| Message ID | 20171105110118.15142-11-mperttunen@nvidia.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 05.11.2017 14:01, Mikko Perttunen wrote: > Add an option to host1x_channel_request to interruptibly wait for a > free channel. This allows IOCTLs that acquire a channel to block > the userspace. > Wouldn't it be more optimal to request channel and block after job's pining, when all patching and checks are completed? Note that right now we have locking around submission in DRM, which I suppose should go away by making locking fine grained. Or maybe it would be more optimal to just iterate over channels, like I suggested before [0]? [0] https://github.com/cyndis/linux/commit/9e6d87f40afb01fbe13ba65c73cb617bdfcd80b2#commitcomment-25012960 > Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com> > --- > drivers/gpu/drm/tegra/drm.c | 9 +++++---- > drivers/gpu/drm/tegra/gr2d.c | 6 +++--- > drivers/gpu/drm/tegra/gr3d.c | 6 +++--- > drivers/gpu/host1x/channel.c | 40 ++++++++++++++++++++++++++++++---------- > drivers/gpu/host1x/channel.h | 1 + > include/linux/host1x.h | 2 +- > 6 files changed, 43 insertions(+), 21 deletions(-) > > diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c > index 658bc8814f38..19f77c1a76c0 100644 > --- a/drivers/gpu/drm/tegra/drm.c > +++ b/drivers/gpu/drm/tegra/drm.c > @@ -389,7 +389,8 @@ static int host1x_waitchk_copy_from_user(struct host1x_waitchk *dest, > * Request a free hardware host1x channel for this user context, or if the > * context already has one, bump its refcount. > * > - * Returns 0 on success, or -EBUSY if there were no free hardware channels. > + * Returns 0 on success, -EINTR if wait for a free channel was interrupted, > + * or other error. > */ > int tegra_drm_context_get_channel(struct tegra_drm_context *context) > { > @@ -398,10 +399,10 @@ int tegra_drm_context_get_channel(struct tegra_drm_context *context) > mutex_lock(&context->lock); > > if (context->pending_jobs == 0) { > - context->channel = host1x_channel_request(client->dev); > - if (!context->channel) { > + context->channel = host1x_channel_request(client->dev, true); > + if (IS_ERR(context->channel)) { > mutex_unlock(&context->lock); > - return -EBUSY; > + return PTR_ERR(context->channel); > } > } > > diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c > index 3db3bcac48b9..c1853402f69b 100644 > --- a/drivers/gpu/drm/tegra/gr2d.c > +++ b/drivers/gpu/drm/tegra/gr2d.c > @@ -32,9 +32,9 @@ static int gr2d_init(struct host1x_client *client) > unsigned long flags = HOST1X_SYNCPT_HAS_BASE; > struct gr2d *gr2d = to_gr2d(drm); > > - gr2d->channel = host1x_channel_request(client->dev); > - if (!gr2d->channel) > - return -ENOMEM; > + gr2d->channel = host1x_channel_request(client->dev, false); > + if (IS_ERR(gr2d->channel)) > + return PTR_ERR(gr2d->channel); > > client->syncpts[0] = host1x_syncpt_request(client->dev, flags); > if (!client->syncpts[0]) { > diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c > index 279438342c8c..793a91d577cb 100644 > --- a/drivers/gpu/drm/tegra/gr3d.c > +++ b/drivers/gpu/drm/tegra/gr3d.c > @@ -42,9 +42,9 @@ static int gr3d_init(struct host1x_client *client) > unsigned long flags = HOST1X_SYNCPT_HAS_BASE; > struct gr3d *gr3d = to_gr3d(drm); > > - gr3d->channel = host1x_channel_request(client->dev); > - if (!gr3d->channel) > - return -ENOMEM; > + gr3d->channel = host1x_channel_request(client->dev, false); > + if (IS_ERR(gr3d->channel)) > + return PTR_ERR(gr3d->channel); > > client->syncpts[0] = host1x_syncpt_request(client->dev, flags); > if (!client->syncpts[0]) { > diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c > index 9d8cad12f9d8..eebcd51261df 100644 > --- a/drivers/gpu/host1x/channel.c > +++ b/drivers/gpu/host1x/channel.c > @@ -43,6 +43,7 @@ int host1x_channel_list_init(struct host1x_channel_list *chlist, > bitmap_zero(chlist->allocated_channels, num_channels); > > mutex_init(&chlist->lock); > + sema_init(&chlist->sema, num_channels); > > return 0; > } > @@ -99,6 +100,8 @@ static void release_channel(struct kref *kref) > host1x_cdma_deinit(&channel->cdma); > > clear_bit(channel->id, chlist->allocated_channels); > + > + up(&chlist->sema); > } > > void host1x_channel_put(struct host1x_channel *channel) > @@ -107,19 +110,30 @@ void host1x_channel_put(struct host1x_channel *channel) > } > EXPORT_SYMBOL(host1x_channel_put); > > -static struct host1x_channel *acquire_unused_channel(struct host1x *host) > +static struct host1x_channel *acquire_unused_channel(struct host1x *host, > + bool wait) > { > struct host1x_channel_list *chlist = &host->channel_list; > unsigned int max_channels = host->info->nb_channels; > unsigned int index; > + int err; > + > + if (wait) { > + err = down_interruptible(&chlist->sema); > + if (err) > + return ERR_PTR(err); > + } else { > + if (down_trylock(&chlist->sema)) > + return ERR_PTR(-EBUSY); > + } > > mutex_lock(&chlist->lock); > > index = find_first_zero_bit(chlist->allocated_channels, max_channels); > - if (index >= max_channels) { > + if (WARN(index >= max_channels, "failed to find free channel")) { > mutex_unlock(&chlist->lock); > dev_err(host->dev, "failed to find free channel\n"); > - return NULL; > + return ERR_PTR(-EBUSY); > } > > chlist->channels[index].id = index; > @@ -134,20 +148,26 @@ static struct host1x_channel *acquire_unused_channel(struct host1x *host) > /** > * host1x_channel_request() - Allocate a channel > * @device: Host1x unit this channel will be used to send commands to > + * @wait: Whether to wait for a free channels if all are reserved > + * > + * Allocates a new host1x channel for @device. If all channels are in use, > + * and @wait is true, does an interruptible wait until one is available. > * > - * Allocates a new host1x channel for @device. May return NULL if CDMA > - * initialization fails. > + * If a channel was acquired, returns a pointer to it. Otherwise returns > + * an error pointer with -EINTR if the wait was interrupted, -EBUSY > + * if a channel could not be acquired or another error code if channel > + * initialization failed. > */ > -struct host1x_channel *host1x_channel_request(struct device *dev) > +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait) > { > struct host1x *host = dev_get_drvdata(dev->parent); > struct host1x_channel_list *chlist = &host->channel_list; > struct host1x_channel *channel; > int err; > > - channel = acquire_unused_channel(host); > - if (!channel) > - return NULL; > + channel = acquire_unused_channel(host, wait); > + if (IS_ERR(channel)) > + return channel; > > kref_init(&channel->refcount); > mutex_init(&channel->submitlock); > @@ -168,6 +188,6 @@ struct host1x_channel *host1x_channel_request(struct device *dev) > > dev_err(dev, "failed to initialize channel\n"); > > - return NULL; > + return ERR_PTR(err); > } > EXPORT_SYMBOL(host1x_channel_request); > diff --git a/drivers/gpu/host1x/channel.h b/drivers/gpu/host1x/channel.h > index e68a8ae9a670..1f5cf8029b62 100644 > --- a/drivers/gpu/host1x/channel.h > +++ b/drivers/gpu/host1x/channel.h > @@ -31,6 +31,7 @@ struct host1x_channel_list { > struct host1x_channel *channels; > > struct mutex lock; > + struct semaphore sema; > unsigned long *allocated_channels; > }; > > diff --git a/include/linux/host1x.h b/include/linux/host1x.h > index f931d28a68ff..2a34905d4408 100644 > --- a/include/linux/host1x.h > +++ b/include/linux/host1x.h > @@ -171,7 +171,7 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); > struct host1x_channel; > struct host1x_job; > > -struct host1x_channel *host1x_channel_request(struct device *dev); > +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait); > struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); > void host1x_channel_put(struct host1x_channel *channel); > int host1x_job_submit(struct host1x_job *job); >
On 05.11.2017 19:14, Dmitry Osipenko wrote: > On 05.11.2017 14:01, Mikko Perttunen wrote: >> Add an option to host1x_channel_request to interruptibly wait for a >> free channel. This allows IOCTLs that acquire a channel to block >> the userspace. >> > > Wouldn't it be more optimal to request channel and block after job's pining, > when all patching and checks are completed? Note that right now we have locking > around submission in DRM, which I suppose should go away by making locking fine > grained. That would be possible, but I don't think it should matter much since contention here should not be the common case. > > Or maybe it would be more optimal to just iterate over channels, like I > suggested before [0]? Somehow I hadn't noticed this before, but this would break the invariant of having one client/class per channel. In general since we haven't seen any issues downstream with the model implemented here, I'd like to try to go with this and if we have problems with channel allocation then we could revisit. Mikko > > [0] > https://github.com/cyndis/linux/commit/9e6d87f40afb01fbe13ba65c73cb617bdfcd80b2#commitcomment-25012960 > >> Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com> >> --- >> drivers/gpu/drm/tegra/drm.c | 9 +++++---- >> drivers/gpu/drm/tegra/gr2d.c | 6 +++--- >> drivers/gpu/drm/tegra/gr3d.c | 6 +++--- >> drivers/gpu/host1x/channel.c | 40 ++++++++++++++++++++++++++++++---------- >> drivers/gpu/host1x/channel.h | 1 + >> include/linux/host1x.h | 2 +- >> 6 files changed, 43 insertions(+), 21 deletions(-) >> >> diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c >> index 658bc8814f38..19f77c1a76c0 100644 >> --- a/drivers/gpu/drm/tegra/drm.c >> +++ b/drivers/gpu/drm/tegra/drm.c >> @@ -389,7 +389,8 @@ static int host1x_waitchk_copy_from_user(struct host1x_waitchk *dest, >> * Request a free hardware host1x channel for this user context, or if the >> * context already has one, bump its refcount. >> * >> - * Returns 0 on success, or -EBUSY if there were no free hardware channels. >> + * Returns 0 on success, -EINTR if wait for a free channel was interrupted, >> + * or other error. >> */ >> int tegra_drm_context_get_channel(struct tegra_drm_context *context) >> { >> @@ -398,10 +399,10 @@ int tegra_drm_context_get_channel(struct tegra_drm_context *context) >> mutex_lock(&context->lock); >> >> if (context->pending_jobs == 0) { >> - context->channel = host1x_channel_request(client->dev); >> - if (!context->channel) { >> + context->channel = host1x_channel_request(client->dev, true); >> + if (IS_ERR(context->channel)) { >> mutex_unlock(&context->lock); >> - return -EBUSY; >> + return PTR_ERR(context->channel); >> } >> } >> >> diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c >> index 3db3bcac48b9..c1853402f69b 100644 >> --- a/drivers/gpu/drm/tegra/gr2d.c >> +++ b/drivers/gpu/drm/tegra/gr2d.c >> @@ -32,9 +32,9 @@ static int gr2d_init(struct host1x_client *client) >> unsigned long flags = HOST1X_SYNCPT_HAS_BASE; >> struct gr2d *gr2d = to_gr2d(drm); >> >> - gr2d->channel = host1x_channel_request(client->dev); >> - if (!gr2d->channel) >> - return -ENOMEM; >> + gr2d->channel = host1x_channel_request(client->dev, false); >> + if (IS_ERR(gr2d->channel)) >> + return PTR_ERR(gr2d->channel); >> >> client->syncpts[0] = host1x_syncpt_request(client->dev, flags); >> if (!client->syncpts[0]) { >> diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c >> index 279438342c8c..793a91d577cb 100644 >> --- a/drivers/gpu/drm/tegra/gr3d.c >> +++ b/drivers/gpu/drm/tegra/gr3d.c >> @@ -42,9 +42,9 @@ static int gr3d_init(struct host1x_client *client) >> unsigned long flags = HOST1X_SYNCPT_HAS_BASE; >> struct gr3d *gr3d = to_gr3d(drm); >> >> - gr3d->channel = host1x_channel_request(client->dev); >> - if (!gr3d->channel) >> - return -ENOMEM; >> + gr3d->channel = host1x_channel_request(client->dev, false); >> + if (IS_ERR(gr3d->channel)) >> + return PTR_ERR(gr3d->channel); >> >> client->syncpts[0] = host1x_syncpt_request(client->dev, flags); >> if (!client->syncpts[0]) { >> diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c >> index 9d8cad12f9d8..eebcd51261df 100644 >> --- a/drivers/gpu/host1x/channel.c >> +++ b/drivers/gpu/host1x/channel.c >> @@ -43,6 +43,7 @@ int host1x_channel_list_init(struct host1x_channel_list *chlist, >> bitmap_zero(chlist->allocated_channels, num_channels); >> >> mutex_init(&chlist->lock); >> + sema_init(&chlist->sema, num_channels); >> >> return 0; >> } >> @@ -99,6 +100,8 @@ static void release_channel(struct kref *kref) >> host1x_cdma_deinit(&channel->cdma); >> >> clear_bit(channel->id, chlist->allocated_channels); >> + >> + up(&chlist->sema); >> } >> >> void host1x_channel_put(struct host1x_channel *channel) >> @@ -107,19 +110,30 @@ void host1x_channel_put(struct host1x_channel *channel) >> } >> EXPORT_SYMBOL(host1x_channel_put); >> >> -static struct host1x_channel *acquire_unused_channel(struct host1x *host) >> +static struct host1x_channel *acquire_unused_channel(struct host1x *host, >> + bool wait) >> { >> struct host1x_channel_list *chlist = &host->channel_list; >> unsigned int max_channels = host->info->nb_channels; >> unsigned int index; >> + int err; >> + >> + if (wait) { >> + err = down_interruptible(&chlist->sema); >> + if (err) >> + return ERR_PTR(err); >> + } else { >> + if (down_trylock(&chlist->sema)) >> + return ERR_PTR(-EBUSY); >> + } >> >> mutex_lock(&chlist->lock); >> >> index = find_first_zero_bit(chlist->allocated_channels, max_channels); >> - if (index >= max_channels) { >> + if (WARN(index >= max_channels, "failed to find free channel")) { >> mutex_unlock(&chlist->lock); >> dev_err(host->dev, "failed to find free channel\n"); >> - return NULL; >> + return ERR_PTR(-EBUSY); >> } >> >> chlist->channels[index].id = index; >> @@ -134,20 +148,26 @@ static struct host1x_channel *acquire_unused_channel(struct host1x *host) >> /** >> * host1x_channel_request() - Allocate a channel >> * @device: Host1x unit this channel will be used to send commands to >> + * @wait: Whether to wait for a free channels if all are reserved >> + * >> + * Allocates a new host1x channel for @device. If all channels are in use, >> + * and @wait is true, does an interruptible wait until one is available. >> * >> - * Allocates a new host1x channel for @device. May return NULL if CDMA >> - * initialization fails. >> + * If a channel was acquired, returns a pointer to it. Otherwise returns >> + * an error pointer with -EINTR if the wait was interrupted, -EBUSY >> + * if a channel could not be acquired or another error code if channel >> + * initialization failed. >> */ >> -struct host1x_channel *host1x_channel_request(struct device *dev) >> +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait) >> { >> struct host1x *host = dev_get_drvdata(dev->parent); >> struct host1x_channel_list *chlist = &host->channel_list; >> struct host1x_channel *channel; >> int err; >> >> - channel = acquire_unused_channel(host); >> - if (!channel) >> - return NULL; >> + channel = acquire_unused_channel(host, wait); >> + if (IS_ERR(channel)) >> + return channel; >> >> kref_init(&channel->refcount); >> mutex_init(&channel->submitlock); >> @@ -168,6 +188,6 @@ struct host1x_channel *host1x_channel_request(struct device *dev) >> >> dev_err(dev, "failed to initialize channel\n"); >> >> - return NULL; >> + return ERR_PTR(err); >> } >> EXPORT_SYMBOL(host1x_channel_request); >> diff --git a/drivers/gpu/host1x/channel.h b/drivers/gpu/host1x/channel.h >> index e68a8ae9a670..1f5cf8029b62 100644 >> --- a/drivers/gpu/host1x/channel.h >> +++ b/drivers/gpu/host1x/channel.h >> @@ -31,6 +31,7 @@ struct host1x_channel_list { >> struct host1x_channel *channels; >> >> struct mutex lock; >> + struct semaphore sema; >> unsigned long *allocated_channels; >> }; >> >> diff --git a/include/linux/host1x.h b/include/linux/host1x.h >> index f931d28a68ff..2a34905d4408 100644 >> --- a/include/linux/host1x.h >> +++ b/include/linux/host1x.h >> @@ -171,7 +171,7 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); >> struct host1x_channel; >> struct host1x_job; >> >> -struct host1x_channel *host1x_channel_request(struct device *dev); >> +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait); >> struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); >> void host1x_channel_put(struct host1x_channel *channel); >> int host1x_job_submit(struct host1x_job *job); >> > > -- > To unsubscribe from this list: send the line "unsubscribe linux-tegra" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html >
