summaryrefslogtreecommitdiffstats
path: root/drivers/misc/habanalabs/context.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-05-07 22:39:22 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2019-05-07 22:39:22 +0200
commitf678d6da749983791850876e3421e7c48a0a7127 (patch)
tree553f818ef8e73bf9d6b1e53bdf623240c1279ffb /drivers/misc/habanalabs/context.c
parentMerge tag 'char-misc-5.2-rc1-part1' of git://git.kernel.org/pub/scm/linux/ker... (diff)
parentintel_th: msu: Add current window tracking (diff)
downloadlinux-f678d6da749983791850876e3421e7c48a0a7127.tar.xz
linux-f678d6da749983791850876e3421e7c48a0a7127.zip
Merge tag 'char-misc-5.2-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc
Pull char/misc update part 2 from Greg KH: "Here is the "real" big set of char/misc driver patches for 5.2-rc1 Loads of different driver subsystem stuff in here, all over the places: - thunderbolt driver updates - habanalabs driver updates - nvmem driver updates - extcon driver updates - intel_th driver updates - mei driver updates - coresight driver updates - soundwire driver cleanups and updates - fastrpc driver updates - other minor driver updates - chardev minor fixups Feels like this tree is getting to be a dumping ground of "small driver subsystems" these days. Which is fine with me, if it makes things easier for those subsystem maintainers. All of these have been in linux-next for a while with no reported issues" * tag 'char-misc-5.2-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (255 commits) intel_th: msu: Add current window tracking intel_th: msu: Add a sysfs attribute to trigger window switch intel_th: msu: Correct the block wrap detection intel_th: Add switch triggering support intel_th: gth: Factor out trace start/stop intel_th: msu: Factor out pipeline draining intel_th: msu: Switch over to scatterlist intel_th: msu: Replace open-coded list_{first,last,next}_entry variants intel_th: Only report useful IRQs to subdevices intel_th: msu: Start handling IRQs intel_th: pci: Use MSI interrupt signalling intel_th: Communicate IRQ via resource intel_th: Add "rtit" source device intel_th: Skip subdevices if their MMIO is missing intel_th: Rework resource passing between glue layers and core intel_th: SPDX-ify the documentation intel_th: msu: Fix single mode with IOMMU coresight: funnel: Support static funnel dt-bindings: arm: coresight: Unify funnel DT binding coresight: replicator: Add new device id for static replicator ...
Diffstat (limited to 'drivers/misc/habanalabs/context.c')
-rw-r--r--drivers/misc/habanalabs/context.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c
index 619ace1c4ef7..4804cdcf4c48 100644
--- a/drivers/misc/habanalabs/context.c
+++ b/drivers/misc/habanalabs/context.c
@@ -106,8 +106,8 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
ctx->cs_sequence = 1;
spin_lock_init(&ctx->cs_lock);
- atomic_set(&ctx->thread_restore_token, 1);
- ctx->thread_restore_wait_token = 0;
+ atomic_set(&ctx->thread_ctx_switch_token, 1);
+ ctx->thread_ctx_switch_wait_token = 0;
if (is_kernel_ctx) {
ctx->asid = HL_KERNEL_ASID_ID; /* KMD gets ASID 0 */