diff options
| author | Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com> | 2026-09-11 13:42:04 +0200 |
|---|---|---|
| committer | Rob Herring (Arm) <robh@kernel.org> | 2026-09-16 16:18:08 -0500 |
| commit | d5eefb1d97ad476c734997fa6741651dde610ceb (patch) | |
| tree | 95b0d4e34570801912d7cff0a64273d31ba5788d /rust/kernel/alloc | |
| parent | c08fe4da4acc36103152cd310a9eb64a99c161d2 (diff) | |
dtc: dt-check-style: Re-work classifying property continuations
Script has an enumeration of DTS Line types (LineType) and one type is a
continuation of multi-line property. This has limitations, because it
basically hides true type of a continued line which makes certain checks
difficult. For example detecting consecutive blank lines
(LineType.BLANK) will fail if the type is continuation.
clock-names = "foo",
/* Comment */
"bar";
Above code not only fails check_blank_lines() rule, but also messes up
how DtsLine array is constructed - the two middle continued lines are
not put under the DtsLine.continuations array.
The concepts of type of line (blank, preprocessor, property etc) and
actual continuation are orthogonal to most of the checks - the checks
need to know what sort of continued line it is. Fixing this solves
false positives of continued properties with blank lines and comments:
arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi:135: [blank-lines] consecutive blank lines
arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi:135: [blank-lines] blank line at end of node body
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260911-dts-style-checker-blank-lines-v1-1-85e779600d98@oss.qualcomm.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Diffstat (limited to 'rust/kernel/alloc')
0 files changed, 0 insertions, 0 deletions
