drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
Signed-off-by: Joe Perches joe@perches.com --- drivers/gpu/drm/drm_print.c | 28 +++++++++++++++++++++------- drivers/gpu/drm/i915/intel_display.c | 15 ++++----------- include/drm/drm_print.h | 27 ++++++++++++++------------- 3 files changed, 39 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 781518fd88e3..79abf6d5b4db 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -89,23 +89,37 @@ void drm_dev_printk(const struct device *dev, const char *level, } EXPORT_SYMBOL(drm_dev_printk);
-void drm_printk(const char *level, unsigned int category, - const char *format, ...) +void drm_dbg(unsigned int category, const char *format, ...) { struct va_format vaf; va_list args;
- if (category != DRM_UT_NONE && !(drm_debug & category)) + if (!(drm_debug & category)) return;
va_start(args, format); vaf.fmt = format; vaf.va = &args;
- printk("%s" "[" DRM_NAME ":%ps]%s %pV", - level, __builtin_return_address(0), - strcmp(level, KERN_ERR) == 0 ? " *ERROR*" : "", &vaf); + printk(KERN_DEBUG "[" DRM_NAME ":%ps] %pV", + __builtin_return_address(0), &vaf); + + va_end(args); +} +EXPORT_SYMBOL(drm_dbg); + +void drm_err(const char *format, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, format); + vaf.fmt = format; + vaf.va = &args; + + printk(KERN_ERR "[" DRM_NAME ":%ps] *ERROR* %pV", + __builtin_return_address(0), &vaf);
va_end(args); } -EXPORT_SYMBOL(drm_printk); +EXPORT_SYMBOL(drm_err); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2933ad38094f..d8e522e3cd39 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -11059,24 +11059,17 @@ intel_compare_link_m_n(const struct intel_link_m_n *m_n, static void __printf(3, 4) pipe_config_err(bool adjust, const char *name, const char *format, ...) { - char *level; - unsigned int category; struct va_format vaf; va_list args;
- if (adjust) { - level = KERN_DEBUG; - category = DRM_UT_KMS; - } else { - level = KERN_ERR; - category = DRM_UT_NONE; - } - va_start(args, format); vaf.fmt = format; vaf.va = &args;
- drm_printk(level, category, "mismatch in %s %pV", name, &vaf); + if (adjust) + drm_dbg(DRM_UT_KMS, "mismatch in %s %pV", name, &vaf); + else + drm_err("mismatch in %s %pV", name, &vaf);
va_end(args); } diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 2a4a42e59a47..3a40c5a3a5fa 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -200,9 +200,10 @@ __printf(6, 7) void drm_dev_printk(const struct device *dev, const char *level, unsigned int category, const char *function_name, const char *prefix, const char *format, ...); -__printf(3, 4) -void drm_printk(const char *level, unsigned int category, - const char *format, ...); +__printf(2, 3) +void drm_dbg(unsigned int category, const char *format, ...); +__printf(1, 2) +void drm_err(const char *format, ...);
/* Macros to make printk easier */
@@ -236,7 +237,7 @@ void drm_printk(const char *level, unsigned int category, drm_dev_printk(dev, KERN_ERR, DRM_UT_NONE, __func__, " *ERROR*",\ fmt, ##__VA_ARGS__) #define DRM_ERROR(fmt, ...) \ - drm_printk(KERN_ERR, DRM_UT_NONE, fmt, ##__VA_ARGS__) + drm_err(fmt, ##__VA_ARGS__)
/** * Rate limited error output. Like DRM_ERROR() but won't flood the log. @@ -279,40 +280,40 @@ void drm_printk(const char *level, unsigned int category, drm_dev_printk(dev, KERN_DEBUG, DRM_UT_CORE, __func__, "", fmt, \ ##args) #define DRM_DEBUG(fmt, ...) \ - drm_printk(KERN_DEBUG, DRM_UT_CORE, fmt, ##__VA_ARGS__) + drm_dbg(DRM_UT_CORE, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_DRIVER(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_DRIVER, __func__, "", \ fmt, ##args) #define DRM_DEBUG_DRIVER(fmt, ...) \ - drm_printk(KERN_DEBUG, DRM_UT_DRIVER, fmt, ##__VA_ARGS__) + drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_KMS(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_KMS, __func__, "", fmt, \ ##args) -#define DRM_DEBUG_KMS(fmt, ...) \ - drm_printk(KERN_DEBUG, DRM_UT_KMS, fmt, ##__VA_ARGS__) +#define DRM_DEBUG_KMS(fmt, ...) \ + drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_PRIME(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_PRIME, __func__, "", \ fmt, ##args) #define DRM_DEBUG_PRIME(fmt, ...) \ - drm_printk(KERN_DEBUG, DRM_UT_PRIME, fmt, ##__VA_ARGS__) + drm_dbg(DRM_UT_PRIME, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_ATOMIC(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_ATOMIC, __func__, "", \ fmt, ##args) #define DRM_DEBUG_ATOMIC(fmt, ...) \ - drm_printk(KERN_DEBUG, DRM_UT_ATOMIC, fmt, ##__VA_ARGS__) + drm_dbg(DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_VBL(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_VBL, __func__, "", fmt, \ ##args) -#define DRM_DEBUG_VBL(fmt, ...) \ - drm_printk(KERN_DEBUG, DRM_UT_VBL, fmt, ##__VA_ARGS__) +#define DRM_DEBUG_VBL(fmt, ...) \ + drm_dbg(DRM_UT_VBL, fmt, ##__VA_ARGS__)
#define DRM_DEBUG_LEASE(fmt, ...) \ - drm_printk(KERN_DEBUG, DRM_UT_LEASE, fmt, ##__VA_ARGS__) + drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__)
#define _DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, level, fmt, args...) \ ({ \
Op 13-03-18 om 23:02 schreef Joe Perches:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
Signed-off-by: Joe Perches joe@perches.com
I guess this adds up. Nice reduction. :)
drivers/gpu/drm/drm_print.c | 28 +++++++++++++++++++++------- drivers/gpu/drm/i915/intel_display.c | 15 ++++----------- include/drm/drm_print.h | 27 ++++++++++++++------------- 3 files changed, 39 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 781518fd88e3..79abf6d5b4db 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -89,23 +89,37 @@ void drm_dev_printk(const struct device *dev, const char *level, } EXPORT_SYMBOL(drm_dev_printk);
-void drm_printk(const char *level, unsigned int category,
const char *format, ...)+void drm_dbg(unsigned int category, const char *format, ...) { struct va_format vaf; va_list args;
- if (category != DRM_UT_NONE && !(drm_debug & category))
if (!(drm_debug & category)) return;
va_start(args, format); vaf.fmt = format; vaf.va = &args;
- printk("%s" "[" DRM_NAME ":%ps]%s %pV",
level, __builtin_return_address(0),strcmp(level, KERN_ERR) == 0 ? " *ERROR*" : "", &vaf);
- printk(KERN_DEBUG "[" DRM_NAME ":%ps] %pV",
__builtin_return_address(0), &vaf);- va_end(args);
+} +EXPORT_SYMBOL(drm_dbg);
+void drm_err(const char *format, ...) +{
struct va_format vaf;
va_list args;
va_start(args, format);
vaf.fmt = format;
vaf.va = &args;
printk(KERN_ERR "[" DRM_NAME ":%ps] *ERROR* %pV",
__builtin_return_address(0), &vaf);va_end(args);
} -EXPORT_SYMBOL(drm_printk); +EXPORT_SYMBOL(drm_err); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2933ad38094f..d8e522e3cd39 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -11059,24 +11059,17 @@ intel_compare_link_m_n(const struct intel_link_m_n *m_n, static void __printf(3, 4) pipe_config_err(bool adjust, const char *name, const char *format, ...) {
char *level;
unsigned int category; struct va_format vaf; va_list args;
if (adjust) {
level = KERN_DEBUG;category = DRM_UT_KMS;} else {
level = KERN_ERR;category = DRM_UT_NONE;}
va_start(args, format); vaf.fmt = format; vaf.va = &args;
drm_printk(level, category, "mismatch in %s %pV", name, &vaf);
- if (adjust)
drm_dbg(DRM_UT_KMS, "mismatch in %s %pV", name, &vaf);- else
drm_err("mismatch in %s %pV", name, &vaf);
Could this use DRM_DEBUG_KMS/DRM_ERROR?
