From: Petr Oros <[email protected]>
When the link goes down the processing loop drops every outstanding
request, and a request whose timestamp is not ready yet is freed
without reading the PHY slot. The hardware completes the capture a
moment later, the orphaned ready bit blocks the port interrupt until
the next link-up sweep, and the freed index can meanwhile be reused
by a new request whose slot the hardware then overwrites. Captured on
a reproducer as ready bits with no in_use owner right after a link
bounce.
Stop dropping on link down. Mark the outstanding requests stale so
their completions are read and discarded, reject new requests while
the link is down, and free a not yet ready slot only after the two
second timeout. This way an index is never reused while the hardware
can still write it and never left untracked while a completion can
still arrive.
To avoid an IRQ storm in the event that we really do have a stale packet
that is not timestamped, modify ice_ptp_tx_tstamps_pending() to ignore
stale timestamps when checking for whether to re-arm the IRQ from the
miscellaneous thread function. Instead, only check for stale packets in the
auxiliary work thread. This way we do not check in a tight loop waiting for
a timestamp that may never come.
This effectively reverts commit fcc2cef37fed ("ice/ptp: fix the PTP worker
retrying indefinitely if the link went down"), which tried to release an
index before this 2 second wait period.
Fixes: fcc2cef37fed ("ice/ptp: fix the PTP worker retrying indefinitely if the
link went down")
Suggested-by: Jacob Keller <[email protected]>
Signed-off-by: Petr Oros <[email protected]>
Signed-off-by: Jacob Keller <[email protected]>
Reviewed-by: Maciek Machnikowski <[email protected]>
---
drivers/net/ethernet/intel/ice/ice_ptp.h | 8 ++++--
drivers/net/ethernet/intel/ice/ice_main.c | 2 +-
drivers/net/ethernet/intel/ice/ice_ptp.c | 44 +++++++++++++++----------------
3 files changed, 28 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h
b/drivers/net/ethernet/intel/ice/ice_ptp.h
index da2003ba3bb0..13158a9319fb 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -132,6 +132,9 @@ struct ice_ptp_tx {
#define INDEX_PER_PORT_E82X 16
#define INDEX_PER_PORT 64
+/* Maximum number of timestamp indexes across all devices */
+#define INDEX_PER_PORT_MAX INDEX_PER_PORT
+
/**
* struct ice_ptp_port - data used to initialize an external port for PTP
*
@@ -316,7 +319,7 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8
idx);
void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx);
void ice_ptp_process_ts(struct ice_pf *pf);
irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf);
-bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf);
+bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf, bool in_irq);
u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
struct ptp_system_timestamp *sts);
@@ -364,7 +367,8 @@ static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
return IRQ_HANDLED;
}
-static inline bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf)
+static inline bool
+ice_ptp_tx_tstamps_pending(struct ice_pf *pf, bool in_irq)
{
return false;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c
b/drivers/net/ethernet/intel/ice/ice_main.c
index bb631ae9e67d..c84d63b8d261 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3248,7 +3248,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int
__always_unused irq, void *data)
ice_irq_dynamic_ena(hw, NULL, NULL);
ice_flush(hw);
- if (ice_ptp_tx_tstamps_pending(pf)) {
+ if (ice_ptp_tx_tstamps_pending(pf, true)) {
/* If any new Tx timestamps happened while in interrupt,
* re-arm the interrupt to trigger it again.
