summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
diff options
context:
space:
mode:
authorSlawomir Mrozowicz <slawomirx.mrozowicz@intel.com>2025-02-17 10:06:35 +0100
committerTony Nguyen <anthony.l.nguyen@intel.com>2025-07-03 09:39:03 -0700
commitb11aa9614df095ee6f15640873dfa6aaf51dd7ef (patch)
tree71100e05c6d8d0e9c9725fdd7d3e682ca2f79f36 /drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
parentda3ab95f9b0609b1f62142991690b257e6c32bad (diff)
ixgbe: add Tx hang detection unhandled MDD
Add Tx Hang detection due to an unhandled MDD Event. Previously, a malicious VF could disable the entire port causing TX to hang on the E610 card. Those events that caused PF to freeze were not detected as an MDD event and usually required a Tx Hang watchdog timer to catch the suspension, and perform a physical function reset. Implement flows in the affected PF driver in such a way to check the cause of the hang, detect it as an MDD event and log an entry of the malicious VF that caused the Hang. The PF blocks the malicious VF, if it continues to be the source of several MDD events. Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com> Signed-off-by: Slawomir Mrozowicz <slawomirx.mrozowicz@intel.com> Co-developed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Reviewed-by: Simon Horman <horms@kernel.org> Tested-by: Rafal Romanowski <rafal.romanowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_main.c')
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_main.c211
1 files changed, 191 insertions, 20 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 4db8e7136571..f1c51ddbaf9e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9,6 +9,7 @@
#include <linux/string.h>
#include <linux/in.h>
#include <linux/interrupt.h>
+#include <linux/iopoll.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/sctp.h>
@@ -1040,6 +1041,48 @@ static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
return ((head <= tail) ? tail : tail + ring->count) - head;
}
+/**
+ * ixgbe_get_vf_idx - provide VF index number based on queue index
+ * @adapter: pointer to the adapter struct
+ * @queue: Tx queue identifier
+ * @vf: output VF index
+ *
+ * Provide VF index number associated to the input queue.
+ *
+ * Returns: 0 if VF provided or error number.
+ */
+static int ixgbe_get_vf_idx(struct ixgbe_adapter *adapter, u16 queue, u16 *vf)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u8 queue_count;
+ u32 reg;
+
+ if (queue >= adapter->num_tx_queues)
+ return -EINVAL;
+
+ /* Determine number of queues by checking
+ * number of virtual functions
+ */
+ reg = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
+ switch (reg & IXGBE_GCR_EXT_VT_MODE_MASK) {
+ case IXGBE_GCR_EXT_VT_MODE_64:
+ queue_count = IXGBE_64VFS_QUEUES;
+ break;
+ case IXGBE_GCR_EXT_VT_MODE_32:
+ queue_count = IXGBE_32VFS_QUEUES;
+ break;
+ case IXGBE_GCR_EXT_VT_MODE_16:
+ queue_count = IXGBE_16VFS_QUEUES;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ *vf = queue / queue_count;
+
+ return 0;
+}
+
static bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
{
u32 tx_done = ixgbe_get_tx_completed(tx_ring);
@@ -1159,6 +1202,150 @@ void ixgbe_update_rx_ring_stats(struct ixgbe_ring *rx_ring,
}
/**
+ * ixgbe_pf_handle_tx_hang - handle Tx hang on PF
+ * @tx_ring: tx ring number
+ * @next: next ring
+ *
+ * Prints a message containing details about the tx hang.
+ */
+static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring,
+ unsigned int next)
+{
+ struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
+ struct ixgbe_hw *hw = &adapter->hw;
+
+ e_err(drv, "Detected Tx Unit Hang%s\n"
+ " Tx Queue <%d>\n"
+ " TDH, TDT <%x>, <%x>\n"
+ " next_to_use <%x>\n"
+ " next_to_clean <%x>\n"
+ "tx_buffer_info[next_to_clean]\n"
+ " time_stamp <%lx>\n"
+ " jiffies <%lx>\n",
+ ring_is_xdp(tx_ring) ? " (XDP)" : "",
+ tx_ring->queue_index,
+ IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
+ IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
+ tx_ring->next_to_use, next,
+ tx_ring->tx_buffer_info[next].time_stamp, jiffies);
+
+ if (!ring_is_xdp(tx_ring))
+ netif_stop_subqueue(tx_ring->netdev,
+ tx_ring->queue_index);
+}
+
+/**
+ * ixgbe_vf_handle_tx_hang - handle Tx hang on VF
+ * @adapter: structure containing ring specific data
+ * @vf: VF index
+ *
+ * Print a message containing details about malicious driver detection.
+ * Set malicious VF link down if the detection happened several times.