Rest looks good, so I can fix up if you want.
~Maarten
On Thu, 2018-03-15 at 14:22 +0100, Maarten Lankhorst wrote:
Op 13-03-18 om 23:02 schreef Joe Perches:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
[]
I guess this adds up. Nice reduction. :)
Yup. 1% of all drm object code.
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
[]
- drm_printk(level, category, "mismatch in %s %pV", name, &vaf);
- if (adjust)
drm_dbg(DRM_UT_KMS, "mismatch in %s %pV", name, &vaf);- else
drm_err("mismatch in %s %pV", name, &vaf);Could this use DRM_DEBUG_KMS/DRM_ERROR?
Rest looks good, so I can fix up if you want.
If want you change something like that, it should be separate patch.
btw: There was separate patch that also reduced object size of the drm_dev_printk calls several months ago. Never applied.
https://lkml.org/lkml/2017/9/25/247
cheers, Joe
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
How much would we lose if we move the (drm_debug&FOO) outside the functions again? I'm somewhat concerned about all the function call overhead when debugs aren't even enabled.
Signed-off-by: Joe Perches joe@perches.com
drivers/gpu/drm/drm_print.c | 28 +++++++++++++++++++++------- drivers/gpu/drm/i915/intel_display.c | 15 ++++----------- include/drm/drm_print.h | 27 ++++++++++++++------------- 3 files changed, 39 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 781518fd88e3..79abf6d5b4db 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -89,23 +89,37 @@ void drm_dev_printk(const struct device *dev, const char *level, } EXPORT_SYMBOL(drm_dev_printk);
-void drm_printk(const char *level, unsigned int category,
const char *format, ...)+void drm_dbg(unsigned int category, const char *format, ...) { struct va_format vaf; va_list args;
- if (category != DRM_UT_NONE && !(drm_debug & category))
if (!(drm_debug & category)) return;
va_start(args, format); vaf.fmt = format; vaf.va = &args;
- printk("%s" "[" DRM_NAME ":%ps]%s %pV",
level, __builtin_return_address(0),strcmp(level, KERN_ERR) == 0 ? " *ERROR*" : "", &vaf);
- printk(KERN_DEBUG "[" DRM_NAME ":%ps] %pV",
__builtin_return_address(0), &vaf);- va_end(args);
+} +EXPORT_SYMBOL(drm_dbg);
+void drm_err(const char *format, ...) +{
struct va_format vaf;
va_list args;
va_start(args, format);
vaf.fmt = format;
vaf.va = &args;
printk(KERN_ERR "[" DRM_NAME ":%ps] *ERROR* %pV",
__builtin_return_address(0), &vaf);va_end(args);
} -EXPORT_SYMBOL(drm_printk); +EXPORT_SYMBOL(drm_err); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2933ad38094f..d8e522e3cd39 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -11059,24 +11059,17 @@ intel_compare_link_m_n(const struct intel_link_m_n *m_n, static void __printf(3, 4) pipe_config_err(bool adjust, const char *name, const char *format, ...) {
char *level;
unsigned int category; struct va_format vaf; va_list args;
if (adjust) {
level = KERN_DEBUG;category = DRM_UT_KMS;} else {
level = KERN_ERR;category = DRM_UT_NONE;}
va_start(args, format); vaf.fmt = format; vaf.va = &args;
drm_printk(level, category, "mismatch in %s %pV", name, &vaf);
if (adjust)
drm_dbg(DRM_UT_KMS, "mismatch in %s %pV", name, &vaf);else
drm_err("mismatch in %s %pV", name, &vaf);va_end(args);
} diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 2a4a42e59a47..3a40c5a3a5fa 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -200,9 +200,10 @@ __printf(6, 7) void drm_dev_printk(const struct device *dev, const char *level, unsigned int category, const char *function_name, const char *prefix, const char *format, ...); -__printf(3, 4) -void drm_printk(const char *level, unsigned int category,
const char *format, ...);+__printf(2, 3) +void drm_dbg(unsigned int category, const char *format, ...); +__printf(1, 2) +void drm_err(const char *format, ...);
/* Macros to make printk easier */
@@ -236,7 +237,7 @@ void drm_printk(const char *level, unsigned int category, drm_dev_printk(dev, KERN_ERR, DRM_UT_NONE, __func__, " *ERROR*",\ fmt, ##__VA_ARGS__) #define DRM_ERROR(fmt, ...) \
- drm_printk(KERN_ERR, DRM_UT_NONE, fmt, ##__VA_ARGS__)
- drm_err(fmt, ##__VA_ARGS__)
/**
- Rate limited error output. Like DRM_ERROR() but won't flood the log.