On 07.11.2017 16:11, Mikko Perttunen wrote: > On 05.11.2017 19:14, Dmitry Osipenko wrote: >> On 05.11.2017 14:01, Mikko Perttunen wrote: >>> Add an option to host1x_channel_request to interruptibly wait for a >>> free channel. This allows IOCTLs that acquire a channel to block >>> the userspace. >>> >> >> Wouldn't it be more optimal to request channel and block after job's pining, >> when all patching and checks are completed? Note that right now we have locking >> around submission in DRM, which I suppose should go away by making locking fine >> grained. > > That would be possible, but I don't think it should matter much since contention > here should not be the common case. > >> >> Or maybe it would be more optimal to just iterate over channels, like I >> suggested before [0]? > > Somehow I hadn't noticed this before, but this would break the invariant of > having one client/class per channel. > Yes, currently there is a weak relation of channel and clients device, but seems channels device is only used for printing dev_* messages and device could be borrowed from the channels job. I don't see any real point of hardwiring channel to a specific device or client. > In general since we haven't seen any issues downstream with the model > implemented here, I'd like to try to go with this and if we have problems with > channel allocation then we could revisit. > I'd prefer to collect some real numbers first, will test it with our grate / mesa stuff. Also, we should have a host1x_test, maybe something similar to submission perf test but using multiple contexts. > >> >> [0] >> https://github.com/cyndis/linux/commit/9e6d87f40afb01fbe13ba65c73cb617bdfcd80b2#commitcomment-25012960 >> >> >>> Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com> >>> --- >>> drivers/gpu/drm/tegra/drm.c | 9 +++++---- >>> drivers/gpu/drm/tegra/gr2d.c | 6 +++--- >>> drivers/gpu/drm/tegra/gr3d.c | 6 +++--- >>> drivers/gpu/host1x/channel.c | 40 ++++++++++++++++++++++++++++++---------- >>> drivers/gpu/host1x/channel.h | 1 + >>> include/linux/host1x.h | 2 +- >>> 6 files changed, 43 insertions(+), 21 deletions(-) >>> >>> diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c >>> index 658bc8814f38..19f77c1a76c0 100644 >>> --- a/drivers/gpu/drm/tegra/drm.c >>> +++ b/drivers/gpu/drm/tegra/drm.c >>> @@ -389,7 +389,8 @@ static int host1x_waitchk_copy_from_user(struct >>> host1x_waitchk *dest, >>> * Request a free hardware host1x channel for this user context, or if the >>> * context already has one, bump its refcount. >>> * >>> - * Returns 0 on success, or -EBUSY if there were no free hardware channels. >>> + * Returns 0 on success, -EINTR if wait for a free channel was interrupted, >>> + * or other error. >>> */ >>> int tegra_drm_context_get_channel(struct tegra_drm_context *context) >>> { >>> @@ -398,10 +399,10 @@ int tegra_drm_context_get_channel(struct >>> tegra_drm_context *context) >>> mutex_lock(&context->lock); >>> >>> if (context->pending_jobs == 0) { >>> - context->channel = host1x_channel_request(client->dev); >>> - if (!context->channel) { >>> + context->channel = host1x_channel_request(client->dev, true); >>> + if (IS_ERR(context->channel)) { >>> mutex_unlock(&context->lock); >>> - return -EBUSY; >>> + return PTR_ERR(context->channel); >>> } >>> } >>> >>> diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c >>> index 3db3bcac48b9..c1853402f69b 100644 >>> --- a/drivers/gpu/drm/tegra/gr2d.c >>> +++ b/drivers/gpu/drm/tegra/gr2d.c >>> @@ -32,9 +32,9 @@ static int gr2d_init(struct host1x_client *client) >>> unsigned long flags = HOST1X_SYNCPT_HAS_BASE; >>> struct gr2d *gr2d = to_gr2d(drm); >>> >>> - gr2d->channel = host1x_channel_request(client->dev); >>> - if (!gr2d->channel) >>> - return -ENOMEM; >>> + gr2d->channel = host1x_channel_request(client->dev, false); >>> + if (IS_ERR(gr2d->channel)) >>> + return PTR_ERR(gr2d->channel); >>> >>> client->syncpts[0] = host1x_syncpt_request(client->dev, flags); >>> if (!client->syncpts[0]) { >>> diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c >>> index 279438342c8c..793a91d577cb 100644 >>> --- a/drivers/gpu/drm/tegra/gr3d.c >>> +++ b/drivers/gpu/drm/tegra/gr3d.c >>> @@ -42,9 +42,9 @@ static int gr3d_init(struct host1x_client *client) >>> unsigned long flags = HOST1X_SYNCPT_HAS_BASE; >>> struct gr3d *gr3d = to_gr3d(drm); >>> >>> - gr3d->channel = host1x_channel_request(client->dev); >>> - if (!gr3d->channel) >>> - return -ENOMEM; >>> + gr3d->channel = host1x_channel_request(client->dev, false); >>> + if (IS_ERR(gr3d->channel)) >>> + return PTR_ERR(gr3d->channel); >>> >>> client->syncpts[0] = host1x_syncpt_request(client->dev, flags); >>> if (!client->syncpts[0]) { >>> diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c >>> index 9d8cad12f9d8..eebcd51261df 100644 >>> --- a/drivers/gpu/host1x/channel.c >>> +++ b/drivers/gpu/host1x/channel.c >>> @@ -43,6 +43,7 @@ int host1x_channel_list_init(struct host1x_channel_list >>> *chlist, >>> bitmap_zero(chlist->allocated_channels, num_channels); >>> >>> mutex_init(&chlist->lock); >>> + sema_init(&chlist->sema, num_channels); >>> >>> return 0; >>> } >>> @@ -99,6 +100,8 @@ static void release_channel(struct kref *kref) >>> host1x_cdma_deinit(&channel->cdma); >>> >>> clear_bit(channel->id, chlist->allocated_channels); >>> + >>> + up(&chlist->sema); >>> } >>> >>> void host1x_channel_put(struct host1x_channel *channel) >>> @@ -107,19 +110,30 @@ void host1x_channel_put(struct host1x_channel *channel) >>> } >>> EXPORT_SYMBOL(host1x_channel_put); >>> >>> -static struct host1x_channel *acquire_unused_channel(struct host1x *host) >>> +static struct host1x_channel *acquire_unused_channel(struct host1x *host, >>> + bool wait) >>> { >>> struct host1x_channel_list *chlist = &host->channel_list; >>> unsigned int max_channels = host->info->nb_channels; >>> unsigned int index; >>> + int err; >>> + >>> + if (wait) { >>> + err = down_interruptible(&chlist->sema); >>> + if (err) >>> + return ERR_PTR(err); >>> + } else { >>> + if (down_trylock(&chlist->sema)) >>> + return ERR_PTR(-EBUSY); >>> + } >>> >>> mutex_lock(&chlist->lock); >>> >>> index = find_first_zero_bit(chlist->allocated_channels, max_channels); >>> - if (index >= max_channels) { >>> + if (WARN(index >= max_channels, "failed to find free channel")) { >>> mutex_unlock(&chlist->lock); >>> dev_err(host->dev, "failed to find free channel\n"); >>> - return NULL; >>> + return ERR_PTR(-EBUSY); >>> } >>> >>> chlist->channels[index].id = index; >>> @@ -134,20 +148,26 @@ static struct host1x_channel >>> *acquire_unused_channel(struct host1x *host) >>> /** >>> * host1x_channel_request() - Allocate a channel >>> * @device: Host1x unit this channel will be used to send commands to >>> + * @wait: Whether to wait for a free channels if all are reserved >>> + * >>> + * Allocates a new host1x channel for @device. If all channels are in use, >>> + * and @wait is true, does an interruptible wait until one is available. >>> * >>> - * Allocates a new host1x channel for @device. May return NULL if CDMA >>> - * initialization fails. >>> + * If a channel was acquired, returns a pointer to it. Otherwise returns >>> + * an error pointer with -EINTR if the wait was interrupted, -EBUSY >>> + * if a channel could not be acquired or another error code if channel >>> + * initialization failed. >>> */ >>> -struct host1x_channel *host1x_channel_request(struct device *dev) >>> +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait) >>> { >>> struct host1x *host = dev_get_drvdata(dev->parent); >>> struct host1x_channel_list *chlist = &host->channel_list; >>> struct host1x_channel *channel; >>> int err; >>> >>> - channel = acquire_unused_channel(host); >>> - if (!channel) >>> - return NULL; >>> + channel = acquire_unused_channel(host, wait); >>> + if (IS_ERR(channel)) >>> + return channel; >>> >>> kref_init(&channel->refcount); >>> mutex_init(&channel->submitlock); >>> @@ -168,6 +188,6 @@ struct host1x_channel *host1x_channel_request(struct >>> device *dev) >>> >>> dev_err(dev, "failed to initialize channel\n"); >>> >>> - return NULL; >>> + return ERR_PTR(err); >>> } >>> EXPORT_SYMBOL(host1x_channel_request); >>> diff --git a/drivers/gpu/host1x/channel.h b/drivers/gpu/host1x/channel.h >>> index e68a8ae9a670..1f5cf8029b62 100644 >>> --- a/drivers/gpu/host1x/channel.h >>> +++ b/drivers/gpu/host1x/channel.h >>> @@ -31,6 +31,7 @@ struct host1x_channel_list { >>> struct host1x_channel *channels; >>> >>> struct mutex lock; >>> + struct semaphore sema; >>> unsigned long *allocated_channels; >>> }; >>> >>> diff --git a/include/linux/host1x.h b/include/linux/host1x.h >>> index f931d28a68ff..2a34905d4408 100644 >>> --- a/include/linux/host1x.h >>> +++ b/include/linux/host1x.h >>> @@ -171,7 +171,7 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); >>> struct host1x_channel; >>> struct host1x_job; >>> >>> -struct host1x_channel *host1x_channel_request(struct device *dev); >>> +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait); >>> struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); >>> void host1x_channel_put(struct host1x_channel *channel); >>> int host1x_job_submit(struct host1x_job *job); >>> >>
On 07.11.2017 18:29, Dmitry Osipenko wrote: > On 07.11.2017 16:11, Mikko Perttunen wrote: >> On 05.11.2017 19:14, Dmitry Osipenko wrote: >>> On 05.11.2017 14:01, Mikko Perttunen wrote: >>>> Add an option to host1x_channel_request to interruptibly wait for a >>>> free channel. This allows IOCTLs that acquire a channel to block >>>> the userspace. >>>> >>> >>> Wouldn't it be more optimal to request channel and block after job's pining, >>> when all patching and checks are completed? Note that right now we have locking >>> around submission in DRM, which I suppose should go away by making locking fine >>> grained. >> >> That would be possible, but I don't think it should matter much since contention >> here should not be the common case. >> >>> >>> Or maybe it would be more optimal to just iterate over channels, like I >>> suggested before [0]? >> >> Somehow I hadn't noticed this before, but this would break the invariant of >> having one client/class per channel. >> > > Yes, currently there is a weak relation of channel and clients device, but seems > channels device is only used for printing dev_* messages and device could be > borrowed from the channels job. I don't see any real point of hardwiring channel > to a specific device or client. Although, it won't work with syncpoint assignment to channel.
