From f4cdf7ca9a1fdcca413157df19753f388a5a224e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 19 Aug 2026 10:09:22 -0700 Subject: Merge tag 'media/v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media Pull media updates from Mauro Carvalho Chehab: - v4l2-core: added ISP statistics support and per-block validation - v4l2-core: Allow unknown HDR10 white point and luminance - New camera sensors: Sony IMX678 and IMX471m, Himax HM1092 IR sensor - New codec: Milos: VPU v2.0 codec support - isp driver: gained support for Dreamchip RPPX1 ISP framework - vsp1 driver: gained support for RZ/T2H and RZ/N2H - Novalake driver: gained CVS support for new NVL hardware - dvb-core: fix feed leak on failed DMX_ADD_PID - several driver fixes, cleanups and minor improvements * tag 'media/v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media: (308 commits) media: ipu-bridge: check all DMI entries when overriding sensor rotation media: v4l2-async: avoid deleting unlinked ASC entry on link error media: rzg2l-cru: Align bytesperline to hardware DMA stride requirement media: intel/ipu6: fix async notifier cleanup leak on parse error media: staging/ipu7: fix async notifier UAF on probe error path media: amd: isp4: fix self-deadlock in isp4sd_pwron_and_init() error path media: amd: isp4: release partial allocations in isp4if_alloc_fw_gpumem() media: rcar-isp: Fix VSPX reference leaks media: rcar-isp: Release ISPCORE resources media: i2c: imx415: Release runtime PM reference on VBLANK error media: i2c: imx415: Return test pattern write errors media: renesas: vsp1: Declare index variables in for loop statement media: renesas: vsp1: Make reset control optional to support platforms without a reset line media: dt-bindings: media: renesas,vsp1: Document RZ/T2H and RZ/N2H SoCs media: dt-bindings: media: renesas,fcp: Document RZ/T2H and RZ/N2H SoCs media: nxp: imx8-isi: Add additional 32-bit RGB format support media: nxp: imx8-isi: Add 16-bit raw Bayer format support media: nxp: imx8-isi: Implement per-stream reference counting for multiplexed streams media: nxp: imx8-isi: Use BIT_ULL() for 64-bit stream masks media: nxp: imx8-isi: Correct color map between V4L2 and ISI ... --- arch/arm64/lib/memcmp.S | 139 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 139 insertions(+) create mode 100644 arch/arm64/lib/memcmp.S (limited to 'arch/arm64/lib/memcmp.S') diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S new file mode 100644 index 000000000..a5ccf2c55 --- /dev/null +++ b/arch/arm64/lib/memcmp.S @@ -0,0 +1,139 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2013-2021, Arm Limited. + * + * Adapted from the original at: + * https://github.com/ARM-software/optimized-routines/blob/e823e3abf5f89ecb/string/aarch64/memcmp.S + */ + +#include +#include + +/* Assumptions: + * + * ARMv8-a, AArch64, unaligned accesses. + */ + +#define L(label) .L ## label + +/* Parameters and result. */ +#define src1 x0 +#define src2 x1 +#define limit x2 +#define result w0 + +/* Internal variables. */ +#define data1 x3 +#define data1w w3 +#define data1h x4 +#define data2 x5 +#define data2w w5 +#define data2h x6 +#define tmp1 x7 +#define tmp2 x8 + +SYM_FUNC_START(__pi_memcmp) + subs limit, limit, 8 + b.lo L(less8) + + ldr data1, [src1], 8 + ldr data2, [src2], 8 + cmp data1, data2 + b.ne L(return) + + subs limit, limit, 8 + b.gt L(more16) + + ldr data1, [src1, limit] + ldr data2, [src2, limit] + b L(return) + +L(more16): + ldr data1, [src1], 8 + ldr data2, [src2], 8 + cmp data1, data2 + bne L(return) + + /* Jump directly to comparing the last 16 bytes for 32 byte (or less) + strings. */ + subs limit, limit, 16 + b.ls L(last_bytes) + + /* We overlap loads between 0-32 bytes at either side of SRC1 when we + try to align, so limit it only to strings larger than 128 bytes. */ + cmp limit, 96 + b.ls L(loop16) + + /* Align src1 and adjust src2 with bytes not yet done. */ + and tmp1, src1, 15 + add limit, limit, tmp1 + sub src1, src1, tmp1 + sub src2, src2, tmp1 + + /* Loop performing 16 bytes per iteration using aligned src1. + Limit is pre-decremented by 16 and must be larger than zero. + Exit if <= 16 bytes left to do or if the data is not equal. */ + .p2align 4 +L(loop16): + ldp data1, data1h, [src1], 16 + ldp data2, data2h, [src2], 16 + subs limit, limit, 16 + ccmp data1, data2, 0, hi + ccmp data1h, data2h, 0, eq + b.eq L(loop16) + + cmp data1, data2 + bne L(return) + mov data1, data1h + mov data2, data2h + cmp data1, data2 + bne L(return) + + /* Compare last 1-16 bytes using unaligned access. */ +L(last_bytes): + add src1, src1, limit + add src2, src2, limit + ldp data1, data1h, [src1] + ldp data2, data2h, [src2] + cmp data1, data2 + bne L(return) + mov data1, data1h + mov data2, data2h + cmp data1, data2 + + /* Compare data bytes and set return value to 0, -1 or 1. */ +L(return): +#ifndef __AARCH64EB__ + rev data1, data1 + rev data2, data2 +#endif + cmp data1, data2 +L(ret_eq): + cset result, ne + cneg result, result, lo + ret + + .p2align 4 + /* Compare up to 8 bytes. Limit is [-8..-1]. */ +L(less8): + adds limit, limit, 4 + b.lo L(less4) + ldr data1w, [src1], 4 + ldr data2w, [src2], 4 + cmp data1w, data2w + b.ne L(return) + sub limit, limit, 4 +L(less4): + adds limit, limit, 4 + beq L(ret_eq) +L(byte_loop): + ldrb data1w, [src1], 1 + ldrb data2w, [src2], 1 + subs limit, limit, 1 + ccmp data1w, data2w, 0, ne /* NZCV = 0b0000. */ + b.eq L(byte_loop) + sub result, data1w, data2w + ret +SYM_FUNC_END(__pi_memcmp) +SYM_FUNC_ALIAS_WEAK(memcmp, __pi_memcmp) +EXPORT_SYMBOL_NOKASAN(memcmp) -- cgit v1.3.1