@@ -279,40 +280,40 @@ void drm_printk(const char *level, unsigned int category, drm_dev_printk(dev, KERN_DEBUG, DRM_UT_CORE, __func__, "", fmt, \ ##args) #define DRM_DEBUG(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_CORE, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_CORE, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_DRIVER(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_DRIVER, __func__, "", \ fmt, ##args) #define DRM_DEBUG_DRIVER(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_KMS(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_KMS, __func__, "", fmt, \ ##args) -#define DRM_DEBUG_KMS(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_KMS, fmt, ##__VA_ARGS__)
+#define DRM_DEBUG_KMS(fmt, ...) \
- drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_PRIME(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_PRIME, __func__, "", \ fmt, ##args) #define DRM_DEBUG_PRIME(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_PRIME, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_PRIME, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_ATOMIC(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_ATOMIC, __func__, "", \ fmt, ##args) #define DRM_DEBUG_ATOMIC(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_VBL(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_VBL, __func__, "", fmt, \ ##args) -#define DRM_DEBUG_VBL(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_VBL, fmt, ##__VA_ARGS__)
+#define DRM_DEBUG_VBL(fmt, ...) \
- drm_dbg(DRM_UT_VBL, fmt, ##__VA_ARGS__)
#define DRM_DEBUG_LEASE(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_LEASE, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__)
#define _DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, level, fmt, args...) \ ({ \ -- 2.15.0
dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Op 15-03-18 om 14:30 schreef Ville Syrjälä:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
How much would we lose if we move the (drm_debug&FOO) outside the functions again? I'm somewhat concerned about all the function call overhead when debugs aren't even enabled.
Upstream: text data bss dec hex filename 377143 5689 4352 387184 5e870 drivers/gpu/drm/drm.ko
With this patch: 373831 5689 4352 383872 5db80 drivers/gpu/drm/drm.ko
Moving the if outside (below): 377629 5689 4352 387670 5ea56 drivers/gpu/drm/drm.ko
Bye savings..
I don't think there are any places in which the debug output is performance sensitive, so I'm ok with not inlining. --- diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 79abf6d5b4db..928822403a59 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -89,14 +89,11 @@ void drm_dev_printk(const struct device *dev, const char *level, } EXPORT_SYMBOL(drm_dev_printk);
-void drm_dbg(unsigned int category, const char *format, ...) +void __drm_dbg(const char *format, ...) { struct va_format vaf; va_list args;
- if (!(drm_debug & category)) - return; - va_start(args, format); vaf.fmt = format; vaf.va = &args; @@ -106,7 +103,7 @@ void drm_dbg(unsigned int category, const char *format, ...)
va_end(args); } -EXPORT_SYMBOL(drm_dbg); +EXPORT_SYMBOL(__drm_dbg);
void drm_err(const char *format, ...) { diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 3a40c5a3a5fa..2a145b97bdfc 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -200,8 +200,17 @@ __printf(6, 7) void drm_dev_printk(const struct device *dev, const char *level, unsigned int category, const char *function_name, const char *prefix, const char *format, ...); -__printf(2, 3) -void drm_dbg(unsigned int category, const char *format, ...); + +__printf(1, 2) +void __drm_dbg(const char *format, ...); + + +#define drm_dbg(category, format, ...) \ + do { \ + if (drm_debug & category) \ + __drm_dbg(format, ## __VA_ARGS__); \ + } while (0) + __printf(1, 2) void drm_err(const char *format, ...);
On Thu, Mar 15, 2018 at 03:04:52PM +0100, Maarten Lankhorst wrote:
Op 15-03-18 om 14:30 schreef Ville Syrjälä:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
How much would we lose if we move the (drm_debug&FOO) outside the functions again? I'm somewhat concerned about all the function call overhead when debugs aren't even enabled.
