ipmi: kcs_bmc: optimize the data buffers allocation
PATCH 1/1 ipmi: kcs_bmc: optimize the data buffers allocation
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
--- drivers/char/ipmi/kcs_bmc.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
drivers/char/ipmi/kcs_bmc.c +6 -4
@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = {struct kcs_bmc *kcs_bmc_alloc (struct device *dev,int sizeof_priv,u32 channel) {struct kcs_bmc *kcs_bmc; +void *buf; kcs_bmc =devm_kzalloc (dev,sizeof (*kcs_bmc) + sizeof_priv,GFP_KERNEL );if (!kcs_bmc)
@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel)mutex_init (&kcs_bmc->mutex);init_waitqueue_head (&kcs_bmc->queue); - kcs_bmc->data_in =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); - kcs_bmc->data_out =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); - kcs_bmc->kbuffer =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); -if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf =devm_kmalloc_array (dev,3 ,KCS_MSG_BUFSIZ ,GFP_KERNEL ); +if (!buf)return NULL ; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf +KCS_MSG_BUFSIZ ; + kcs_bmc->kbuffer = buf +KCS_MSG_BUFSIZ *2 ; kcs_bmc->miscdev.minor =MISC_DYNAMIC_MINOR ; kcs_bmc->miscdev.name =dev_name (dev);
Signature · 1 line
2.7.4
Hi Corey,
The 4.17 merge window is opened now, this patch is not yet in linux-next tree,
so it will be merged into 4.18 ?
Thanks & Regards,
Haiyue
Quoted 37 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
Signed-off-by Haiyue Wang <[email protected]>--- drivers/char/ipmi/kcs_bmc.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-4@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = {struct kcs_bmc *kcs_bmc_alloc (struct device *dev,int sizeof_priv,u32 channel) {struct kcs_bmc *kcs_bmc; +void *buf; kcs_bmc =devm_kzalloc (dev,sizeof (*kcs_bmc) + sizeof_priv,GFP_KERNEL );if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel)mutex_init (&kcs_bmc->mutex);init_waitqueue_head (&kcs_bmc->queue); - kcs_bmc->data_in =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); - kcs_bmc->data_out =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); - kcs_bmc->kbuffer =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); -if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf =devm_kmalloc_array (dev,3 ,KCS_MSG_BUFSIZ ,GFP_KERNEL ); +if (!buf)return NULL ; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf +KCS_MSG_BUFSIZ ; + kcs_bmc->kbuffer = buf +KCS_MSG_BUFSIZ *2 ; kcs_bmc->miscdev.minor =MISC_DYNAMIC_MINOR ; kcs_bmc->miscdev.name =dev_name (dev);
Quoted 6 lines · Haiyue
Hi Corey,
The 4.17 merge window is opened now, this patch is not yet in linux-next tree,
so it will be merged into 4.18 ?
Yeah, this came in kind of late, and I had some other critical things I was having to focus on, so I've been kind of out of the loop.
If it's urgent, I can work on getting it into 4.17 later, but I'd rather wait on 4.18.
-corey
Quoted 41 lines
Thanks & Regards,
Haiyue
Quoted 35 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
Signed-off-by Haiyue Wang <[email protected]>---
drivers/char/ipmi/kcs_bmc.c| 10 ++++++----1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-3@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = { struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) { struct kcs_bmc *kcs_bmc; + void *buf; kcs_bmc = devm_kzalloc(dev, sizeof(*kcs_bmc) + sizeof_priv, GFP_KERNEL); if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) mutex_init(&kcs_bmc->mutex); init_waitqueue_head(&kcs_bmc->queue); - kcs_bmc->data_in = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->data_out = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->kbuffer = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf = devm_kmalloc_array(dev, 3, KCS_MSG_BUFSIZ, GFP_KERNEL); + if (!buf) return NULL; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf + KCS_MSG_BUFSIZ; + kcs_bmc->kbuffer = buf + KCS_MSG_BUFSIZ * 2; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; kcs_bmc->miscdev.name = dev_name(dev);
Just a small piece of cake, not so urgent. I just try to understand
the code commitment process, such as time etc. :)
Thanks!
BR,
Haiyue
Quoted 59 lines · Corey Minyard
Quoted 6 lines · Haiyue
Hi Corey,
The 4.17 merge window is opened now, this patch is not yet in linux-next tree,
so it will be merged into 4.18 ?
Yeah, this came in kind of late, and I had some other critical things I was having to focus on, so I've been kind of out of the loop.
If it's urgent, I can work on getting it into 4.17 later, but I'd rather wait on 4.18.
