[PATCH 2/2] ARM: dma-mapping: flush FROM_DEVICE buffers on legacy backends
From: Karl Mehltretter
Date: Thu Sep 10 2026 - 02:48:58 EST
The legacy write-back cache backends invalidate DMA_FROM_DEVICE buffers
when ownership passes to the device. A plain invalidate can discard dirty
CPU cache lines. If the device writes only part of the buffer, untouched
bytes can expose memory contents older than those present at the handoff.
This was reproduced on the ARM926EJ-S (ARMv5TEJ) in a SAM9X75. A
mapping-only test lost 339,936 to 351,744 of 409,600 CPU-written bytes per
100-iteration run. In a separate usbfs test, a webcam returned short
isochronous packets into a buffer that usbfs had cleared. Across five
boots, the existing kernel exposed 29,403 non-zero bytes among 245,708
unwritten gap bytes to userspace.
With this change, five fresh 100-iteration runs on the same SAM9X75 board
each lost 0 of 409,600 bytes.
Use the existing clean-and-invalidate operation for DMA_FROM_DEVICE at
device handoff. The cache lines remain invalid after the handoff, but dirty
CPU data reaches memory first. Keep the existing no-op ownership-return
hooks. These backends already use the same operation for
DMA_BIDIRECTIONAL.
The XScale 80200 A0/A1 path already uses clean-and-invalidate for this case
and remains unchanged.
Cc: stable@xxxxxxxxxxxxxxx
Assisted-by: LLM
Signed-off-by: Karl Mehltretter <kmehltretter@xxxxxxxxx>
---
arch/arm/mm/cache-fa.S | 1 -
arch/arm/mm/cache-v4wb.S | 1 -
arch/arm/mm/proc-arm1020.S | 1 -
arch/arm/mm/proc-arm1020e.S | 1 -
arch/arm/mm/proc-arm1022.S | 1 -
arch/arm/mm/proc-arm1026.S | 1 -
arch/arm/mm/proc-arm920.S | 1 -
arch/arm/mm/proc-arm922.S | 1 -
arch/arm/mm/proc-arm925.S | 1 -
arch/arm/mm/proc-arm926.S | 1 -
arch/arm/mm/proc-arm940.S | 1 -
arch/arm/mm/proc-arm946.S | 1 -
arch/arm/mm/proc-feroceon.S | 2 --
arch/arm/mm/proc-mohawk.S | 1 -
arch/arm/mm/proc-xsc3.S | 1 -
arch/arm/mm/proc-xscale.S | 1 -
16 files changed, 17 deletions(-)
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index e1641799569b..1ff3d66fe944 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -232,7 +232,6 @@ SYM_TYPED_FUNC_START(fa_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq fa_dma_clean_range
- bcs fa_dma_inv_range
b fa_dma_flush_range
SYM_FUNC_END(fa_dma_map_area)
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index 874fe5310f9a..87036c8bb318 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -244,7 +244,6 @@ SYM_TYPED_FUNC_START(v4wb_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq v4wb_dma_clean_range
- bcs v4wb_dma_inv_range
b v4wb_dma_flush_range
SYM_FUNC_END(v4wb_dma_map_area)
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 4612a4961e81..c79f3c3e47a0 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -350,7 +350,6 @@ SYM_TYPED_FUNC_START(arm1020_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm1020_dma_clean_range
- bcs arm1020_dma_inv_range
b arm1020_dma_flush_range
SYM_FUNC_END(arm1020_dma_map_area)
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index b4a8a3a8eda3..a117e26e4763 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -337,7 +337,6 @@ SYM_TYPED_FUNC_START(arm1020e_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm1020e_dma_clean_range
- bcs arm1020e_dma_inv_range
b arm1020e_dma_flush_range
SYM_FUNC_END(arm1020e_dma_map_area)
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 709870e99e19..63b4992f8ad2 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -336,7 +336,6 @@ SYM_TYPED_FUNC_START(arm1022_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm1022_dma_clean_range
- bcs arm1022_dma_inv_range
b arm1022_dma_flush_range
SYM_FUNC_END(arm1022_dma_map_area)
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index 02f7370a8c5c..c5e50395473b 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -331,7 +331,6 @@ SYM_TYPED_FUNC_START(arm1026_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm1026_dma_clean_range
