Files
linux-nvgpu/drivers/gpu/nvgpu/common/ce/ce.c
Tejal Kudav b80b2bdab8 gpu: nvgpu: Add CE interrupt handling
a. LAUNCH_ERR
    - Userspace error.
    - Triggered due to faulty launch.
    - Handle using recovery to reset CE engine and teardown the
      faulty channel.

b. An INVALID_CONFIG -
    - Triggered when LCE is mapped to floorswept PCE.
    - On iGPU, we use the default PCE 2 LCE  HW mapping.
      The default mapping can be read from NV_CE_PCE2LCE_CONFIG
      INIT value in CE refmanual.
    - NvGPU driver configures the mapping on dGPUs (currently only on
      Turing).
    - So, this interrupt can only be triggered if there is
      kernel or HW error
    - Recovery ( which is killing the context + engine reset) will
      not help resolve this error.
    - Trigger Quiesce as part of handling.

c. A MTHD_BUFFER_FAULT -
    - NvGPU driver allocates fault buffers for all TSGs or contexts,
      maps them in BAR2 VA space and writes the VA into channel
      instance block.
    - Can be triggered only due to kernel bug
    - Recovery will not help, need quiesce

d. FBUF_CRC_FAIL
    - Triggered when the CRC entry read from the method fault buffer
      does not match the computed CRC from the methods contained in
      the buffer.
    - This indicates memory corruption and is a fatal interrupt which
      at least requires the LCE to be reset before operations can
      start again, if not the entire GPU.
    - Better to quiesce on memory corruption
      CE Engine reset (via recovery) will not help.

e. FBUF_MAGIC_CHK_FAIL
    - Triggered when the MAGIC_NUM entry read from the method fault
      buf does not match NV_CE_MTHD_BUFFER_GLOBAL_HDR_MAGIC_NUM_VAL
    - This indicates memory corruption and is a fatal interrupt
    - Better to quiesce on memory corruption

f. STALLING_DEBUG
    - Only triggered with SW write for debug purposes
    - Debug interrupt, currently ignored

Move launch error handling from GP10b to GV11b HAL as -
1. LAUNCHERR_REPORT errcode METHOD_BUFFER_ACCESS_FAULT is not
   defined on Pascal
2. We do not support GP10b on dev-main ToT

JIRA NVGPU-8102

Change-Id: Idc84119bc23b5e85f3479fe62cc8720e98b627a5
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2678893
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
2022-03-14 17:12:14 -07:00

109 lines
3.2 KiB
C

/*
* Copyright (c) 2018-2022, NVIDIA CORPORATION. All rights reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
#include <nvgpu/types.h>
#include <nvgpu/gk20a.h>
#include <nvgpu/engines.h>
#include <nvgpu/device.h>
#include <nvgpu/ce.h>
#include <nvgpu/power_features/cg.h>
#include <nvgpu/cic_mon.h>
#include <nvgpu/mc.h>
#include <nvgpu/rc.h>
#include <nvgpu/nvgpu_init.h>
int nvgpu_ce_init_support(struct gk20a *g)
{
int err = 0;
if (g->ops.ce.set_pce2lce_mapping != NULL) {
g->ops.ce.set_pce2lce_mapping(g);
}
/*
* Bug 1895019
* Each time PCE2LCE config is updated and if it happens to
* map a LCE which was previously unmapped, then ELCG would have turned
* off the clock to the unmapped LCE and when the LCE config is updated,
* a race occurs between the config update and ELCG turning on the clock
* to that LCE, this might result in LCE dropping the config update.
* To avoid such a race, each time PCE2LCE config is updated toggle
* resets for all LCEs.
*/
err = nvgpu_mc_reset_devtype(g, NVGPU_DEVTYPE_LCE);
if (err != 0) {
nvgpu_err(g, "NVGPU_DEVTYPE_LCE reset failed");
return err;
}
nvgpu_cg_slcg_ce2_load_enable(g);
nvgpu_cg_blcg_ce_load_enable(g);
#if defined(CONFIG_NVGPU_NON_FUSA)
nvgpu_cg_elcg_ce_load_enable(g);
#endif
if (g->ops.ce.init_prod_values != NULL) {
g->ops.ce.init_prod_values(g);
}
#ifdef CONFIG_NVGPU_NONSTALL_INTR
if (g->ops.ce.init_hw != NULL) {
g->ops.ce.init_hw(g);
}
#endif
if (g->ops.ce.intr_enable != NULL) {
g->ops.ce.intr_enable(g, true);
}
/** Enable interrupts at MC level */
nvgpu_cic_mon_intr_stall_unit_config(g, NVGPU_CIC_INTR_UNIT_CE, NVGPU_CIC_INTR_ENABLE);
#ifdef CONFIG_NVGPU_NONSTALL_INTR
nvgpu_cic_mon_intr_nonstall_unit_config(g, NVGPU_CIC_INTR_UNIT_CE, NVGPU_CIC_INTR_ENABLE);
#endif
return 0;
}
void nvgpu_ce_stall_isr(struct gk20a *g, u32 inst_id, u32 pri_base)
{
bool needs_rc = false;
bool needs_quiesce = false;
if (g->ops.ce.isr_stall != NULL) {
g->ops.ce.isr_stall(g, inst_id, pri_base, &needs_rc,
&needs_quiesce);
}
if (needs_quiesce) {
nvgpu_sw_quiesce(g);
}
if (needs_rc) {
nvgpu_log(g, gpu_dbg_intr,
"Recovery needed to handle CE interrupt.");
nvgpu_rc_ce_fault(g, inst_id);
}
}