiting
for the health poll to start incrementing. Also remove the 1s sleep
at the beginning.

fixes: 89d44f0a6c73 ('net/mlx5_core: Add pci error handlers to mlx5_core
driver')
Signed-off-by: Daniel Jurgens <danielj@...lanox.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

Signed-off-by: Saeed Mahameed <saeedm@...lanox.com>
Signed-off-by: David S. Miller <davem@...emloft.net>

---
 drivers/net/ethernet/mellanox/mlx5/core/main.c |   41 +++++++++----------------
 1 file changed, 15 insertions(+), 26 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1306,46 +1306,31 @@ void mlx5_disable_device(struct mlx5_cor
 	mlx5_pci_err_detected(dev->pdev, 0);
 }
 
-/* wait for the device to show vital signs. For now we check
- * that we can read the device ID and that the health buffer
- * shows a non zero value which is different than 0xffffffff
+/* wait for the device to show vital signs by waiting
+ * for the health counter to start counting.
  */
-static void wait_vital(struct pci_dev *pdev)
+static int wait_vital(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 	struct mlx5_core_health *health = &dev->priv.health;
 	const int niter = 100;
+	u32 last_count = 0;
 	u32 count;
-	u16 did;
 	int i;
 
-	/* Wait for firmware to be ready after reset */
-	msleep(1000);
-	for (i = 0; i < niter; i++) {
-		if (pci_read_config_word(pdev, 2, &did)) {
-			dev_warn(&pdev->dev, "failed reading config word\n");
-			break;
-		}
-		if (did == pdev->device) {
-			dev_info(&pdev->dev, "device ID correctly read after %d iterations\n", i);
-			break;
-		}
-		msleep(50);
-	}
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
-
 	for (i = 0; i < niter; i++) {
 		count = ioread32be(health->health_counter);
 		if (count && count != 0xffffffff) {
-			dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
-			break;
+			if (last_count && last_count != count) {
+				dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+				return 0;
+			}
+			last_count = count;
 		}
 		msleep(50);
 	}
 
-	if (i == niter)
-		dev_warn(&pdev->dev, "%s-%d: could not read device ID\n", __func__, __LINE__);
+	return -ETIMEDOUT;
 }
 
 static void mlx5_pci_resume(struct pci_dev *pdev)
@@ -1357,7 +1342,11 @@ static void mlx5_pci_resume(struct pci_d
 	dev_info(&pdev->dev, "%s was called\n", __func__);
 
 	pci_save_state(pdev);
-	wait_vital(pdev);
+	err = wait_vital(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+		return;
+	}
 
 	err = mlx5_load_one(dev, priv);
 	if (err)