-corey
Quoted 42 lines
Thanks & Regards,
Haiyue
Quoted 36 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
Signed-off-by Haiyue Wang <[email protected]>---
drivers/char/ipmi/kcs_bmc.c| 10 ++++++----1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-3@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = { struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) { struct kcs_bmc *kcs_bmc; + void *buf; kcs_bmc = devm_kzalloc(dev, sizeof(*kcs_bmc) + sizeof_priv, GFP_KERNEL); if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) mutex_init(&kcs_bmc->mutex); init_waitqueue_head(&kcs_bmc->queue); - kcs_bmc->data_in = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->data_out = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->kbuffer = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf = devm_kmalloc_array(dev, 3, KCS_MSG_BUFSIZ, GFP_KERNEL); + if (!buf) return NULL; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf + KCS_MSG_BUFSIZ; + kcs_bmc->kbuffer = buf + KCS_MSG_BUFSIZ * 2; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; kcs_bmc->miscdev.name = dev_name(dev);
Quoted 2 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
I'm finally getting to this.
Is there a reason you want to do this? In general, it's better to not try to outsmart your base system. Depending on the memory allocator, in this case, you might actually use more memory. You probably won't use any less.
In the original case, you allocate three 1000 byte buffers, resulting in 3 1024 byte slab allocated.
In the changed case, you will allocate a 3000 byte buffer, resulting in a single 4096 byte slab allocation, wasting 1024 more bytes of memory.
-corey
Quoted 34 lines
Signed-off-by Haiyue Wang <[email protected]>--- drivers/char/ipmi/kcs_bmc.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-4@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = {struct kcs_bmc *kcs_bmc_alloc (struct device *dev,int sizeof_priv,u32 channel) {struct kcs_bmc *kcs_bmc; +void *buf; kcs_bmc =devm_kzalloc (dev,sizeof (*kcs_bmc) + sizeof_priv,GFP_KERNEL );if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel)mutex_init (&kcs_bmc->mutex);init_waitqueue_head (&kcs_bmc->queue); - kcs_bmc->data_in =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); - kcs_bmc->data_out =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); - kcs_bmc->kbuffer =devm_kmalloc (dev,KCS_MSG_BUFSIZ ,GFP_KERNEL ); -if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf =devm_kmalloc_array (dev,3 ,KCS_MSG_BUFSIZ ,GFP_KERNEL ); +if (!buf)return NULL ; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf +KCS_MSG_BUFSIZ ; + kcs_bmc->kbuffer = buf +KCS_MSG_BUFSIZ *2 ; kcs_bmc->miscdev.minor =MISC_DYNAMIC_MINOR ; kcs_bmc->miscdev.name =dev_name (dev);
Quoted 11 lines · Corey Minyard
Quoted 2 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
I'm finally getting to this.
Is there a reason you want to do this? In general, it's better to not try to outsmart your base system. Depending on the memory allocator, in this case, you might actually use more memory. You probably won't use any less.
I got this idea from another code review, but that patch allocates 30 more the same size memory block, reducing the devm_kmalloc call will be better. For KCS only have 3, may be the key point is memory waste.
Quoted 6 lines
In the original case, you allocate three 1000 byte buffers, resulting in 3 1024 byte slab allocated.
In the changed case, you will allocate a 3000 byte buffer, resulting in a single 4096 byte slab allocation, wasting 1024 more bytes of memory.
As the kcs has memory copy between in/out/kbuffer, put them in the same page will be better ? Such as the same TLB ? (Well, I just got this from book, no real experience of memory accessing performance. And also, I was told that using space to save the time. :-)).
Just my stupid thinking. I'm OK to drop this patch if it doesn't help with performance, or something else.
BR.
Haiyue
Quoted 36 lines
-corey
Quoted 32 lines
Signed-off-by Haiyue Wang <[email protected]>---
drivers/char/ipmi/kcs_bmc.c| 10 ++++++----1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-3@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = { struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) { struct kcs_bmc *kcs_bmc; + void *buf; kcs_bmc = devm_kzalloc(dev, sizeof(*kcs_bmc) + sizeof_priv, GFP_KERNEL); if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) mutex_init(&kcs_bmc->mutex); init_waitqueue_head(&kcs_bmc->queue); - kcs_bmc->data_in = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->data_out = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->kbuffer = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf = devm_kmalloc_array(dev, 3, KCS_MSG_BUFSIZ, GFP_KERNEL); + if (!buf) return NULL; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf + KCS_MSG_BUFSIZ; + kcs_bmc->kbuffer = buf + KCS_MSG_BUFSIZ * 2; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; kcs_bmc->miscdev.name = dev_name(dev);
Hi Corey,
Since IPMI 2.0 just defined minimum, no maximum:
----
KCS/SMIC Input : Required: 40 bytes IPMI Message, minimum
KCS/SMIC Output : Required: 38 bytes IPMI Message, minimum
----
We can enlarge the block size for avoiding waste, and make our driver
support most worst message size case. And I think this patch make checking
simple (from 3 to 1), and the code clean, this is the biggest reason I want to
change. The TLB is just memory management study from book, no data to
support access improvement. :)
BR,
Haiyue
Quoted 73 lines · Haiyue
Quoted 11 lines · Corey Minyard
Quoted 2 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
I'm finally getting to this.
