Re: [PATCH 2/4] amdgpu_ucode: reduce number of pr_debug calls

[jim . cromie]

On Wed, Sep 29, 2021 at 8:08 PM Joe Perches  wrote:
>
> On Wed, 2021-09-29 at 19:44 -0600, Jim Cromie wrote:
> > There are blocks of DRM_DEBUG calls, consolidate their args into
> > single calls.  With dynamic-debug in use, each callsite consumes 56
> > bytes of callsite data, and this patch removes about 65 calls, so
> > it saves ~3.5kb.
> >
> > no functional changes.
>
> No functional change, but an output logging content change.
>
> > RFC: this creates multi-line log messages, does that break any syslog
> > conventions ?
>
> It does change the output as each individual DRM_DEBUG is a call to
> __drm_dbg which is effectively:
>
> printk(KERN_DEBUG "[" DRM_NAME ":%ps] %pV",
>__builtin_return_address(0), );
>
>

ok.  that would disqualify the nouveau patch too.

Re: [PATCH 2/4] amdgpu_ucode: reduce number of pr_debug calls

[Joe Perches]

On Wed, 2021-09-29 at 19:44 -0600, Jim Cromie wrote:
> There are blocks of DRM_DEBUG calls, consolidate their args into
> single calls.  With dynamic-debug in use, each callsite consumes 56
> bytes of callsite data, and this patch removes about 65 calls, so
> it saves ~3.5kb.
> 
> no functional changes.

No functional change, but an output logging content change.

> RFC: this creates multi-line log messages, does that break any syslog
> conventions ?

It does change the output as each individual DRM_DEBUG is a call to
__drm_dbg which is effectively:

printk(KERN_DEBUG "[" DRM_NAME ":%ps] %pV",
   __builtin_return_address(0), );


> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c 
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
[]
> @@ -30,17 +30,26 @@
>  
> 
>  static void amdgpu_ucode_print_common_hdr(const struct 
> common_firmware_header *hdr)
>  {
> - DRM_DEBUG("size_bytes: %u\n", le32_to_cpu(hdr->size_bytes));
> - DRM_DEBUG("header_size_bytes: %u\n", 
> le32_to_cpu(hdr->header_size_bytes));
[]
> + DRM_DEBUG("size_bytes: %u\n"
> +   "header_size_bytes: %u\n"

etc...

[PATCH 2/4] amdgpu_ucode: reduce number of pr_debug calls

[Jim Cromie]

There are blocks of DRM_DEBUG calls, consolidate their args into
single calls.  With dynamic-debug in use, each callsite consumes 56
bytes of callsite data, and this patch removes about 65 calls, so
it saves ~3.5kb.

no functional changes.

RFC: this creates multi-line log messages, does that break any syslog
conventions ?

Signed-off-by: Jim Cromie 
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 293 --
 1 file changed, 158 insertions(+), 135 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index abd8469380e5..411179142a6e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -30,17 +30,26 @@
 
