[PATCH] dma/swiotlb: make high watermark tracking boot-time opt-in
From: Frank Chen
Date: Mon Jul 13 2026 - 23:26:17 EST
From: chenhuguanshen <chenhgs@xxxxxxxxxxxxxxx>
Under heavy concurrent DMA traffic on CoCo VMs, inc_used_and_hiwater()
performs an atomic_long_add_return() plus a CAS loop on the global
used_hiwater, and dec_used() performs an atomic_long_sub() on total_used.
All CPUs contend on the same cacheline, causing measurable throughput
degradation at scale.
Historically these counters were only compiled in under CONFIG_DEBUG_FS,
which means production kernels with debugfs paid the atomic overhead
unconditionally once the symbols were present. Make the tracking
boot-time opt-in instead so that it is disabled by default with near-zero
overhead via static_call, and can be enabled via "swiotlb=track_hiwater"
parameter on demand for debugging.
Changes:
- The previous inc_used_and_hiwater() maintained a separate atomic
total_used counter for accurate hiwater updates. This is replaced with
mem_used() which sums across areas. While less precise (no cross-area
locking), the result is adequate for high watermark statistics and
avoids the overhead of maintaining total_used on every alloc/free.
- Refactor high watermark tracking to use static_call, allowing it to be
enabled at boot via the swiotlb=track_hiwater parameter when
CONFIG_DEBUG_FS is set. When disabled (the default), the static_call
resolves to a no-op function, ensuring near-zero overhead.
- Remove the total_used atomic counter from io_tlb_mem since it is no
longer needed. The debugfs "io_tlb_used" file already uses mem_used()
to report current usage.
Suggested-by: Fan Du <fan.du@xxxxxxxxx>
Signed-off-by: Jun Miao <jun.miao@xxxxxxxxx>
Co-developed-by: Fan Du <fan.du@xxxxxxxxx>
Signed-off-by: Fan Du <fan.du@xxxxxxxxx>
Tested-by: chenhuguanshen <chenhgs@xxxxxxxxxxxxxxx>
Signed-off-by: chenhuguanshen <chenhgs@xxxxxxxxxxxxxxx>
---
v1 -> v2:
- Change the patch title.
- Doing the exact hiwater calculation is dynamic and defaults to "off",
dynamic config would replace being under #ifdef CONFIG_DEBUG_FS
- The mechanism used for dynamic config needs to be one that is selectable
on the kernel boot line so that the exact hiwater mark during boot is easily available.
---
.../admin-guide/kernel-parameters.txt | 3 +-
include/linux/swiotlb.h | 10 +-
kernel/dma/swiotlb.c | 125 +++++++++---------
3 files changed, 68 insertions(+), 70 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index b2d7d3540ded..bb60c55383a0 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -7485,7 +7485,7 @@ Kernel parameters
Execution Facility on pSeries.
swiotlb= [ARM,PPC,MIPS,X86,S390,EARLY]
- Format: { <int> [,<int>] | force | noforce }
+ Format: { <int> [,<int>] | force | noforce | track_hiwater }
<int> -- Number of I/O TLB slabs
<int> -- Second integer after comma. Number of swiotlb
areas with their own lock. Will be rounded up
@@ -7493,6 +7493,7 @@ Kernel parameters
force -- force using of bounce buffers even if they
wouldn't be automatically used by the kernel
noforce -- Never use bounce buffers (for debugging)
+ track_hiwater -- Track high watermark of swiotlb buffers
switches= [HW,M68k,EARLY]
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 3dae0f592063..e308792243cc 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -97,11 +97,8 @@ struct io_tlb_pool {
* @lock: Lock to synchronize changes to the list.
* @pools: List of IO TLB memory pool descriptors (if dynamic).
* @dyn_alloc: Dynamic IO TLB pool allocation work.
- * @total_used: The total number of slots in the pool that are currently used
- * across all areas. Used only for calculating used_hiwater in
- * debugfs.
- * @used_hiwater: The high water mark for total_used. Used only for reporting
- * in debugfs.
+ * @used_hiwater: The high watermark of used slots. Can be enabled at
+ * boot time via swiotlb=track_hiwater.
* @transient_nslabs: The total number of slots in all transient pools that
* are currently used across all areas.
*/
@@ -119,9 +116,8 @@ struct io_tlb_mem {
struct work_struct dyn_alloc;
#endif
#ifdef CONFIG_DEBUG_FS
- atomic_long_t total_used;
- atomic_long_t used_hiwater;
atomic_long_t transient_nslabs;
+ atomic_long_t used_hiwater;
#endif
};
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 1abd3e6146f4..5828163c15f7 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -180,8 +180,55 @@ static unsigned int limit_nareas(unsigned int nareas, unsigned long nslots)
return nareas;
}
-static int __init
-setup_io_tlb_npages(char *str)
+#ifdef CONFIG_DEBUG_FS
+static unsigned long mem_used(struct io_tlb_mem *mem);
+
+/*
+ * Track the total used slots to determine the high watermark.
+ * Unlike the previous total_used atomic counter which provided
+ * exact values, mem_used() iterates areas without cross-area
+ * locking and may return imprecise results under concurrent
+ * alloc/free. This is acceptable for high watermark statistics
+ * and avoids the overhead of maintaining a dedicated atomic
+ * counter on every allocation and free.
