| Message ID | 20240325232039.76836-3-mschmidt@redhat.com |
|---|---|
| State | Accepted |
| Delegated to: | Anthony Nguyen |
| Headers | show |
| Series | ice: lighter locking for PTP time reading | expand |
> -----Original Message----- > From: Intel-wired-lan <intel-wired-lan-bounces@osuosl.org> On Behalf Of Michal Schmidt > Sent: Tuesday, March 26, 2024 4:51 AM > To: intel-wired-lan@lists.osuosl.org > Cc: Jiri Pirko <jiri@resnulli.us>; Temerkhanov, Sergey <sergey.temerkhanov@intel.com>; netdev@vger.kernel.org; Richard Cochran <richardcochran@gmail.com>; Kubalewski, Arkadiusz <arkadiusz.kubalewski@intel.com>; Kolacinski, Karol <karol.kolacinski@intel.com>; Marcin Szycik <marcin.szycik@linux.intel.com>; Nguyen, Anthony L <anthony.l.nguyen@intel.com>; Kitszel, Przemyslaw <przemyslaw.kitszel@intel.com>; Keller, Jacob E <jacob.e.keller@intel.com> > Subject: [Intel-wired-lan] [PATCH net-next v4 2/3] ice: avoid the PTP hardware semaphore in gettimex64 path > > The PTP hardware semaphore (PFTSYN_SEM) is used to synchronize operations that program the PTP timers. The operations involve issuing commands to the sideband queue. The E810 does not have a hardware sideband queue, so the admin queue is used. The admin queue is slow. > I have observed delays in hundreds of milliseconds waiting for ice_sq_done. > > When phc2sys reads the time from the ice PTP clock and PFTSYN_SEM is held by a task performing one of the slow operations, ice_ptp_lock can easily time out. phc2sys gets -EBUSY and the kernel prints: > ice 0000:XX:YY.0: PTP failed to get time These messages appear once every few seconds, causing log spam. > > The E810 datasheet recommends an algorithm for reading the upper 64 bits of the GLTSYN_TIME register. It matches what's implemented in ice_ptp_read_src_clk_reg. It is robust against wrap-around, but not necessarily against the concurrent setting of the register (with GLTSYN_CMD_{INIT,ADJ}_TIME commands). Perhaps that's why > ice_ptp_gettimex64 also takes PFTSYN_SEM. > > The race with time setters can be prevented without relying on the PTP hardware semaphore. Using the "ice_adapter" from the previous patch, we can have a common spinlock for the PFs that share the clock hardware. > It will protect the reading and writing to the GLTSYN_TIME register. > The writing is performed indirectly, by the hardware, as a result of the driver writing GLTSYN_CMD_SYNC in ice_ptp_exec_tmr_cmd. I wasn't sure if the ice_flush there is enough to make sure GLTSYN_TIME has been updated, but it works well in my testing. > > My test code can be seen here: > https://gitlab.com/mschmidt2/linux/-/commits/ice-ptp-host-side-lock-10 > It consists of: > - kernel threads reading the time in a busy loop and looking at the > deltas between consecutive values, reporting new maxima. > - a shell script that sets the time repeatedly; > - a bpftrace probe to produce a histogram of the measured deltas. > Without the spinlock ptp_gltsyn_time_lock, it is easy to see tearing. > Deltas in the [2G, 4G) range appear in the histograms. > With the spinlock added, there is no tearing and the biggest delta I saw was in the range [1M, 2M), that is under 2 ms. > > Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> > Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> > Signed-off-by: Michal Schmidt <mschmidt@redhat.com> > --- > drivers/net/ethernet/intel/ice/ice_adapter.c | 2 ++ drivers/net/ethernet/intel/ice/ice_adapter.h | 6 ++++++ > drivers/net/ethernet/intel/ice/ice_ptp.c | 8 +------- > drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 3 +++ > 4 files changed, 12 insertions(+), 7 deletions(-) > Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c index f00ab998e853..52d15ef7f4b1 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.c +++ b/drivers/net/ethernet/intel/ice/ice_adapter.c @@ -6,6 +6,7 @@ #include <linux/mutex.h> #include <linux/pci.