*/
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c
b/drivers/net/ethernet/intel/ice/ice_ptp.c
index a049dc7a2241..1a9bf8839404 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -364,9 +364,12 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64
in_tstamp)
static bool
ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx)
{
+ struct ice_ptp_port *ptp_port =
+ container_of(tx, struct ice_ptp_port, tx);
+
lockdep_assert_held(&tx->lock);
- return tx->init && !tx->calibrating;
+ return tx->init && !tx->calibrating && ptp_port->link_up;
}
/**
@@ -563,7 +566,6 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx)
struct ice_pf *pf;
struct ice_hw *hw;
u64 tstamp_ready;
- bool link_up;
int err;
u8 idx;
@@ -581,14 +583,11 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx
*tx)
return;
}
- /* Drop packets if the link went down */
- link_up = ptp_port->link_up;
-
for_each_set_bit(idx, tx->in_use, tx->len) {
struct skb_shared_hwtstamps shhwtstamps = {};
u8 phy_idx = idx + tx->offset;
u64 raw_tstamp = 0, tstamp;
- bool drop_ts = !link_up;
+ bool drop_ts = false;
struct sk_buff *skb;
/* Drop packets which have waited for more than 2 seconds */
@@ -1372,6 +1371,9 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
if (pf->hw.reset_ongoing)
return;
+ if (!linkup)
+ ice_ptp_mark_tx_tracker_stale(&ptp_port->tx);
+
if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
test_bit(ICE_FLAG_DPLL, pf->flags)) {
int pin, err;
@@ -2763,28 +2765,29 @@ void ice_ptp_process_ts(struct ice_pf *pf)
}
}
-static bool ice_port_has_timestamps(struct ice_ptp_tx *tx)
+static bool ice_port_has_timestamps(struct ice_ptp_tx *tx, bool in_irq)
{
- bool more_timestamps;
+ DECLARE_BITMAP(tstamps, INDEX_PER_PORT_MAX) = {};
scoped_guard(spinlock_irqsave, &tx->lock) {
if (!tx->init)
return false;
- more_timestamps = !bitmap_empty(tx->in_use, tx->len);
+ if (in_irq)
+ return bitmap_andnot(tstamps, tx->in_use, tx->stale,
tx->len);
+ else
+ return !bitmap_empty(tx->in_use, tx->len);
}
-
- return more_timestamps;
}
-static bool ice_any_port_has_timestamps(struct ice_pf *pf)
+static bool ice_any_port_has_timestamps(struct ice_pf *pf, bool in_irq)
{
bool have_tstamps = false;
struct ice_ptp_port *port;
rcu_read_lock();
list_for_each_entry_rcu(port, &pf->adapter->ports.list, list_node) {
- if (ice_port_has_timestamps(&port->tx)) {
+ if (ice_port_has_timestamps(&port->tx, in_irq)) {
have_tstamps = true;
break;
}
@@ -2794,7 +2797,7 @@ static bool ice_any_port_has_timestamps(struct ice_pf *pf)
return have_tstamps;
}
-bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf)
+bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf, bool in_irq)
{
struct ice_hw *hw = &pf->hw;
int ret;
@@ -2804,11 +2807,11 @@ bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf)
case ICE_PTP_TX_INTERRUPT_NONE:
return false;
case ICE_PTP_TX_INTERRUPT_SELF:
- if (ice_port_has_timestamps(&pf->ptp.port.tx))
+ if (ice_port_has_timestamps(&pf->ptp.port.tx, in_irq))
return true;
break;
case ICE_PTP_TX_INTERRUPT_ALL:
- if (ice_any_port_has_timestamps(pf))
+ if (ice_any_port_has_timestamps(pf, in_irq))
return true;
break;
default:
@@ -2884,7 +2887,7 @@ irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
/* E830 can read timestamps in the top half using rd32() */
ice_ptp_process_ts(pf);
- if (ice_ptp_tx_tstamps_pending(pf)) {
+ if (ice_ptp_tx_tstamps_pending(pf, true)) {
/* Process outstanding Tx timestamps. If there
* is more work, re-arm the interrupt to trigger again.
*/
@@ -2914,7 +2917,6 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct
ice_pf *pf)
{
struct device *dev = ice_pf_to_dev(pf);
struct ice_hw *hw = &pf->hw;
- int ret;
if (!pf->ptp.port.tx.has_ready_bitmap)
return;
@@ -2922,11 +2924,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct
ice_pf *pf)
if (!ice_pf_src_tmr_owned(pf))
return;
- ret = ice_check_phy_tx_tstamp_ready(hw);
- if (ret < 0) {
- dev_dbg(dev, "PTP periodic task unable to read PHY timestamp
ready bitmap, err %d\n",
- ret);
- } else if (ret) {
+ if (ice_ptp_tx_tstamps_pending(pf, false)) {
dev_dbg(dev, "PTP periodic task detected waiting timestamps.
Triggering Tx timestamp interrupt now.\n");
wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
--
2.55.0.814.gc42f45431d0f
