summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/xe/xe_device.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/xe/xe_device.c')
-rw-r--r--drivers/gpu/drm/xe/xe_device.c127
1 files changed, 75 insertions, 52 deletions
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 9e4773a17ef8..c7d373c70f0f 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -8,6 +8,7 @@
#include <linux/aperture.h>
#include <linux/delay.h>
#include <linux/fault-inject.h>
+#include <linux/iopoll.h>
#include <linux/units.h>
#include <drm/drm_atomic_helper.h>
@@ -45,11 +46,13 @@
#include "xe_hwmon.h"
#include "xe_i2c.h"
#include "xe_irq.h"
+#include "xe_late_bind_fw.h"
#include "xe_mmio.h"
#include "xe_module.h"
#include "xe_nvm.h"
#include "xe_oa.h"
#include "xe_observation.h"
+#include "xe_pagefault.h"
#include "xe_pat.h"
#include "xe_pcode.h"
#include "xe_pm.h"
@@ -435,7 +438,7 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
err = ttm_device_init(&xe->ttm, &xe_ttm_funcs, xe->drm.dev,
xe->drm.anon_inode->i_mapping,
- xe->drm.vma_offset_manager, false, false);
+ xe->drm.vma_offset_manager, 0);
if (WARN_ON(err))
goto err;
@@ -457,6 +460,8 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
if (err)
goto err;
+ xe_validation_device_init(&xe->val);
+
init_waitqueue_head(&xe->ufence_wq);
init_rwsem(&xe->usm.lock);
@@ -530,7 +535,7 @@ static bool xe_driver_flr_disabled(struct xe_device *xe)
* re-init and saving/restoring (or re-populating) the wiped memory. Since we
* perform the FLR as the very last action before releasing access to the HW
* during the driver release flow, we don't attempt recovery at all, because
- * if/when a new instance of i915 is bound to the device it will do a full
+ * if/when a new instance of Xe is bound to the device it will do a full
* re-init anyway.
*/
static void __xe_driver_flr(struct xe_device *xe)
@@ -627,16 +632,22 @@ mask_err:
return err;
}
-static bool verify_lmem_ready(struct xe_device *xe)
+static int lmem_initializing(struct xe_device *xe)
{
- u32 val = xe_mmio_read32(xe_root_tile_mmio(xe), GU_CNTL) & LMEM_INIT;
+ if (xe_mmio_read32(xe_root_tile_mmio(xe), GU_CNTL) & LMEM_INIT)
+ return 0;
- return !!val;
+ if (signal_pending(current))
+ return -EINTR;
+
+ return 1;
}
static int wait_for_lmem_ready(struct xe_device *xe)
{
- unsigned long timeout, start;
+ const unsigned long TIMEOUT_SEC = 60;
+ unsigned long prev_jiffies;
+ int initializing;
if (!IS_DGFX(xe))
return 0;
@@ -644,54 +655,50 @@ static int wait_for_lmem_ready(struct xe_device *xe)
if (IS_SRIOV_VF(xe))
return 0;
- if (verify_lmem_ready(xe))
+ if (!lmem_initializing(xe))
return 0;
drm_dbg(&xe->drm, "Waiting for lmem initialization\n");
+ prev_jiffies = jiffies;
- start = jiffies;
- timeout = start + secs_to_jiffies(60); /* 60 sec! */
-
- do {
- if (signal_pending(current))
- return -EINTR;
-
- /*
- * The boot firmware initializes local memory and
- * assesses its health. If memory training fails,
- * the punit will have been instructed to keep the GT powered
- * down.we won't be able to communicate with it
- *
- * If the status check is done before punit updates the register,
- * it can lead to the system being unusable.
- * use a timeout and defer the probe to prevent this.
- */
- if (time_after(jiffies, timeout)) {
- drm_dbg(&xe->drm, "lmem not initialized by firmware\n");
- return -EPROBE_DEFER;
- }
-
- msleep(20);
-
- } while (!verify_lmem_ready(xe));
+ /*
+ * The boot firmware initializes local memory and
+ * assesses its health. If memory training fails,
+ * the punit will have been instructed to keep the GT powered
+ * down.we won't be able to communicate with it
+ *
+ * If the status check is done before punit updates the register,
+ * it can lead to the system being unusable.
+ * use a timeout and defer the probe to prevent this.