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/xarray.h> #include "ice_adapter.h" @@ -35,6 +36,7 @@ static struct ice_adapter *ice_adapter_new(void) if (!adapter) return NULL; + spin_lock_init(&adapter->ptp_gltsyn_time_lock); refcount_set(&adapter->refcount, 1); return adapter; diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h index cb5a02eb24c1..9d11014ec02f 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.h +++ b/drivers/net/ethernet/intel/ice/ice_adapter.h @@ -4,15 +4,21 @@ #ifndef _ICE_ADAPTER_H_ #define _ICE_ADAPTER_H_ +#include <linux/spinlock_types.h> #include <linux/refcount_types.h> struct pci_dev; /** * struct ice_adapter - PCI adapter resources shared across PFs + * @ptp_gltsyn_time_lock: Spinlock protecting access to the GLTSYN_TIME + * register of the PTP clock. * @refcount: Reference count. struct ice_pf objects hold the references. */ struct ice_adapter { + /* For access to the GLTSYN_TIME register */ + spinlock_t ptp_gltsyn_time_lock; + refcount_t refcount; }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index c11eba07283c..0875f37add78 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -374,6 +374,7 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) u8 tmr_idx; tmr_idx = ice_get_ptp_src_clock_index(hw); + guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock); /* Read the system timestamp pre PHC read */ ptp_read_system_prets(sts); @@ -1925,15 +1926,8 @@ ice_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts, struct ptp_system_timestamp *sts) { struct ice_pf *pf = ptp_info_to_pf(info); - struct ice_hw *hw = &pf->hw; - - if (!ice_ptp_lock(hw)) { - dev_err(ice_pf_to_dev(pf), "PTP failed to get time\n"); - return -EBUSY; - } ice_ptp_read_time(pf, ts, sts); - ice_ptp_unlock(hw); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 187ce9b54e1a..2b9423a173bb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -274,6 +274,9 @@ void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) */ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + + guard(spinlock)(&pf->adapter->ptp_gltsyn_time_lock); wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD); ice_flush(hw); }
The PTP hardware semaphore (PFTSYN_SEM) is used to synchronize operations that program the PTP timers. The operations involve issuing commands to the sideband queue. The E810 does not have a hardware sideband queue, so the admin queue is used. The admin queue is slow. I have observed delays in hundreds of milliseconds waiting for ice_sq_done. When phc2sys reads the time from the ice PTP clock and PFTSYN_SEM is held by a task performing one of the slow operations, ice_ptp_lock can easily time out. phc2sys gets -EBUSY and the kernel prints: ice 0000:XX:YY.0: PTP failed to get time These messages appear once every few seconds, causing log spam. The E810 datasheet recommends an algorithm for reading the upper 64 bits of the GLTSYN_TIME register. It matches what's implemented in ice_ptp_read_src_clk_reg. It is robust against wrap-around, but not necessarily against the concurrent setting of the register (with GLTSYN_CMD_{INIT,ADJ}_TIME commands). Perhaps that's why ice_ptp_gettimex64 also takes PFTSYN_SEM. The race with time setters can be prevented without relying on the PTP hardware semaphore. Using the "ice_adapter" from the previous patch, we can have a common spinlock for the PFs that share the clock hardware. It will protect the reading and writing to the GLTSYN_TIME register. The writing is performed indirectly, by the hardware, as a result of the driver writing GLTSYN_CMD_SYNC in ice_ptp_exec_tmr_cmd. I wasn't sure if the ice_flush there is enough to make sure GLTSYN_TIME has been updated, but it works well in my testing. My test code can be seen here: https://gitlab.com/mschmidt2/linux/-/commits/ice-ptp-host-side-lock-10 It consists of: - kernel threads reading the time in a busy loop and looking at the deltas between consecutive values, reporting new maxima. - a shell script that sets the time repeatedly; - a bpftrace probe to produce a histogram of the measured deltas. Without the spinlock ptp_gltsyn_time_lock, it is easy to see tearing. Deltas in the [2G, 4G) range appear in the histograms. With the spinlock added, there is no tearing and the biggest delta I saw was in the range [1M, 2M), that is under 2 ms. Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Signed-off-by: Michal Schmidt <mschmidt@redhat.com> --- drivers/net/ethernet/intel/ice/ice_adapter.c | 2 ++ drivers/net/ethernet/intel/ice/ice_adapter.h | 6 ++++++ drivers/net/ethernet/intel/ice/ice_ptp.c | 8 +------- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 3 +++ 4 files changed, 12 insertions(+), 7 deletions(-)