On 11.11.2017 00:15, Dmitry Osipenko wrote: > On 07.11.2017 18:29, Dmitry Osipenko wrote: >> On 07.11.2017 16:11, Mikko Perttunen wrote: >>> On 05.11.2017 19:14, Dmitry Osipenko wrote: >>>> On 05.11.2017 14:01, Mikko Perttunen wrote: >>>>> Add an option to host1x_channel_request to interruptibly wait for a >>>>> free channel. This allows IOCTLs that acquire a channel to block >>>>> the userspace. >>>>> >>>> >>>> Wouldn't it be more optimal to request channel and block after job's pining, >>>> when all patching and checks are completed? Note that right now we have locking >>>> around submission in DRM, which I suppose should go away by making locking fine >>>> grained. >>> >>> That would be possible, but I don't think it should matter much since contention >>> here should not be the common case. >>> >>>> >>>> Or maybe it would be more optimal to just iterate over channels, like I >>>> suggested before [0]? >>> >>> Somehow I hadn't noticed this before, but this would break the invariant of >>> having one client/class per channel. >>> >> >> Yes, currently there is a weak relation of channel and clients device, but seems >> channels device is only used for printing dev_* messages and device could be >> borrowed from the channels job. I don't see any real point of hardwiring channel >> to a specific device or client. > > Although, it won't work with syncpoint assignment to channel. On the other hand.. it should work if one syncpoint could be assigned to multiple channels, couldn't it?
On 12.11.2017 13:23, Dmitry Osipenko wrote: > On 11.11.2017 00:15, Dmitry Osipenko wrote: >> On 07.11.2017 18:29, Dmitry Osipenko wrote: >>> On 07.11.2017 16:11, Mikko Perttunen wrote: >>>> On 05.11.2017 19:14, Dmitry Osipenko wrote: >>>>> On 05.11.2017 14:01, Mikko Perttunen wrote: >>>>>> Add an option to host1x_channel_request to interruptibly wait for a >>>>>> free channel. This allows IOCTLs that acquire a channel to block >>>>>> the userspace. >>>>>> >>>>> >>>>> Wouldn't it be more optimal to request channel and block after job's pining, >>>>> when all patching and checks are completed? Note that right now we have locking >>>>> around submission in DRM, which I suppose should go away by making locking fine >>>>> grained. >>>> >>>> That would be possible, but I don't think it should matter much since contention >>>> here should not be the common case. >>>> >>>>> >>>>> Or maybe it would be more optimal to just iterate over channels, like I >>>>> suggested before [0]? >>>> >>>> Somehow I hadn't noticed this before, but this would break the invariant of >>>> having one client/class per channel. >>>> >>> >>> Yes, currently there is a weak relation of channel and clients device, but seems >>> channels device is only used for printing dev_* messages and device could be >>> borrowed from the channels job. I don't see any real point of hardwiring channel >>> to a specific device or client. >> >> Although, it won't work with syncpoint assignment to channel. > > On the other hand.. it should work if one syncpoint could be assigned to > multiple channels, couldn't it? A syncpoint can only be mapped to a single channel, so unfortunately this won't work. Mikko > -- > To unsubscribe from this list: send the line "unsubscribe linux-tegra" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html >
On 29.11.2017 12:10, Mikko Perttunen wrote: > On 12.11.2017 13:23, Dmitry Osipenko wrote: >> On 11.11.2017 00:15, Dmitry Osipenko wrote: >>> On 07.11.2017 18:29, Dmitry Osipenko wrote: >>>> On 07.11.2017 16:11, Mikko Perttunen wrote: >>>>> On 05.11.2017 19:14, Dmitry Osipenko wrote: >>>>>> On 05.11.2017 14:01, Mikko Perttunen wrote: >>>>>>> Add an option to host1x_channel_request to interruptibly wait for a >>>>>>> free channel. This allows IOCTLs that acquire a channel to block >>>>>>> the userspace. >>>>>>> >>>>>> >>>>>> Wouldn't it be more optimal to request channel and block after job's pining, >>>>>> when all patching and checks are completed? Note that right now we have >>>>>> locking >>>>>> around submission in DRM, which I suppose should go away by making locking >>>>>> fine >>>>>> grained. >>>>> >>>>> That would be possible, but I don't think it should matter much since >>>>> contention >>>>> here should not be the common case. >>>>> >>>>>> >>>>>> Or maybe it would be more optimal to just iterate over channels, like I >>>>>> suggested before [0]? >>>>> >>>>> Somehow I hadn't noticed this before, but this would break the invariant of >>>>> having one client/class per channel. >>>>> >>>> >>>> Yes, currently there is a weak relation of channel and clients device, but >>>> seems >>>> channels device is only used for printing dev_* messages and device could be >>>> borrowed from the channels job. I don't see any real point of hardwiring >>>> channel >>>> to a specific device or client. >>> >>> Although, it won't work with syncpoint assignment to channel. >> >> On the other hand.. it should work if one syncpoint could be assigned to >> multiple channels, couldn't it? > > A syncpoint can only be mapped to a single channel, so unfortunately this won't > work. Okay, in DRM we are requesting syncpoint on channels 'open' and syncpoint assignment happens on jobs submission. So firstly submitted job will assign syncpoint to the first channel and second job would re-assign syncpoint to a second channel while first job is still in-progress, how is it going to work?