Is there a reason you want to do this? In general, it's better to not try to outsmart your base system. Depending on the memory allocator, in this case, you might actually use more memory. You probably won't use any less.
I got this idea from another code review, but that patch allocates 30 more the same size memory block, reducing the
devm_kmalloccall will be better. For KCS only have 3, may be the key point is memory waste.Quoted 6 lines
In the original case, you allocate three 1000 byte buffers, resulting in 3 1024 byte slab allocated.
In the changed case, you will allocate a 3000 byte buffer, resulting in a single 4096 byte slab allocation, wasting 1024 more bytes of memory.
As the kcs has memory copy between in/out/kbuffer, put them in the same page will be better ? Such as the same TLB ? (Well, I just got this from book, no real experience of memory accessing performance. And also, I was told that using space to save the time. :-)).
Just my stupid thinking. I'm OK to drop this patch if it doesn't help with performance, or something else.
BR.
HaiyueQuoted 37 lines
-corey
Quoted 33 lines
Signed-off-by Haiyue Wang <[email protected]>---
drivers/char/ipmi/kcs_bmc.c| 10 ++++++----1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-3@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = { struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) { struct kcs_bmc *kcs_bmc; + void *buf; kcs_bmc = devm_kzalloc(dev, sizeof(*kcs_bmc) + sizeof_priv, GFP_KERNEL); if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) mutex_init(&kcs_bmc->mutex); init_waitqueue_head(&kcs_bmc->queue); - kcs_bmc->data_in = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->data_out = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->kbuffer = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf = devm_kmalloc_array(dev, 3, KCS_MSG_BUFSIZ, GFP_KERNEL); + if (!buf) return NULL; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf + KCS_MSG_BUFSIZ; + kcs_bmc->kbuffer = buf + KCS_MSG_BUFSIZ * 2; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; kcs_bmc->miscdev.name = dev_name(dev);
Quoted 10 lines · Haiyue
Hi Corey,
Since IPMI 2.0 just defined minimum, no maximum:
----
KCS/SMIC Input : Required: 40 bytes IPMI Message, minimum
KCS/SMIC Output : Required: 38 bytes IPMI Message, minimum
Yes, though there are practical maximums that are much smaller than 1000 bytes.
Quoted 11 lines
----
We can enlarge the block size for avoiding waste, and make our driver
support most worst message size case. And I think this patch make checking
simple (from 3 to 1), and the code clean, this is the biggest reason I want to
change. The TLB is just memory management study from book, no data to
support access improvement. :)
I would argue that the way it is now expresses the intent of the code better than one allocation split into three parts. Expressing your intent is more important than the number of checks and a minuscule performance improvement. For me it makes the code easier to understand. If you had a tool that checked for out-of-bounds memory access, then a single allocation might not find an overrun between the parts. Smaller allocations tend to result in less memory fragmentation.
My preference is to leave it as it is. However, it's not that important, and if you really want this patch, I can include it.
Thanks,
-corey
Quoted 82 lines
BR,
Haiyue
Quoted 74 lines · Haiyue
Quoted 11 lines · Corey Minyard
Quoted 2 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
I'm finally getting to this.
Is there a reason you want to do this? In general, it's better to not try to outsmart your base system. Depending on the memory allocator, in this case, you might actually use more memory. You probably won't use any less.
I got this idea from another code review, but that patch allocates 30 more the same size memory block, reducing the
devm_kmalloccall will be better. For KCS only have 3, may be the key point is memory waste.Quoted 6 lines
In the original case, you allocate three 1000 byte buffers, resulting in 3 1024 byte slab allocated.
In the changed case, you will allocate a 3000 byte buffer, resulting in a single 4096 byte slab allocation, wasting 1024 more bytes of memory.
As the kcs has memory copy between in/out/kbuffer, put them in the same page will be better ? Such as the same TLB ? (Well, I just got this from book, no real experience of memory accessing performance. And also, I was told that using space to save the time. :-)).
Just my stupid thinking. I'm OK to drop this patch if it doesn't help with performance, or something else.
BR.
