dma/mapping.c: dev_dbg support for dma_addressing_limited
PATCH 1/1 dma/mapping.c: dev_dbg support for dma_addressing_limited
In the debug and resolution of an issue involving forced use of bounce buffers, 7170130e4c72 ("x86/mm/init: Handle the special case of device private pages in add_pages(), to not increase max_pfn and trigger dma_addressing_limited() bounce buffers"). It would have been easier to debug the issue if dma_addressing_limited() had debug information about the device not being able to address all of memory and thus forcing all accesses through a bounce buffer. Please see[2]
Implement dev_dbg to debug the potential use of bounce buffers when we hit the condition. When swiotlb is used, dma_addressing_limited() is used to determine the size of maximum dma buffer size in dma_direct_max_mapping_size(). The debug prints could be triggered in that check as well (when enabled).
---
Changelog v2:
- Convert WARN_ONCE to dev_dbg
Testing:
- Limited testing on a VM, could not trigger the debug message on the machine
kernel/dma/mapping.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)
kernel/dma/mapping.c +10 -1
@@ -918,7 +918,7 @@ EXPORT_SYMBOL(dma_set_coherent_mask);* the system, else %false. Lack of addressing bits is the prime reason for * bounce buffering, but might not be the only one. */ -bool dma_addressing_limited (struct device *dev) +static bool __dma_addressing_limited (struct device *dev) {const struct dma_map_ops *ops =get_dma_ops (dev);
@@ -930,6 +930,15 @@ bool dma_addressing_limited(struct device *dev)return false;return !dma_direct_all_ram_mapped (dev); } + +bool dma_addressing_limited (struct device *dev) +{ +if (!__dma_addressing_limited (dev)) +return false; + +dev_dbg (dev,"might have lower perf due to bounce buffering\n" ); +return true; +}EXPORT_SYMBOL_GPL (dma_addressing_limited);size_t dma_max_mapping_size (struct device *dev)
Signature · 1 line
2.49.0
kernel/dma/mapping.c bool dma_addressing_limited(struct device *dev) · line 939
Quoted 1 line · Balbir Singh
kernel/dma/mapping.c +1
-0+dev_dbg (dev,"might have lower perf due to bounce buffering\n" );
I don't think that's a good message. Report the actual observation, i.e. "device is DMA addressing limited" and not a guessed conclusion.
Quoted 6 lines · Christoph Hellwig
kernel/dma/mapping.c bool dma_addressing_limited(struct device *dev) · line 939
Quoted 1 line · Balbir Singh
kernel/dma/mapping.c +1
-0+dev_dbg (dev,"might have lower perf due to bounce buffering\n" );I don't think that's a good message. Report the actual observation, i.e. "device is DMA addressing limited" and not a guessed conclusion.
The bounce buffering remark came from the rest of the mention in code and I agree the perf is based on my experience and may not be true in all cases.
I'll respin
Balbir