Upstream: text data bss dec hex filename 377143 5689 4352 387184 5e870 drivers/gpu/drm/drm.ko
With this patch: 373831 5689 4352 383872 5db80 drivers/gpu/drm/drm.ko
Moving the if outside (below): 377629 5689 4352 387670 5ea56 drivers/gpu/drm/drm.ko
Bye savings..
I don't think there are any places in which the debug output is performance sensitive, so I'm ok with not inlining.
Not performance sensitive as such perhaps. But pointlessly wasting cpu cycles for nop function calls isn't particularly great. Would be nice to actually measure how much overhead there is on some weaker systems. IIRC older Atoms were particularly bad at this stuff.
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 79abf6d5b4db..928822403a59 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -89,14 +89,11 @@ void drm_dev_printk(const struct device *dev, const char *level, } EXPORT_SYMBOL(drm_dev_printk);
-void drm_dbg(unsigned int category, const char *format, ...) +void __drm_dbg(const char *format, ...) { struct va_format vaf; va_list args;
- if (!(drm_debug & category))
return;- va_start(args, format); vaf.fmt = format; vaf.va = &args;
@@ -106,7 +103,7 @@ void drm_dbg(unsigned int category, const char *format, ...)
va_end(args); } -EXPORT_SYMBOL(drm_dbg); +EXPORT_SYMBOL(__drm_dbg);
void drm_err(const char *format, ...) { diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 3a40c5a3a5fa..2a145b97bdfc 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -200,8 +200,17 @@ __printf(6, 7) void drm_dev_printk(const struct device *dev, const char *level, unsigned int category, const char *function_name, const char *prefix, const char *format, ...); -__printf(2, 3) -void drm_dbg(unsigned int category, const char *format, ...);
+__printf(1, 2) +void __drm_dbg(const char *format, ...);
+#define drm_dbg(category, format, ...) \
- do { \
if (drm_debug & category) \__drm_dbg(format, ## __VA_ARGS__); \- } while (0)
__printf(1, 2) void drm_err(const char *format, ...);
On Thu, 2018-03-15 at 17:05 +0200, Ville Syrjälä wrote:
On Thu, Mar 15, 2018 at 03:04:52PM +0100, Maarten Lankhorst wrote:
Op 15-03-18 om 14:30 schreef Ville Syrjälä:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
How much would we lose if we move the (drm_debug&FOO) outside the functions again?
again?
I'm somewhat concerned about all the function call overhead when debugs aren't even enabled.
Perhaps better to have compilation elimination of the entire debug output instead.
I think you are discussing a different issue and this discussion should not block this patch as this patch has no impact other than code size reduction.
On Thu, Mar 15, 2018 at 08:17:53AM -0700, Joe Perches wrote:
On Thu, 2018-03-15 at 17:05 +0200, Ville Syrjälä wrote:
On Thu, Mar 15, 2018 at 03:04:52PM +0100, Maarten Lankhorst wrote:
Op 15-03-18 om 14:30 schreef Ville Syrjälä:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
How much would we lose if we move the (drm_debug&FOO) outside the functions again?
again?
We used to do that. Someone changed it a while back, unintentially I believe.
I'm somewhat concerned about all the function call overhead when debugs aren't even enabled.
Perhaps better to have compilation elimination of the entire debug output instead.
That would require every bug reporter to recompile the kernel first. So this is not a solution we would ever seriously consider.
Not sure if it would be possible to use the alternatives thing to eliminate the function calls unless the user boots wih drm.debug!=0?
I think you are discussing a different issue and this discussion should not block this patch as this patch has no impact other than code size reduction.