 static void amdgpu_ucode_print_common_hdr(const struct common_firmware_header 
*hdr)
 {
-   DRM_DEBUG("size_bytes: %u\n", le32_to_cpu(hdr->size_bytes));
-   DRM_DEBUG("header_size_bytes: %u\n", 
le32_to_cpu(hdr->header_size_bytes));
-   DRM_DEBUG("header_version_major: %u\n", 
le16_to_cpu(hdr->header_version_major));
-   DRM_DEBUG("header_version_minor: %u\n", 
le16_to_cpu(hdr->header_version_minor));
-   DRM_DEBUG("ip_version_major: %u\n", le16_to_cpu(hdr->ip_version_major));
-   DRM_DEBUG("ip_version_minor: %u\n", le16_to_cpu(hdr->ip_version_minor));
-   DRM_DEBUG("ucode_version: 0x%08x\n", le32_to_cpu(hdr->ucode_version));
-   DRM_DEBUG("ucode_size_bytes: %u\n", le32_to_cpu(hdr->ucode_size_bytes));
-   DRM_DEBUG("ucode_array_offset_bytes: %u\n",
- le32_to_cpu(hdr->ucode_array_offset_bytes));
-   DRM_DEBUG("crc32: 0x%08x\n", le32_to_cpu(hdr->crc32));
+   DRM_DEBUG("size_bytes: %u\n"
+ "header_size_bytes: %u\n"
+ "header_version_major: %u\n"
+ "header_version_minor: %u\n"
+ "ip_version_major: %u\n"
+ "ip_version_minor: %u\n"
+ "ucode_version: 0x%08x\n"
+ "ucode_size_bytes: %u\n"
+ "ucode_array_offset_bytes: %u\n"
+ "crc32: 0x%08x\n",
+ le32_to_cpu(hdr->size_bytes),
+ le32_to_cpu(hdr->header_size_bytes),
+ le16_to_cpu(hdr->header_version_major),
+ le16_to_cpu(hdr->header_version_minor),
+ le16_to_cpu(hdr->ip_version_major),
+ le16_to_cpu(hdr->ip_version_minor),
+ le32_to_cpu(hdr->ucode_version),
+ le32_to_cpu(hdr->ucode_size_bytes),
+ le32_to_cpu(hdr->ucode_array_offset_bytes),
+ le32_to_cpu(hdr->crc32));
 }
 
 void amdgpu_ucode_print_mc_hdr(const struct common_firmware_header *hdr)
@@ -55,9 +64,9 @@ void amdgpu_ucode_print_mc_hdr(const struct 
common_firmware_header *hdr)
const struct mc_firmware_header_v1_0 *mc_hdr =
container_of(hdr, struct mc_firmware_header_v1_0, 
header);
 
-   DRM_DEBUG("io_debug_size_bytes: %u\n",
- le32_to_cpu(mc_hdr->io_debug_size_bytes));
-   DRM_DEBUG("io_debug_array_offset_bytes: %u\n",
+   DRM_DEBUG("io_debug_size_bytes: %u\n"
+ "io_debug_array_offset_bytes: %u\n",
+ le32_to_cpu(mc_hdr->io_debug_size_bytes),
  le32_to_cpu(mc_hdr->io_debug_array_offset_bytes));
} else {
DRM_ERROR("Unknown MC ucode version: %u.%u\n", version_major, 
version_minor);
@@ -82,13 +91,17 @@ void amdgpu_ucode_print_smc_hdr(const struct 
common_firmware_header *hdr)
switch (version_minor) {
case 0:
v2_0_hdr = container_of(hdr, struct 
smc_firmware_header_v2_0, v1_0.header);
-   DRM_DEBUG("ppt_offset_bytes: %u\n", 
le32_to_cpu(v2_0_hdr->ppt_offset_bytes));
-   DRM_DEBUG("ppt_size_bytes: %u\n", 
le32_to_cpu(v2_0_hdr->ppt_size_bytes));
+   DRM_DEBUG("ppt_offset_bytes: %u\n"
+ "ppt_size_bytes: %u\n",
+ le32_to_cpu(v2_0_hdr->ppt_offset_bytes),
+ le32_to_cpu(v2_0_hdr->ppt_size_bytes));
break;
case 1:
v2_1_hdr = container_of(hdr, struct 
smc_firmware_header_v2_1, v1_0.header);
-   DRM_DEBUG("pptable_count: %u\n", 
le32_to_cpu(v2_1_hdr->pptable_count));
-   DRM_DEBUG("pptable_entry_offset: %u\n", 
le32_to_cpu(v2_1_hdr->pptable_entry_offset));
+   DRM_DEBUG("pptable_count: %u\n"
+ "pptable_entry_offset: %u\n",
+ le32_to_cpu(v2_1_hdr->pptable_count),
+ le32_to_cpu(v2_1_hdr->pptable_entry_offset));
break;
default:
break;
@@ -111,10 +124,12 @@ void