tracing/dma: Cap dma_map_sg tracepoint arrays to prevent buffer overflow
Subsystems (2)
PATCH v2 1/1 tracing/dma: Cap dma_map_sg tracepoint arrays to prevent buffer overflow
The dma_map_sg tracepoint can trigger a perf buffer overflow when tracing large scatter-gather lists. With devices like virtio-gpu creating large DRM buffers, nents can exceed 1000 entries, resulting in:
phys_addrs: 1000 * 8 bytes = 8,000 bytes
dma_addrs: 1000 * 8 bytes = 8,000 bytes
lengths: 1000 * 4 bytes = 4,000 bytes
Total: ~20,000 bytes
This exceeds PERF_MAX_TRACE_SIZE (8192 bytes), causing:
WARNING: CPU: 0 PID: 5497 at kernel/trace/trace_event_perf.c:405 perf buffer not large enough, wanted 24620, have 8192
Cap all three dynamic arrays at 128 entries using min() in the array size calculation. This ensures arrays are only as large as needed (up to the cap), avoiding unnecessary memory allocation for small operations while preventing overflow for large ones.
The tracepoint now records the full nents/ents counts and a truncated flag so users can see when data has been capped.
Changes in v2:
- Use min(nents, DMA_TRACE_MAX_ENTRIES) for dynamic array sizing instead of fixed DMA_TRACE_MAX_ENTRIES allocation (feedback from Steven Rostedt)
- This allocates only what's needed up to the cap, avoiding waste for small operations
--- include/trace/events/dma.h | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-)
include/trace/events/dma.h +19 -6
@@ -275,6 +275,8 @@ TRACE_EVENT(dma_free_sgt, sizeof(u64), sizeof(u64))) ); +#define DMA_TRACE_MAX_ENTRIES 128 + TRACE_EVENT(dma_map_sg, TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, int ents, enum dma_data_direction dir, unsigned long attrs),
@@ -282,9 +284,12 @@ TRACE_EVENT(dma_map_sg,TP_STRUCT__entry (__string (device ,dev_name (dev )) -__dynamic_array (u64, phys_addrs, nents) -__dynamic_array (u64, dma_addrs, ents) - __dynamic_array(unsigned int, lengths, ents) +__field (int, full_nents) +__field (int, full_ents) +__field (bool, truncated) +__dynamic_array (u64, phys_addrs,min (nents,DMA_TRACE_MAX_ENTRIES )) +__dynamic_array (u64, dma_addrs,min (ents,DMA_TRACE_MAX_ENTRIES )) + __dynamic_array(unsigned int, lengths, min(ents, DMA_TRACE_MAX_ENTRIES)) __field(enum dma_data_direction, dir) __field(unsigned long, attrs) ),
@@ -292,11 +297,16 @@ TRACE_EVENT(dma_map_sg,TP_fast_assign ( struct scatterlist *sg;int i; +int traced_nents =min_t (int, nents,DMA_TRACE_MAX_ENTRIES ); +int traced_ents =min_t (int, ents,DMA_TRACE_MAX_ENTRIES );__assign_str (device); -for_each_sg (sgl, sg, nents, i) + __entry->full_nents = nents; + __entry->full_ents = ents; + __entry->truncated = (nents >DMA_TRACE_MAX_ENTRIES ) || (ents >DMA_TRACE_MAX_ENTRIES ); +for_each_sg (sgl, sg, traced_nents, i) ((u64 *)__get_dynamic_array (phys_addrs))[i] =sg_phys (sg); -for_each_sg (sgl, sg, ents, i) { +for_each_sg (sgl, sg, traced_ents, i) { ((u64 *)__get_dynamic_array (dma_addrs))[i] =sg_dma_address (sg); ((unsigned int *)__get_dynamic_array(lengths))[i] =
@@ -306,9 +316,12 @@ TRACE_EVENT(dma_map_sg, __entry->attrs = attrs; ), - TP_printk("%s dir=%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", + TP_printk("%s dir=%s nents=%d/%d ents=%d/%d%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", __get_str(device), decode_dma_data_direction(__entry->dir), + min_t(int, __entry->full_nents, DMA_TRACE_MAX_ENTRIES), __entry->full_nents, + min_t(int, __entry->full_ents, DMA_TRACE_MAX_ENTRIES), __entry->full_ents, + __entry->truncated ? " [TRUNCATED]" : "", __print_array(__get_dynamic_array(dma_addrs), __get_dynamic_array_len(dma_addrs) / sizeof(u64), sizeof(u64)),
Signature · 1 line
2.43.0
Quoted 90 lines · Deepanshu Kartikey
The
dma_map_sgtracepoint can trigger a perf buffer overflow when tracing large scatter-gather lists. With devices like virtio-gpu creating large DRM buffers, nents can exceed 1000 entries, resulting in:
phys_addrs: 1000 * 8 bytes = 8,000 bytes
dma_addrs: 1000 * 8 bytes = 8,000 bytes
lengths: 1000 * 4 bytes = 4,000 bytes
Total: ~20,000 bytesThis exceeds
PERF_MAX_TRACE_SIZE(8192 bytes), causing:WARNING: CPU: 0 PID: 5497 at kernel/trace/trace_event_perf.c:405 perf buffer not large enough, wanted 24620, have 8192Cap all three dynamic arrays at 128 entries using
min()in the array size calculation. This ensures arrays are only as large as needed (up to the cap), avoiding unnecessary memory allocation for small operations while preventing overflow for large ones.The tracepoint now records the full nents/ents counts and a truncated flag so users can see when data has been capped.