But what is the goal of the code size reduction? I assume the main goal is to make better use of the instruction cache to make the code faster. If there's a tradeoff between smaller and slightly faster vs. larger and a singificantly faster I tend to think we should go for the latter option.
On Thu, 2018-03-15 at 17:37 +0200, Ville Syrjälä wrote:
On Thu, Mar 15, 2018 at 08:17:53AM -0700, Joe Perches wrote:
On Thu, 2018-03-15 at 17:05 +0200, Ville Syrjälä wrote:
On Thu, Mar 15, 2018 at 03:04:52PM +0100, Maarten Lankhorst wrote:
Op 15-03-18 om 14:30 schreef Ville Syrjälä:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
How much would we lose if we move the (drm_debug&FOO) outside the functions again?
again?
We used to do that. Someone changed it a while back, unintentially I believe.
I'm somewhat concerned about all the function call overhead when debugs aren't even enabled.
Perhaps better to have compilation elimination of the entire debug output instead.
That would require every bug reporter to recompile the kernel first. So this is not a solution we would ever seriously consider.
Not sure if it would be possible to use the alternatives thing to eliminate the function calls unless the user boots wih drm.debug!=0?
I think you are discussing a different issue and this discussion should not block this patch as this patch has no impact other than code size reduction.
But what is the goal of the code size reduction?
Smaller code.
I assume the main goal is to make better use of the instruction cache to make the code faster. If there's a tradeoff between smaller and slightly faster vs. larger and a singificantly faster I tend to think we should go for the latter option.
There's no trade-off in this patch for faster/larger. This patch is simply smaller. Smaller is better.
Your faster/larger should be a different patch proposal.
On Thu, Mar 15, 2018 at 08:44:05AM -0700, Joe Perches wrote:
On Thu, 2018-03-15 at 17:37 +0200, Ville Syrjälä wrote:
On Thu, Mar 15, 2018 at 08:17:53AM -0700, Joe Perches wrote:
On Thu, 2018-03-15 at 17:05 +0200, Ville Syrjälä wrote:
On Thu, Mar 15, 2018 at 03:04:52PM +0100, Maarten Lankhorst wrote:
Op 15-03-18 om 14:30 schreef Ville Syrjälä:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote: > drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary > arguments that can be removed by creating separate functins. > > Create specific functions for these calls to reduce x86/64 defconfig > size by ~20k. > > Modify the existing macros to use the specific calls. > > new: > $ size -t drivers/gpu/drm/built-in.a | tail -1 > 1876562 44542 995 1922099 1d5433 (TOTALS) > > old: > $ size -t drivers/gpu/drm/built-in.a | tail -1 > 1897565 44542 995 1943102 1da63e (TOTALS) > > Miscellanea: > > o intel_display requires a change to use the specific calls.
How much would we lose if we move the (drm_debug&FOO) outside the functions again?
again?
We used to do that. Someone changed it a while back, unintentially I believe.
I'm somewhat concerned about all the function call overhead when debugs aren't even enabled.
Perhaps better to have compilation elimination of the entire debug output instead.
That would require every bug reporter to recompile the kernel first. So this is not a solution we would ever seriously consider.
Not sure if it would be possible to use the alternatives thing to eliminate the function calls unless the user boots wih drm.debug!=0?
I think you are discussing a different issue and this discussion should not block this patch as this patch has no impact other than code size reduction.
But what is the goal of the code size reduction?
Smaller code.
I assume the main goal is to make better use of the instruction cache to make the code faster. If there's a tradeoff between smaller and slightly faster vs. larger and a singificantly faster I tend to think we should go for the latter option.
There's no trade-off in this patch for faster/larger. This patch is simply smaller. Smaller is better.
This feels a bit like saying pink is better than red because it's more pink.
That said, I'm not arguing against this patch as such. Making things smaller "just because" usually doesn't cause problems. But I was hoping that we might be after some more tangible gains here, and thus pointed out that there may be a better way to achieve even bigger gains.
On Thu, 2018-03-15 at 18:14 +0200, Ville Syrjälä wrote:
There's no trade-off in this patch for faster/larger. This patch is simply smaller. Smaller is better.