On 29.11.2017 14:18, Dmitry Osipenko wrote: > On 29.11.2017 12:10, Mikko Perttunen wrote: >> On 12.11.2017 13:23, Dmitry Osipenko wrote: >>> On 11.11.2017 00:15, Dmitry Osipenko wrote: >>>> On 07.11.2017 18:29, Dmitry Osipenko wrote: >>>>> On 07.11.2017 16:11, Mikko Perttunen wrote: >>>>>> On 05.11.2017 19:14, Dmitry Osipenko wrote: >>>>>>> On 05.11.2017 14:01, Mikko Perttunen wrote: >>>>>>>> Add an option to host1x_channel_request to interruptibly wait for a >>>>>>>> free channel. This allows IOCTLs that acquire a channel to block >>>>>>>> the userspace. >>>>>>>> >>>>>>> >>>>>>> Wouldn't it be more optimal to request channel and block after job's pining, >>>>>>> when all patching and checks are completed? Note that right now we have >>>>>>> locking >>>>>>> around submission in DRM, which I suppose should go away by making locking >>>>>>> fine >>>>>>> grained. >>>>>> >>>>>> That would be possible, but I don't think it should matter much since >>>>>> contention >>>>>> here should not be the common case. >>>>>> >>>>>>> >>>>>>> Or maybe it would be more optimal to just iterate over channels, like I >>>>>>> suggested before [0]? >>>>>> >>>>>> Somehow I hadn't noticed this before, but this would break the invariant of >>>>>> having one client/class per channel. >>>>>> >>>>> >>>>> Yes, currently there is a weak relation of channel and clients device, but >>>>> seems >>>>> channels device is only used for printing dev_* messages and device could be >>>>> borrowed from the channels job. I don't see any real point of hardwiring >>>>> channel >>>>> to a specific device or client. >>>> >>>> Although, it won't work with syncpoint assignment to channel. >>> >>> On the other hand.. it should work if one syncpoint could be assigned to >>> multiple channels, couldn't it? >> >> A syncpoint can only be mapped to a single channel, so unfortunately this won't >> work. > Okay, in DRM we are requesting syncpoint on channels 'open' and syncpoint > assignment happens on jobs submission. So firstly submitted job will assign > syncpoint to the first channel and second job would re-assign syncpoint to a > second channel while first job is still in-progress, how is it going to work? > When a context is created, it's assigned both a syncpoint and channel and this pair stays for as long as the context is alive (i.e. as long as there are jobs), so even if the syncpoint is reassigned to a channel at every submit, it is always assigned to the same channel, so nothing breaks. Multiple contexts cannot share syncpoints so things work out. Obviously this is not ideal as we currently never unassign syncpoints but at least it is not broken. Mikko
On 29.11.2017 15:25, Mikko Perttunen wrote: > On 29.11.2017 14:18, Dmitry Osipenko wrote: >> On 29.11.2017 12:10, Mikko Perttunen wrote: >>> On 12.11.2017 13:23, Dmitry Osipenko wrote: >>>> On 11.11.2017 00:15, Dmitry Osipenko wrote: >>>>> On 07.11.2017 18:29, Dmitry Osipenko wrote: >>>>>> On 07.11.2017 16:11, Mikko Perttunen wrote: >>>>>>> On 05.11.2017 19:14, Dmitry Osipenko wrote: >>>>>>>> On 05.11.2017 14:01, Mikko Perttunen wrote: >>>>>>>>> Add an option to host1x_channel_request to interruptibly wait for a >>>>>>>>> free channel. This allows IOCTLs that acquire a channel to block >>>>>>>>> the userspace. >>>>>>>>> >>>>>>>> >>>>>>>> Wouldn't it be more optimal to request channel and block after job's >>>>>>>> pining, >>>>>>>> when all patching and checks are completed? Note that right now we have >>>>>>>> locking >>>>>>>> around submission in DRM, which I suppose should go away by making locking >>>>>>>> fine >>>>>>>> grained. >>>>>>> >>>>>>> That would be possible, but I don't think it should matter much since >>>>>>> contention >>>>>>> here should not be the common case. >>>>>>> >>>>>>>> >>>>>>>> Or maybe it would be more optimal to just iterate over channels, like I >>>>>>>> suggested before [0]? >>>>>>> >>>>>>> Somehow I hadn't noticed this before, but this would break the invariant of >>>>>>> having one client/class per channel. >>>>>>> >>>>>> >>>>>> Yes, currently there is a weak relation of channel and clients device, but >>>>>> seems >>>>>> channels device is only used for printing dev_* messages and device could be >>>>>> borrowed from the channels job. I don't see any real point of hardwiring >>>>>> channel >>>>>> to a specific device or client. >>>>> >>>>> Although, it won't work with syncpoint assignment to channel. >>>> >>>> On the other hand.. it should work if one syncpoint could be assigned to >>>> multiple channels, couldn't it? >>> >>> A syncpoint can only be mapped to a single channel, so unfortunately this won't >>> work. >> Okay, in DRM we are requesting syncpoint on channels 'open' and syncpoint >> assignment happens on jobs submission. So firstly submitted job will assign >> syncpoint to the first channel and second job would re-assign syncpoint to a >> second channel while first job is still in-progress, how is it going to work? >> > > When a context is created, it's assigned both a syncpoint and channel and this > pair stays for as long as the context is alive (i.e. as long as there are jobs), > so even if the syncpoint is reassigned to a channel at every submit, it is > always assigned to the same channel, so nothing breaks. Multiple contexts cannot > share syncpoints so things work out. > > Obviously this is not ideal as we currently never unassign syncpoints but at > least it is not broken. Right, I forgot that you made tegra_drm_context_get_channel() to re-use requested channel if there are pending jobs.