Changes in v2:
- Usemin(nents, DMA_TRACE_MAX_ENTRIES)for dynamic array sizing instead of fixedDMA_TRACE_MAX_ENTRIESallocation (feedback from Steven Rostedt)
- This allocates only what's needed up to the cap, avoiding waste for small operationsReported-by [email protected]Tested-by [email protected]Signed-off-by Deepanshu Kartikey <[email protected]>--- include/trace/events/dma.h | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-)include/trace/events/dma.h +15
-5@@ -275,6 +275,8 @@ TRACE_EVENT(dma_free_sgt, sizeof(u64), sizeof(u64))) ); +#define DMA_TRACE_MAX_ENTRIES 128 + TRACE_EVENT(dma_map_sg, TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, int ents, enum dma_data_direction dir, unsigned long attrs),@@ -282,9 +284,12 @@ TRACE_EVENT(dma_map_sg,TP_STRUCT__entry (__string (device ,dev_name (dev )) -__dynamic_array (u64, phys_addrs, nents) -__dynamic_array (u64, dma_addrs, ents) - __dynamic_array(unsigned int, lengths, ents) +__field (int, full_nents) +__field (int, full_ents) +__field (bool, truncated) +__dynamic_array (u64, phys_addrs,min (nents,DMA_TRACE_MAX_ENTRIES )) +__dynamic_array (u64, dma_addrs,min (ents,DMA_TRACE_MAX_ENTRIES )) + __dynamic_array(unsigned int, lengths, min(ents, DMA_TRACE_MAX_ENTRIES)) __field(enum dma_data_direction, dir) __field(unsigned long, attrs) ),@@ -292,11 +297,16 @@ TRACE_EVENT(dma_map_sg,TP_fast_assign ( struct scatterlist *sg;int i; +int traced_nents =min_t (int, nents,DMA_TRACE_MAX_ENTRIES ); +int traced_ents =min_t (int, ents,DMA_TRACE_MAX_ENTRIES );__assign_str (device); -for_each_sg (sgl, sg, nents, i) + __entry->full_nents = nents; + __entry->full_ents = ents; + __entry->truncated = (nents >DMA_TRACE_MAX_ENTRIES ) || (ents >DMA_TRACE_MAX_ENTRIES ); +for_each_sg (sgl, sg, traced_nents, i) ((u64 *)__get_dynamic_array (phys_addrs))[i] =sg_phys (sg); -for_each_sg (sgl, sg, ents, i) { +for_each_sg (sgl, sg, traced_ents, i) { ((u64 *)__get_dynamic_array (dma_addrs))[i] =sg_dma_address (sg); ((unsigned int *)__get_dynamic_array(lengths))[i] =@@ -306,9 +316,12 @@ TRACE_EVENT(dma_map_sg, __entry->attrs = attrs; ),
include/trace/events/dma.h TRACE_EVENT(dma_map_sg, · line 327
Quoted 10 lines
include/trace/events/dma.h +4
-1- TP_printk("%s dir=%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", + TP_printk("%s dir=%s nents=%d/%d ents=%d/%d%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", __get_str(device), decode_dma_data_direction(__entry->dir), + min_t(int, __entry->full_nents, DMA_TRACE_MAX_ENTRIES), __entry->full_nents, + min_t(int, __entry->full_ents, DMA_TRACE_MAX_ENTRIES), __entry->full_ents, + __entry->truncated ? " [TRUNCATED]" : "", __print_array(__get_dynamic_array(dma_addrs), __get_dynamic_array_len(dma_addrs) / sizeof(u64), sizeof(u64)),
Although it's a bit unusual that there's no limit on dynamic arrays like there is for %*ph.
Steven Rostedt
maintainerQuoted 3 lines · On Fri, 30 Jan 2026 11:27:47 -0500 Sean Anderson <[email protected]>…
Reviwed-by Sean Anderson <[email protected]>Although it's a bit unusual that there's no limit on dynamic arrays like there is for %*ph.
Dynamic arrays are done in fast paths. I rather not add an extra branch to test cases where its most likely not going to exceed the limit.