+ */
+static void ixgbe_vf_handle_tx_hang(struct ixgbe_adapter *adapter, u16 vf)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+
+ if (adapter->hw.mac.type != ixgbe_mac_e610)
+ return;
+
+ e_warn(drv,
+ "Malicious Driver Detection tx hang detected on PF %d VF %d MAC: %pM",
+ hw->bus.func, vf, adapter->vfinfo[vf].vf_mac_addresses);
+
+ adapter->tx_hang_count[vf]++;
+ if (adapter->tx_hang_count[vf] == IXGBE_MAX_TX_VF_HANGS) {
+ ixgbe_set_vf_link_state(adapter, vf,
+ IFLA_VF_LINK_STATE_DISABLE);
+ adapter->tx_hang_count[vf] = 0;
+ }
+}
+
+static u32 ixgbe_poll_tx_icache(struct ixgbe_hw *hw, u16 queue, u16 idx)
+{
+ IXGBE_WRITE_REG(hw, IXGBE_TXDESCIC, queue * idx);
+ return IXGBE_READ_REG(hw, IXGBE_TXDESCIC);
+}
+
+/**
+ * ixgbe_check_illegal_queue - search for queue with illegal packet
+ * @adapter: structure containing ring specific data
+ * @queue: queue index
+ *
+ * Check if tx descriptor connected with input queue
+ * contains illegal packet.
+ *
+ * Returns: true if queue contain illegal packet.
+ */
+static bool ixgbe_check_illegal_queue(struct ixgbe_adapter *adapter,
+ u16 queue)
+{
+ u32 hdr_len_reg, mss_len_reg, type_reg;
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 mss_len, header_len, reg;
+
+ for (u16 i = 0; i < IXGBE_MAX_TX_DESCRIPTORS; i++) {
+ /* HW will clear bit IXGBE_TXDESCIC_READY when address
+ * is written to address field. HW will set this bit
+ * when iCache read is done, and data is ready at TIC_DWx.
+ * Set descriptor address.
+ */
+ read_poll_timeout(ixgbe_poll_tx_icache, reg,
+ !(reg & IXGBE_TXDESCIC_READY), 0, 0, false,
+ hw, queue, i);
+
+ /* read tx descriptor access registers */
+ hdr_len_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_VLAN_MACIP_LENS_REG));
+ type_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_TYPE_TUCMD_MLHL));
+ mss_len_reg = IXGBE_READ_REG(hw, IXGBE_TIC_DW2(IXGBE_MSS_L4LEN_IDX));
+
+ /* check if Advanced Context Descriptor */
+ if (FIELD_GET(IXGBE_ADVTXD_DTYP_MASK, type_reg) !=
+ IXGBE_ADVTXD_DTYP_CTXT)
+ continue;
+
+ /* check for illegal MSS and Header length */
+ mss_len = FIELD_GET(IXGBE_ADVTXD_MSS_MASK, mss_len_reg);
+ header_len = FIELD_GET(IXGBE_ADVTXD_HEADER_LEN_MASK,
+ hdr_len_reg);
+ if ((mss_len + header_len) > SZ_16K) {
+ e_warn(probe, "mss len + header len too long\n");
+ return true;
+ }
+ }
+
+ return false;
+}
+
+/**
+ * ixgbe_handle_mdd_event - handle mdd event
+ * @adapter: structure containing ring specific data
+ * @tx_ring: tx descriptor ring to handle
+ *
+ * Reset VF driver if malicious vf detected or
+ * illegal packet in an any queue detected.
+ */
+static void ixgbe_handle_mdd_event(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *tx_ring)
+{
+ u16 vf, q;
+
+ if (adapter->vfinfo && ixgbe_check_mdd_event(adapter)) {
+ /* vf mdd info and malicious vf detected */
+ if (!ixgbe_get_vf_idx(adapter, tx_ring->queue_index, &vf))
+ ixgbe_vf_handle_tx_hang(adapter, vf);
+ } else {
+ /* malicious vf not detected */
+ for (q = 0; q < IXGBE_MAX_TX_QUEUES; q++) {
+ if (ixgbe_check_illegal_queue(adapter, q) &&
+ !ixgbe_get_vf_idx(adapter, q, &vf))
+ /* illegal queue detected */
+ ixgbe_vf_handle_tx_hang(adapter, vf);
+ }
+ }
+}
+
+/**
* ixgbe_clean_tx_irq - Reclaim resources after transmit completes
* @q_vector: structure containing interrupt and ring information
* @tx_ring: tx ring to clean
@@ -1265,26 +1452,10 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
adapter->tx_ipsec += total_ipsec;
if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
- /* schedule immediate reset if we believe we hung */
- struct ixgbe_hw *hw = &adapter->hw;
- e_err(drv, "Detected Tx Unit Hang %s\n"
- " Tx Queue <%d>\n"
- " TDH, TDT <%x>, <%x>\n"
- " next_to_use <%x>\n"
- " next_to_clean <%x>\n"
- "tx_buffer_info[next_to_clean]\n"
- " time_stamp <%lx>\n"
- " jiffies <%lx>\n",
- ring_is_xdp(tx_ring) ? "(XDP)" : "",
- tx_ring->queue_index,
- IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
- IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
- tx_ring->next_to_use, i,
- tx_ring->tx_buffer_info[i].time_stamp, jiffies);
-
- if (!ring_is_xdp(tx_ring))
- netif_stop_subqueue(tx_ring->netdev,
- tx_ring->queue_index);
+ if (adapter->hw.mac.type == ixgbe_mac_e610)
+ ixgbe_handle_mdd_event(adapter, tx_ring);
+
+ ixgbe_pf_handle_tx_hang(tx_ring, i);
e_info(probe,
"tx hang %d detected on queue %d, resetting adapter\n",