| Message ID | 20160804092153.23032-9-lee.jones@linaro.org |
|---|---|
| State | New |
| Headers | show |
On Thu 04 Aug 02:21 PDT 2016, Lee Jones wrote: > There is little point wasting CPU cycles completing integrity checking > (i.e. ensuring nothing has changed) on the resource table if we *know* > that it will be changed (by us). In this patch we skip resource table > integrity checks if a platform-specific remoteproc driver has requested > an amendment or an appended entry. > If we apply the auto-boot series first, I believe this dance goes away. Regards, Bjorn > Signed-off-by: Lee Jones <lee.jones@linaro.org> > --- > drivers/remoteproc/remoteproc_core.c | 11 +++++++++++ > 1 file changed, 11 insertions(+) > > diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c > index 6b4e29a..9a077e4 100644 > --- a/drivers/remoteproc/remoteproc_core.c > +++ b/drivers/remoteproc/remoteproc_core.c > @@ -1126,6 +1126,10 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) > rproc->bootaddr = rproc_get_boot_addr(rproc, fw); > ret = -EINVAL; > > + /* If we've overridden the resource table, we know it's changed. */ > + if (!list_empty(&rproc->override_resources)) > + goto skip_table_check; > + > /* look for the resource table */ > table = rproc_find_rsc_table(rproc, fw, &tablesz); > if (!table) { > @@ -1139,6 +1143,8 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) > goto clean_up; > } > > + skip_table_check: > + > /* handle fw resources which are required to boot rproc */ > ret = rproc_handle_resources(rproc, tablesz, rproc_loading_handlers); > if (ret) { > @@ -1216,10 +1222,15 @@ static void rproc_fw_config_virtio(const struct firmware *fw, void *context) > table = rproc_apply_resource_overrides(rproc, &table, &tablesz); > if (IS_ERR(table)) > goto out; > + > + /* No point checking table if we know it *has* changed */ > + goto skip_table_check; > } > > rproc->table_csum = crc32(0, table, tablesz); > > + skip_table_check: > + > /* > * Create a copy of the resource table. When a virtio device starts > * and calls vring_new_virtqueue() the address of the allocated vring > -- > 2.9.0 >
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 6b4e29a..9a077e4 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1126,6 +1126,10 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) rproc->bootaddr = rproc_get_boot_addr(rproc, fw); ret = -EINVAL; + /* If we've overridden the resource table, we know it's changed. */ + if (!list_empty(&rproc->override_resources)) + goto skip_table_check; + /* look for the resource table */ table = rproc_find_rsc_table(rproc, fw, &tablesz); if (!table) { @@ -1139,6 +1143,8 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) goto clean_up; } + skip_table_check: + /* handle fw resources which are required to boot rproc */ ret = rproc_handle_resources(rproc, tablesz, rproc_loading_handlers); if (ret) { @@ -1216,10 +1222,15 @@ static void rproc_fw_config_virtio(const struct firmware *fw, void *context) table = rproc_apply_resource_overrides(rproc, &table, &tablesz); if (IS_ERR(table)) goto out; + + /* No point checking table if we know it *has* changed */ + goto skip_table_check; } rproc->table_csum = crc32(0, table, tablesz); + skip_table_check: + /* * Create a copy of the resource table. When a virtio device starts * and calls vring_new_virtqueue() the address of the allocated vring
There is little point wasting CPU cycles completing integrity checking (i.e. ensuring nothing has changed) on the resource table if we *know* that it will be changed (by us). In this patch we skip resource table integrity checks if a platform-specific remoteproc driver has requested an amendment or an appended entry. Signed-off-by: Lee Jones <lee.jones@linaro.org> --- drivers/remoteproc/remoteproc_core.c | 11 +++++++++++ 1 file changed, 11 insertions(+) -- 2.9.0