- bcs arm1026_dma_inv_range
b arm1026_dma_flush_range
SYM_FUNC_END(arm1026_dma_map_area)
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 0326067c6c75..e30b013432f0 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -299,7 +299,6 @@ SYM_TYPED_FUNC_START(arm920_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm920_dma_clean_range
- bcs arm920_dma_inv_range
b arm920_dma_flush_range
SYM_FUNC_END(arm920_dma_map_area)
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 3fe6fdf0d325..b1ace8c664e2 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -301,7 +301,6 @@ SYM_TYPED_FUNC_START(arm922_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm922_dma_clean_range
- bcs arm922_dma_inv_range
b arm922_dma_flush_range
SYM_FUNC_END(arm922_dma_map_area)
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index 2d15467e4a08..3d91d16e4af0 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -357,7 +357,6 @@ SYM_TYPED_FUNC_START(arm925_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm925_dma_clean_range
- bcs arm925_dma_inv_range
b arm925_dma_flush_range
SYM_FUNC_END(arm925_dma_map_area)
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index d94aa8199452..bd335d703590 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -320,7 +320,6 @@ SYM_TYPED_FUNC_START(arm926_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm926_dma_clean_range
- bcs arm926_dma_inv_range
b arm926_dma_flush_range
SYM_FUNC_END(arm926_dma_map_area)
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index 545c076c36d2..ba7158639ab7 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -264,7 +264,6 @@ SYM_TYPED_FUNC_START(arm940_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm940_dma_clean_range
- bcs arm940_dma_inv_range
b arm940_dma_flush_range
SYM_FUNC_END(arm940_dma_map_area)
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index f3d4e18c3fba..a135c654b854 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -306,7 +306,6 @@ SYM_TYPED_FUNC_START(arm946_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm946_dma_clean_range
- bcs arm946_dma_inv_range
b arm946_dma_flush_range
SYM_FUNC_END(arm946_dma_map_area)
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 7f08d06c9625..dbaf01ba7cb5 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -391,7 +391,6 @@ SYM_TYPED_FUNC_START(feroceon_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq feroceon_dma_clean_range
- bcs feroceon_dma_inv_range
b feroceon_dma_flush_range
SYM_FUNC_END(feroceon_dma_map_area)
@@ -405,7 +404,6 @@ SYM_TYPED_FUNC_START(feroceon_range_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq feroceon_range_dma_clean_range
- bcs feroceon_range_dma_inv_range
b feroceon_range_dma_flush_range
SYM_FUNC_END(feroceon_range_dma_map_area)
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 4669c63e3121..7df85a32f7b5 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -287,7 +287,6 @@ SYM_TYPED_FUNC_START(mohawk_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq mohawk_dma_clean_range
- bcs mohawk_dma_inv_range
b mohawk_dma_flush_range
SYM_FUNC_END(mohawk_dma_map_area)
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index fd25634a2ed5..6c5910bcc211 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -332,7 +332,6 @@ SYM_TYPED_FUNC_START(xsc3_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq xsc3_dma_clean_range
- bcs xsc3_dma_inv_range
b xsc3_dma_flush_range
SYM_FUNC_END(xsc3_dma_map_area)
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index d8462df8020b..86422559d91e 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -390,7 +390,6 @@ SYM_TYPED_FUNC_START(xscale_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq xscale_dma_clean_range
- bcs xscale_dma_inv_range
b xscale_dma_flush_range
SYM_FUNC_END(xscale_dma_map_area)
--
2.53.0