gpu: nvgpu: sync_framework cleanups

This patch deals with cleanups meant to make things simpler for the
upcoming os abstraction patches for the sync framework. This patch
causes some substantial changes which are listed out as follows.

1) sync_timeline is moved out of gk20a_fence into struct
nvgpu_channel_linux. New function pointers are created to facilitate os
independent methods for enabling/disabling timeline and are now named
as os_fence_framework. These function pointers are located in the struct
os_channel under struct gk20a.

2) construction of the channel_sync require nvgpu_finalize_poweron_linux()
to be invoked before invocations to nvgpu_init_mm_ce_context(). Hence,
these methods are now moved away from gk20a_finalize_poweron() and
invoked after nvgpu_finalize_poweron_linux().

3) sync_fence creation is now delinked from fence construction and move
to the channel_sync_gk20a's  channel_incr methods. These sync_fences are
mainly associated with post_fences.

4) In case userspace requires the sync_fences to be constructed, we
try to obtain an fd before the gk20a_channel_submit_gpfifo() instead of
trying to do that later. This is used to avoid potential after effects
of duplicate work submission due to failure to obtain an unused fd.

JIRA NVGPU-66

Change-Id: I42a3e4e2e692a113b1b36d2b48ab107ae4444dfa
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1678400
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 17 insertions, 4 deletions

diff --git a/drivers/gpu/nvgpu/common/linux/ioctl_ctrl.c b/drivers/gpu/nvgpu/common/linux/ioctl_ctrl.c
index e4b66460..70707a5c 100644
--- a/drivers/gpu/nvgpu/common/linux/ioctl_ctrl.c
+++ b/drivers/gpu/nvgpu/common/linux/ioctl_ctrl.c
@@ -344,10 +344,19 @@ static int gk20a_ctrl_prepare_compressible_read(
         struct gk20a_fence *fence_out = NULL;
         int submit_flags = nvgpu_submit_gpfifo_user_flags_to_common_flags(
                 args->submit_flags);
+        int fd = -1;
 
         fence.id = args->fence.syncpt_id;
         fence.value = args->fence.syncpt_value;
 
+        /* Try and allocate an fd here*/
+        if ((submit_flags & NVGPU_SUBMIT_FLAGS_FENCE_GET)
+                && (submit_flags & NVGPU_SUBMIT_FLAGS_SYNC_FENCE)) {
+                        fd = get_unused_fd_flags(O_RDWR);
+                        if (fd < 0)
+                                return fd;
+        }
+
         ret = gk20a_prepare_compressible_read(l, args->handle,
                         args->request_compbits, args->offset,
                         args->compbits_hoffset, args->compbits_voffset,
@@ -356,20 +365,24 @@ static int gk20a_ctrl_prepare_compressible_read(
                         submit_flags, &fence, &args->valid_compbits,
                         &args->zbc_color, &fence_out);
 
-        if (ret)
+        if (ret) {
+                if (fd != -1)
+                        put_unused_fd(fd);
                 return ret;
+        }
 
         /* Convert fence_out to something we can pass back to user space. */
         if (submit_flags & NVGPU_SUBMIT_FLAGS_FENCE_GET) {
                 if (submit_flags & NVGPU_SUBMIT_FLAGS_SYNC_FENCE) {
                         if (fence_out) {
-                                int fd = gk20a_fence_install_fd(fence_out);
-                                if (fd < 0)
-                                        ret = fd;
+                                ret = gk20a_fence_install_fd(fence_out, fd);
+                                if (ret)
+                                        put_unused_fd(fd);
                                 else
                                         args->fence.fd = fd;
                         } else {
                                 args->fence.fd = -1;
+                                put_unused_fd(fd);
                         }
                 } else {
                         if (fence_out) {