+ */
+ poll_timeout_us(initializing = lmem_initializing(xe),
+ initializing <= 0,
+ 20 * USEC_PER_MSEC, TIMEOUT_SEC * USEC_PER_SEC, true);
+ if (initializing < 0)
+ return initializing;
+
+ if (initializing) {
+ drm_dbg(&xe->drm, "lmem not initialized by firmware\n");
+ return -EPROBE_DEFER;
+ }
drm_dbg(&xe->drm, "lmem ready after %ums",
- jiffies_to_msecs(jiffies - start));
+ jiffies_to_msecs(jiffies - prev_jiffies));
return 0;
}
ALLOW_ERROR_INJECTION(wait_for_lmem_ready, ERRNO); /* See xe_pci_probe() */
-static void sriov_update_device_info(struct xe_device *xe)
+static void vf_update_device_info(struct xe_device *xe)
{
+ xe_assert(xe, IS_SRIOV_VF(xe));
/* disable features that are not available/applicable to VFs */
- if (IS_SRIOV_VF(xe)) {
- xe->info.probe_display = 0;
- xe->info.has_heci_cscfi = 0;
- xe->info.has_heci_gscfi = 0;
- xe->info.skip_guc_pc = 1;
- xe->info.skip_pcode = 1;
- }
+ xe->info.probe_display = 0;
+ xe->info.has_heci_cscfi = 0;
+ xe->info.has_heci_gscfi = 0;
+ xe->info.has_late_bind = 0;
+ xe->info.skip_guc_pc = 1;
+ xe->info.skip_pcode = 1;
}
static int xe_device_vram_alloc(struct xe_device *xe)
@@ -732,7 +739,8 @@ int xe_device_probe_early(struct xe_device *xe)
xe_sriov_probe_early(xe);
- sriov_update_device_info(xe);
+ if (IS_SRIOV_VF(xe))
+ vf_update_device_info(xe);
err = xe_pcode_probe_early(xe);
if (err || xe_survivability_mode_is_requested(xe)) {
@@ -775,6 +783,8 @@ static int probe_has_flat_ccs(struct xe_device *xe)
return 0;
gt = xe_root_mmio_gt(xe);
+ if (!gt)
+ return 0;
fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
if (!fw_ref)
@@ -887,6 +897,10 @@ int xe_device_probe(struct xe_device *xe)
return err;
}
+ err = xe_pagefault_init(xe);
+ if (err)
+ return err;
+
if (xe->tiles->media_gt &&
XE_GT_WA(xe->tiles->media_gt, 15015404425_disable))
XE_DEVICE_WA_DISABLE(xe, 15015404425);
@@ -901,6 +915,10 @@ int xe_device_probe(struct xe_device *xe)
if (err)
return err;
+ err = xe_late_bind_init(&xe->late_bind);
+ if (err)
+ return err;
+
err = xe_oa_init(xe);
if (err)
return err;
@@ -950,7 +968,7 @@ int xe_device_probe(struct xe_device *xe)
xe_vsec_init(xe);
- err = xe_sriov_late_init(xe);
+ err = xe_sriov_init_late(xe);
if (err)
goto err_unregister_display;
@@ -980,16 +998,16 @@ void xe_device_shutdown(struct xe_device *xe)
drm_dbg(&xe->drm, "Shutting down device\n");
- if (xe_driver_flr_disabled(xe)) {
- xe_display_pm_shutdown(xe);
+ xe_display_pm_shutdown(xe);
- xe_irq_suspend(xe);
+ xe_irq_suspend(xe);
- for_each_gt(gt, xe, id)
- xe_gt_shutdown(gt);
+ for_each_gt(gt, xe, id)
+ xe_gt_shutdown(gt);
- xe_display_pm_shutdown_late(xe);
- } else {
+ xe_display_pm_shutdown_late(xe);
+
+ if (!xe_driver_flr_disabled(xe)) {
/* BOOM! */
__xe_driver_flr(xe);
}
@@ -1051,6 +1069,8 @@ void xe_device_l2_flush(struct xe_device *xe)
unsigned int fw_ref;
gt = xe_root_mmio_gt(xe);
+ if (!gt)
+ return;
if (!XE_GT_WA(gt, 16023588340))
return;
@@ -1062,7 +1082,7 @@ void xe_device_l2_flush(struct xe_device *xe)
spin_lock(&gt->global_invl_lock);
xe_mmio_write32(&gt->mmio, XE2_GLOBAL_INVAL, 0x1);
- if (xe_mmio_wait32(&gt->mmio, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true))
+ if (xe_mmio_wait32(&gt->mmio, XE2_GLOBAL_INVAL, 0x1, 0x0, 1000, NULL, true))
xe_gt_err_once(gt, "Global invalidation timeout\n");
spin_unlock(&gt->global_invl_lock);
@@ -1096,6 +1116,9 @@ void xe_device_td_flush(struct xe_device *xe)
return;
root_gt = xe_root_mmio_gt(xe);
+ if (!root_gt)
+ return;
+
if (XE_GT_WA(root_gt, 16023588340)) {
/* A transient flush is not sufficient: flush the L2 */
xe_device_l2_flush(xe);
@@ -1199,7 +1222,7 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
*
* /sys/bus/pci/devices/<device>/survivability_mode
*
- * - Admin/userpsace consumer can use firmware flashing tools like fwupd to flash
+ * - Admin/userspace consumer can use firmware flashing tools like fwupd to flash
* firmware and restore device to normal operation.
*/
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-27 13:03:22 +0000