-- Steve
Quoted 30 lines · Deepanshu Kartikey
The
dma_map_sgtracepoint can trigger a perf buffer overflow when tracing large scatter-gather lists. With devices like virtio-gpu creating large DRM buffers, nents can exceed 1000 entries, resulting in:phys_addrs: 1000 * 8 bytes = 8,000 bytes dma_addrs: 1000 * 8 bytes = 8,000 bytes lengths: 1000 * 4 bytes = 4,000 bytes Total: ~20,000 bytesThis exceeds
PERF_MAX_TRACE_SIZE(8192 bytes), causing:WARNING: CPU: 0 PID: 5497 at kernel/trace/trace_event_perf.c:405 perf buffer not large enough, wanted 24620, have 8192Cap all three dynamic arrays at 128 entries using
min()in the array size calculation. This ensures arrays are only as large as needed (up to the cap), avoiding unnecessary memory allocation for small operations while preventing overflow for large ones.The tracepoint now records the full nents/ents counts and a truncated flag so users can see when data has been capped.
Changes in v2:
- Usemin(nents, DMA_TRACE_MAX_ENTRIES)for dynamic array sizing instead of fixedDMA_TRACE_MAX_ENTRIESallocation (feedback from Steven Rostedt)
- This allocates only what's needed up to the cap, avoiding waste for small operations
Quoted 4 lines
Reported-by [email protected]Tested-by [email protected]Signed-off-by Deepanshu Kartikey <[email protected]>
Applied to dma-mapping-fixes, thanks!
Quoted 56 lines
--- include/trace/events/dma.h | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-)include/trace/events/dma.h +15
-5@@ -275,6 +275,8 @@ TRACE_EVENT(dma_free_sgt, sizeof(u64), sizeof(u64))) ); +#define DMA_TRACE_MAX_ENTRIES 128 + TRACE_EVENT(dma_map_sg, TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, int ents, enum dma_data_direction dir, unsigned long attrs),@@ -282,9 +284,12 @@ TRACE_EVENT(dma_map_sg,TP_STRUCT__entry (__string (device ,dev_name (dev )) -__dynamic_array (u64, phys_addrs, nents) -__dynamic_array (u64, dma_addrs, ents) - __dynamic_array(unsigned int, lengths, ents) +__field (int, full_nents) +__field (int, full_ents) +__field (bool, truncated) +__dynamic_array (u64, phys_addrs,min (nents,DMA_TRACE_MAX_ENTRIES )) +__dynamic_array (u64, dma_addrs,min (ents,DMA_TRACE_MAX_ENTRIES )) + __dynamic_array(unsigned int, lengths, min(ents, DMA_TRACE_MAX_ENTRIES)) __field(enum dma_data_direction, dir) __field(unsigned long, attrs) ),@@ -292,11 +297,16 @@ TRACE_EVENT(dma_map_sg,TP_fast_assign ( struct scatterlist *sg;int i; +int traced_nents =min_t (int, nents,DMA_TRACE_MAX_ENTRIES ); +int traced_ents =min_t (int, ents,DMA_TRACE_MAX_ENTRIES );__assign_str (device); -for_each_sg (sgl, sg, nents, i) + __entry->full_nents = nents; + __entry->full_ents = ents; + __entry->truncated = (nents >DMA_TRACE_MAX_ENTRIES ) || (ents >DMA_TRACE_MAX_ENTRIES ); +for_each_sg (sgl, sg, traced_nents, i) ((u64 *)__get_dynamic_array (phys_addrs))[i] =sg_phys (sg); -for_each_sg (sgl, sg, ents, i) { +for_each_sg (sgl, sg, traced_ents, i) { ((u64 *)__get_dynamic_array (dma_addrs))[i] =sg_dma_address (sg); ((unsigned int *)__get_dynamic_array(lengths))[i] =@@ -306,9 +316,12 @@ TRACE_EVENT(dma_map_sg, __entry->attrs = attrs; ),
include/trace/events/dma.h TRACE_EVENT(dma_map_sg, · line 327
Quoted 10 lines
include/trace/events/dma.h +4
-1- TP_printk("%s dir=%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", + TP_printk("%s dir=%s nents=%d/%d ents=%d/%d%s dma_addrs=%s sizes=%s phys_addrs=%s attrs=%s", __get_str(device), decode_dma_data_direction(__entry->dir), + min_t(int, __entry->full_nents, DMA_TRACE_MAX_ENTRIES), __entry->full_nents, + min_t(int, __entry->full_ents, DMA_TRACE_MAX_ENTRIES), __entry->full_ents, + __entry->truncated ? " [TRUNCATED]" : "", __print_array(__get_dynamic_array(dma_addrs), __get_dynamic_array_len(dma_addrs) / sizeof(u64), sizeof(u64)),
Best regards
Signature · 2 lines
Marek Szyprowski, PhD Samsung R&D Institute Poland