+ */
+static void account_hiwater_real(struct io_tlb_mem *mem)
+{
+ unsigned long old_hiwater, new_used;
+
+ new_used = mem_used(mem);
+ old_hiwater = atomic_long_read(&mem->used_hiwater);
+ do {
+ if (new_used <= old_hiwater)
+ break;
+ } while (!atomic_long_try_cmpxchg(&mem->used_hiwater,
+ &old_hiwater, new_used));
+}
+
+static void account_hiwater_nop(struct io_tlb_mem *mem)
+{
+}
+
+DEFINE_STATIC_CALL(swiotlb_account_hiwater, account_hiwater_nop);
+
+static __always_inline void account_hiwater(struct io_tlb_mem *mem)
+{
+ static_call(swiotlb_account_hiwater)(mem);
+}
+
+#else
+static __always_inline void account_hiwater(struct io_tlb_mem *mem)
+{
+}
+#endif
+
+/*
+ * The tracking of used slots high watermark can be enabled
+ * by appending "track_hiwater" to the swiotlb= boot parameter.
+ * When disabled the tracking functions are no-ops with near-zero
+ * overhead via static_call.
+ */
+static int __init setup_io_tlb_npages(char *str)
{
if (isdigit(*str)) {
/* avoid tail segment of size < IO_TLB_SEGSIZE */
@@ -194,10 +241,21 @@ setup_io_tlb_npages(char *str)
swiotlb_adjust_nareas(simple_strtoul(str, &str, 0));
if (*str == ',')
++str;
- if (!strcmp(str, "force"))
+ if (!strncmp(str, "force", 5)) {
swiotlb_force_bounce = true;
- else if (!strcmp(str, "noforce"))
+ str += 5;
+ } else if (!strncmp(str, "noforce", 7)) {
swiotlb_force_disable = true;
+ str += 7;
+ }
+#ifdef CONFIG_DEBUG_FS
+ if (*str == ',')
+ ++str;
+ if (!strncmp(str, "track_hiwater", 13)) {
+ static_call_update(swiotlb_account_hiwater,
+ account_hiwater_real);
+ }
+#endif
return 0;
}
@@ -959,40 +1017,6 @@ static unsigned int wrap_area_index(struct io_tlb_pool *mem, unsigned int index)
return index;
}
-/*
- * Track the total used slots with a global atomic value in order to have
- * correct information to determine the high water mark. The mem_used()
- * function gives imprecise results because there's no locking across
- * multiple areas.
- */
-#ifdef CONFIG_DEBUG_FS
-static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
-{
- unsigned long old_hiwater, new_used;
-
- new_used = atomic_long_add_return(nslots, &mem->total_used);
- old_hiwater = atomic_long_read(&mem->used_hiwater);
- do {
- if (new_used <= old_hiwater)
- break;
- } while (!atomic_long_try_cmpxchg(&mem->used_hiwater,
- &old_hiwater, new_used));
-}
-
-static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
-{
- atomic_long_sub(nslots, &mem->total_used);
-}
-
-#else /* !CONFIG_DEBUG_FS */
-static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
-{
-}
-static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
-{
-}
-#endif /* CONFIG_DEBUG_FS */
-
#ifdef CONFIG_SWIOTLB_DYNAMIC
#ifdef CONFIG_DEBUG_FS
static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots)
@@ -1134,7 +1158,7 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool
area->used += nslots;
spin_unlock_irqrestore(&area->lock, flags);
- inc_used_and_hiwater(dev->dma_io_tlb_mem, nslots);
+ account_hiwater(dev->dma_io_tlb_mem);
return slot_index;
}
@@ -1295,24 +1319,6 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
#endif /* CONFIG_SWIOTLB_DYNAMIC */
-#ifdef CONFIG_DEBUG_FS
-
-/**
- * mem_used() - get number of used slots in an allocator
- * @mem: Software IO TLB allocator.
- *
- * The result is accurate in this version of the function, because an atomic
- * counter is available if CONFIG_DEBUG_FS is set.
- *
- * Return: Number of used slots.
- */
-static unsigned long mem_used(struct io_tlb_mem *mem)
-{
- return atomic_long_read(&mem->total_used);
-}
-
-#else /* !CONFIG_DEBUG_FS */
-
/**
* mem_pool_used() - get number of used slots in a memory pool
* @pool: Software IO TLB memory pool.
@@ -1357,8 +1363,6 @@ static unsigned long mem_used(struct io_tlb_mem *mem)
#endif
}
-#endif /* CONFIG_DEBUG_FS */
-
/**
* swiotlb_tbl_map_single() - bounce buffer map a single contiguous physical area
* @dev: Device which maps the buffer.
@@ -1508,8 +1512,6 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr,
mem->slots[i].list = ++count;
area->used -= nslots;
spin_unlock_irqrestore(&area->lock, flags);
-
- dec_used(dev->dma_io_tlb_mem, nslots);
}
#ifdef CONFIG_SWIOTLB_DYNAMIC
@@ -1531,7 +1533,6 @@ static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr,
if (!pool->transient)
return false;
- dec_used(dev->dma_io_tlb_mem, pool->nslabs);
swiotlb_del_pool(dev, pool);
dec_transient_used(dev->dma_io_tlb_mem, pool->nslabs);
return true;
--
2.34.1