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 658bc8814f38..19f77c1a76c0 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -389,7 +389,8 @@ static int host1x_waitchk_copy_from_user(struct host1x_waitchk *dest, * Request a free hardware host1x channel for this user context, or if the * context already has one, bump its refcount. * - * Returns 0 on success, or -EBUSY if there were no free hardware channels. + * Returns 0 on success, -EINTR if wait for a free channel was interrupted, + * or other error. */ int tegra_drm_context_get_channel(struct tegra_drm_context *context) { @@ -398,10 +399,10 @@ int tegra_drm_context_get_channel(struct tegra_drm_context *context) mutex_lock(&context->lock); if (context->pending_jobs == 0) { - context->channel = host1x_channel_request(client->dev); - if (!context->channel) { + context->channel = host1x_channel_request(client->dev, true); + if (IS_ERR(context->channel)) { mutex_unlock(&context->lock); - return -EBUSY; + return PTR_ERR(context->channel); } } diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c index 3db3bcac48b9..c1853402f69b 100644 --- a/drivers/gpu/drm/tegra/gr2d.c +++ b/drivers/gpu/drm/tegra/gr2d.c @@ -32,9 +32,9 @@ static int gr2d_init(struct host1x_client *client) unsigned long flags = HOST1X_SYNCPT_HAS_BASE; struct gr2d *gr2d = to_gr2d(drm); - gr2d->channel = host1x_channel_request(client->dev); - if (!gr2d->channel) - return -ENOMEM; + gr2d->channel = host1x_channel_request(client->dev, false); + if (IS_ERR(gr2d->channel)) + return PTR_ERR(gr2d->channel); client->syncpts[0] = host1x_syncpt_request(client->dev, flags); if (!client->syncpts[0]) { diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c index 279438342c8c..793a91d577cb 100644 --- a/drivers/gpu/drm/tegra/gr3d.c +++ b/drivers/gpu/drm/tegra/gr3d.c @@ -42,9 +42,9 @@ static int gr3d_init(struct host1x_client *client) unsigned long flags = HOST1X_SYNCPT_HAS_BASE; struct gr3d *gr3d = to_gr3d(drm); - gr3d->channel = host1x_channel_request(client->dev); - if (!gr3d->channel) - return -ENOMEM; + gr3d->channel = host1x_channel_request(client->dev, false); + if (IS_ERR(gr3d->channel)) + return PTR_ERR(gr3d->channel); client->syncpts[0] = host1x_syncpt_request(client->dev, flags); if (!client->syncpts[0]) { diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c index 9d8cad12f9d8..eebcd51261df 100644 --- a/drivers/gpu/host1x/channel.c +++ b/drivers/gpu/host1x/channel.c @@ -43,6 +43,7 @@ int host1x_channel_list_init(struct host1x_channel_list *chlist, bitmap_zero(chlist->allocated_channels, num_channels); mutex_init(&chlist->lock); + sema_init(&chlist->sema, num_channels); return 0; } @@ -99,6 +100,8 @@ static void release_channel(struct kref *kref) host1x_cdma_deinit(&channel->cdma); clear_bit(channel->id, chlist->allocated_channels); + + up(&chlist->sema); } void host1x_channel_put(struct host1x_channel *channel) @@ -107,19 +110,30 @@ void host1x_channel_put(struct host1x_channel *channel) } EXPORT_SYMBOL(host1x_channel_put); -static struct host1x_channel *acquire_unused_channel(struct host1x *host) +static struct host1x_channel *acquire_unused_channel(struct host1x *host, + bool wait) { struct host1x_channel_list *chlist = &host->channel_list; unsigned int max_channels = host->info->nb_channels; unsigned int index; + int err; + + if (wait) { + err = down_interruptible(&chlist->sema); + if (err) + return ERR_PTR(err); + } else { + if (down_trylock(&chlist->sema)) + return ERR_PTR(-EBUSY); + } mutex_lock(&chlist->lock); index = find_first_zero_bit(chlist->allocated_channels, max_channels); - if (index >= max_channels) { + if (WARN(index >= max_channels, "failed to find free channel")) { mutex_unlock(&chlist->lock); dev_err(host->dev, "failed to find free channel\n"); - return NULL; + return ERR_PTR(-EBUSY); } chlist->channels[index].id = index; @@ -134,20 +148,26 @@ static struct host1x_channel *acquire_unused_channel(struct host1x *host) /** * host1x_channel_request() - Allocate a channel * @device: Host1x unit this channel will be used to send commands to + * @wait: Whether to wait for a free channels if all are reserved + * + * Allocates a new host1x channel for @device. If all channels are in use, + * and @wait is true, does an interruptible wait until one is available. * - * Allocates a new host1x channel for @device. May return NULL if CDMA - * initialization fails. + * If a channel was acquired, returns a pointer to it. Otherwise returns + * an error pointer with -EINTR if the wait was interrupted, -EBUSY + * if a channel could not be acquired or another error code if channel + * initialization failed. */ -struct host1x_channel *host1x_channel_request(struct device *dev) +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait) { struct host1x *host = dev_get_drvdata(dev->parent); struct host1x_channel_list *chlist = &host->channel_list; struct host1x_channel *channel; int err; - channel = acquire_unused_channel(host); - if (!channel) - return NULL; + channel = acquire_unused_channel(host, wait); + if (IS_ERR(channel)) + return channel; kref_init(&channel->refcount); mutex_init(&channel->submitlock); @@ -168,6 +188,6 @@ struct host1x_channel *host1x_channel_request(struct device *dev) dev_err(dev, "failed to initialize channel\n"); - return NULL; + return ERR_PTR(err); } EXPORT_SYMBOL(host1x_channel_request); diff --git a/drivers/gpu/host1x/channel.h b/drivers/gpu/host1x/channel.h index e68a8ae9a670..1f5cf8029b62 100644 --- a/drivers/gpu/host1x/channel.h +++ b/drivers/gpu/host1x/channel.h @@ -31,6 +31,7 @@ struct host1x_channel_list { struct host1x_channel *channels; struct mutex lock; + struct semaphore sema; unsigned long *allocated_channels; }; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index f931d28a68ff..2a34905d4408 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -171,7 +171,7 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); struct host1x_channel; struct host1x_job; -struct host1x_channel *host1x_channel_request(struct device *dev); +struct host1x_channel *host1x_channel_request(struct device *dev, bool wait); struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); void host1x_channel_put(struct host1x_channel *channel); int host1x_job_submit(struct host1x_job *job);
Add an option to host1x_channel_request to interruptibly wait for a free channel. This allows IOCTLs that acquire a channel to block the userspace. Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com> --- drivers/gpu/drm/tegra/drm.c | 9 +++++---- drivers/gpu/drm/tegra/gr2d.c | 6 +++--- drivers/gpu/drm/tegra/gr3d.c | 6 +++--- drivers/gpu/host1x/channel.c | 40 ++++++++++++++++++++++++++++++---------- drivers/gpu/host1x/channel.h | 1 + include/linux/host1x.h | 2 +- 6 files changed, 43 insertions(+), 21 deletions(-)