HaiyueQuoted 38 lines
-corey
Quoted 34 lines
Signed-off-by Haiyue Wang <[email protected]>---
drivers/char/ipmi/kcs_bmc.c| 10 ++++++----1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-3@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = { struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) { struct kcs_bmc *kcs_bmc; + void *buf; kcs_bmc = devm_kzalloc(dev, sizeof(*kcs_bmc) + sizeof_priv, GFP_KERNEL); if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) mutex_init(&kcs_bmc->mutex); init_waitqueue_head(&kcs_bmc->queue); - kcs_bmc->data_in = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->data_out = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->kbuffer = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf = devm_kmalloc_array(dev, 3, KCS_MSG_BUFSIZ, GFP_KERNEL); + if (!buf) return NULL; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf + KCS_MSG_BUFSIZ; + kcs_bmc->kbuffer = buf + KCS_MSG_BUFSIZ * 2; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR;
kcs_bmc->miscdev.name=dev_name(dev);
Quoted 27 lines · Corey Minyard
Quoted 10 lines · Haiyue
Hi Corey,
Since IPMI 2.0 just defined minimum, no maximum:
----
KCS/SMIC Input : Required: 40 bytes IPMI Message, minimum
KCS/SMIC Output : Required: 38 bytes IPMI Message, minimum
Yes, though there are practical maximums that are much smaller than 1000 bytes.
Quoted 11 lines
----
We can enlarge the block size for avoiding waste, and make our driver
support most worst message size case. And I think this patch make checking
simple (from 3 to 1), and the code clean, this is the biggest reason I want to
change. The TLB is just memory management study from book, no data to
support access improvement. :)
Quoted 8 lines
I would argue that the way it is now expresses the intent of the code better than one allocation split into three parts. Expressing your intent is more important than the number of checks and a minuscule performance improvement. For me it makes the code easier to understand. If you had a tool that checked for out-of-bounds memory access, then a single allocation might not find an overrun between the parts. Smaller allocations tend to result in less memory fragmentation.
When I wrote the commit, I felt that the message was not so professional, and the reason sounded weak. The driver development is a complex work, needs considering more things, not just one. Thanks for your patience.
Quoted 3 lines
My preference is to leave it as it is. However, it's not that important, and if you really want this patch, I can include it.
So leave it as it is, abandon this patch. :-)
BTW, another patch about KCS BMC chip support:
https://lkml.org/lkml/2018/3/22/284
Look forward your reviewing, I've tried my best to make it better.
Quoted 89 lines
Thanks,
-corey
Quoted 84 lines
BR,
Haiyue
Quoted 76 lines · Haiyue
Quoted 11 lines · Corey Minyard
Quoted 2 lines · Haiyue Wang
Allocate a continuous memory block for the three KCS data buffers with related index assignment.
I'm finally getting to this.
Is there a reason you want to do this? In general, it's better to not try to outsmart your base system. Depending on the memory allocator, in this case, you might actually use more memory. You probably won't use any less.
I got this idea from another code review, but that patch allocates 30 more the same size memory block, reducing the
devm_kmalloccall will be better. For KCS only have 3, may be the key point is memory waste.Quoted 6 lines
In the original case, you allocate three 1000 byte buffers, resulting in 3 1024 byte slab allocated.
In the changed case, you will allocate a 3000 byte buffer, resulting in a single 4096 byte slab allocation, wasting 1024 more bytes of memory.
As the kcs has memory copy between in/out/kbuffer, put them in the same page will be better ? Such as the same TLB ? (Well, I just got this from book, no real experience of memory accessing performance. And also, I was told that using space to save the time. :-)).
Just my stupid thinking. I'm OK to drop this patch if it doesn't help with performance, or something else.
BR.
HaiyueQuoted 40 lines
-corey
Quoted 36 lines
Signed-off-by Haiyue Wang <[email protected]>---
drivers/char/ipmi/kcs_bmc.c| 10 ++++++----1 file changed, 6 insertions(+), 4 deletions(-)drivers/char/ipmi/kcs_bmc.c +6
-3@@ -435,6 +435,7 @@ static const struct file_operations kcs_bmc_fops = { struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) { struct kcs_bmc *kcs_bmc; + void *buf; kcs_bmc = devm_kzalloc(dev, sizeof(*kcs_bmc) + sizeof_priv, GFP_KERNEL); if (!kcs_bmc)@@ -448,11 +449,12 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) mutex_init(&kcs_bmc->mutex); init_waitqueue_head(&kcs_bmc->queue); - kcs_bmc->data_in = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->data_out = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->kbuffer = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer) + buf = devm_kmalloc_array(dev, 3, KCS_MSG_BUFSIZ, GFP_KERNEL); + if (!buf) return NULL; + kcs_bmc->data_in = buf; + kcs_bmc->data_out = buf + KCS_MSG_BUFSIZ; + kcs_bmc->kbuffer = buf + KCS_MSG_BUFSIZ * 2;
kcs_bmc->miscdev.minor=MISC_DYNAMIC_MINOR;kcs_bmc->miscdev.name=dev_name(dev);