This feels a bit like saying pink is better than red because it's more pink.
Silly. If you can't say smaller total object code that performs the same task identically is better, I think we can't discuss much of anything about code together.
Any printk related mechanism is not fast-path so any icache dilution isn't an issue.
That said, I'm not arguing against this patch as such. Making things smaller "just because" usually doesn't cause problems.
It seems more like you haven't read the patch.
But I was hoping that we might be after some more tangible gains here, and thus pointed out that there may be a better way to achieve even bigger gains.
Sure, it's just any such a discussion should not affect this patch being applied.
This patch reduces the argument count of the drm_printk (now drm_dbg) call and so is faster to execute even if the emit test is internal to the drm_dbg function.
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
Signed-off-by: Joe Perches joe@perches.com
Impressed with the size of the bikeshed piled on top of this I decided to cut this all short by merging it.
Thanks for the patch. -Daniel
drivers/gpu/drm/drm_print.c | 28 +++++++++++++++++++++------- drivers/gpu/drm/i915/intel_display.c | 15 ++++----------- include/drm/drm_print.h | 27 ++++++++++++++------------- 3 files changed, 39 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 781518fd88e3..79abf6d5b4db 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -89,23 +89,37 @@ void drm_dev_printk(const struct device *dev, const char *level, } EXPORT_SYMBOL(drm_dev_printk);
-void drm_printk(const char *level, unsigned int category,
const char *format, ...)+void drm_dbg(unsigned int category, const char *format, ...) { struct va_format vaf; va_list args;
- if (category != DRM_UT_NONE && !(drm_debug & category))
if (!(drm_debug & category)) return;
va_start(args, format); vaf.fmt = format; vaf.va = &args;
- printk("%s" "[" DRM_NAME ":%ps]%s %pV",
level, __builtin_return_address(0),strcmp(level, KERN_ERR) == 0 ? " *ERROR*" : "", &vaf);
- printk(KERN_DEBUG "[" DRM_NAME ":%ps] %pV",
__builtin_return_address(0), &vaf);- va_end(args);
+} +EXPORT_SYMBOL(drm_dbg);
+void drm_err(const char *format, ...) +{
struct va_format vaf;
va_list args;
va_start(args, format);
vaf.fmt = format;
vaf.va = &args;
printk(KERN_ERR "[" DRM_NAME ":%ps] *ERROR* %pV",
__builtin_return_address(0), &vaf);va_end(args);
} -EXPORT_SYMBOL(drm_printk); +EXPORT_SYMBOL(drm_err); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2933ad38094f..d8e522e3cd39 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -11059,24 +11059,17 @@ intel_compare_link_m_n(const struct intel_link_m_n *m_n, static void __printf(3, 4) pipe_config_err(bool adjust, const char *name, const char *format, ...) {
char *level;
unsigned int category; struct va_format vaf; va_list args;
if (adjust) {
level = KERN_DEBUG;category = DRM_UT_KMS;} else {
level = KERN_ERR;category = DRM_UT_NONE;}
va_start(args, format); vaf.fmt = format; vaf.va = &args;
drm_printk(level, category, "mismatch in %s %pV", name, &vaf);
if (adjust)
drm_dbg(DRM_UT_KMS, "mismatch in %s %pV", name, &vaf);else
drm_err("mismatch in %s %pV", name, &vaf);va_end(args);
} diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index 2a4a42e59a47..3a40c5a3a5fa 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -200,9 +200,10 @@ __printf(6, 7) void drm_dev_printk(const struct device *dev, const char *level, unsigned int category, const char *function_name, const char *prefix, const char *format, ...); -__printf(3, 4) -void drm_printk(const char *level, unsigned int category,
const char *format, ...);+__printf(2, 3) +void drm_dbg(unsigned int category, const char *format, ...); +__printf(1, 2) +void drm_err(const char *format, ...);
/* Macros to make printk easier */
@@ -236,7 +237,7 @@ void drm_printk(const char *level, unsigned int category, drm_dev_printk(dev, KERN_ERR, DRM_UT_NONE, __func__, " *ERROR*",\ fmt, ##__VA_ARGS__) #define DRM_ERROR(fmt, ...) \
- drm_printk(KERN_ERR, DRM_UT_NONE, fmt, ##__VA_ARGS__)
- drm_err(fmt, ##__VA_ARGS__)
/**
- Rate limited error output. Like DRM_ERROR() but won't flood the log.
@@ -279,40 +280,40 @@ void drm_printk(const char *level, unsigned int category, drm_dev_printk(dev, KERN_DEBUG, DRM_UT_CORE, __func__, "", fmt, \ ##args) #define DRM_DEBUG(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_CORE, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_CORE, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_DRIVER(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_DRIVER, __func__, "", \ fmt, ##args) #define DRM_DEBUG_DRIVER(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_KMS(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_KMS, __func__, "", fmt, \ ##args) -#define DRM_DEBUG_KMS(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_KMS, fmt, ##__VA_ARGS__)
+#define DRM_DEBUG_KMS(fmt, ...) \
- drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_PRIME(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_PRIME, __func__, "", \ fmt, ##args) #define DRM_DEBUG_PRIME(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_PRIME, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_PRIME, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_ATOMIC(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_ATOMIC, __func__, "", \ fmt, ##args) #define DRM_DEBUG_ATOMIC(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
#define DRM_DEV_DEBUG_VBL(dev, fmt, args...) \ drm_dev_printk(dev, KERN_DEBUG, DRM_UT_VBL, __func__, "", fmt, \ ##args) -#define DRM_DEBUG_VBL(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_VBL, fmt, ##__VA_ARGS__)
+#define DRM_DEBUG_VBL(fmt, ...) \
- drm_dbg(DRM_UT_VBL, fmt, ##__VA_ARGS__)
#define DRM_DEBUG_LEASE(fmt, ...) \
- drm_printk(KERN_DEBUG, DRM_UT_LEASE, fmt, ##__VA_ARGS__)
- drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__)
#define _DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, level, fmt, args...) \ ({ \ -- 2.15.0
dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
On Fri, 2018-03-16 at 08:41 +0100, Daniel Vetter wrote:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
Signed-off-by: Joe Perches joe@perches.com
Impressed with the size of the bikeshed piled on top of this I decided to cut this all short by merging it.
Thanks.
There was a similar patch for the DRM_DEV_ macros awhile ago that also reduced object code.
https://lkml.org/lkml/2017/9/25/247
Never applied.
Want a remerge resend?
On Fri, Mar 16, 2018 at 05:29:02AM -0700, Joe Perches wrote:
On Fri, 2018-03-16 at 08:41 +0100, Daniel Vetter wrote:
On Tue, Mar 13, 2018 at 03:02:15PM -0700, Joe Perches wrote:
drm_printk is used for both DRM_ERROR and DRM_DEBUG with unnecessary arguments that can be removed by creating separate functins.
Create specific functions for these calls to reduce x86/64 defconfig size by ~20k.
Modify the existing macros to use the specific calls.
new: $ size -t drivers/gpu/drm/built-in.a | tail -1 1876562 44542 995 1922099 1d5433 (TOTALS)
old: $ size -t drivers/gpu/drm/built-in.a | tail -1 1897565 44542 995 1943102 1da63e (TOTALS)
Miscellanea:
o intel_display requires a change to use the specific calls.
Signed-off-by: Joe Perches joe@perches.com
Impressed with the size of the bikeshed piled on top of this I decided to cut this all short by merging it.
Thanks.
There was a similar patch for the DRM_DEV_ macros awhile ago that also reduced object code.
https://lkml.org/lkml/2017/9/25/247
Never applied.
Want a remerge resend?
Yeah dropped out of my inbox, resending is easier. Please do so.
In case you wonder, I try to fairly intentionally drop stuff on the floor, to force other people on dri-devel to not load everything onto me, making me a bottleneck. But then occasionally a patch drops through all nets because tracking mailing lists is impossible :-/ -Daniel
dri-devel@lists.freedesktop.org
-
Daniel Vetter -
Joe Perches -
Maarten Lankhorst -
Ville Syrjälä