summaryrefslogtreecommitdiffstats
path: root/arch/arc/lib/memset-archs.S
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2026-08-24 08:46:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2026-08-24 08:46:03 -0700
commitcf9610f9116d55c5a66ef9f1faecacabd93a9322 (patch)
tree757a3d280760c654767631cab5ad8af2d86d1848 /arch/arc/lib/memset-archs.S
downloadlinux-stable-cf9610f9116d55c5a66ef9f1faecacabd93a9322.tar.gz
linux-stable-cf9610f9116d55c5a66ef9f1faecacabd93a9322.zip
Merge tag 'pinctrl-v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrlgrafted
Pull pin control updates from Linus Walleij: "Core changes: - Use the non-blocking mux_state_try_select() in the generic MUX pin control back-end - Free pin maps on pinctrl_generic_to_map() failure in the core helpers New hardware pin control: - Qualcomm Maili TLMM SoC, PMG1110 PMIC, and Eliza LPASS LPI TLMM SoC (this is for the low power audio, LPASS = Low Power Audio SubSystem portions) - Upboard support on top of the Intel pin controller - Apple T6030 and T6031 support (just compatible strings) - Samsung Exynos 8855 SoC - Mediatek MT6858 SoC - Rockchip RK3308B and RV1106 SoCs - Airoha EN7523 and AN7563 SoCs Improvements: - Qualcomm TLMM GPIOs are unconditionally marked as wakeup capable - Qualcomm improvements on top of the Qualcomm PDC (power domain controller) irqchip improvements from tglx:s tree - Qualcomm IPQ806x and IPQ9650 non-urgent pin grop fixups - The NPCM8xx driver has been put into shape fixing many pin and group definitions - Some non-urgent Tegra 264 pin assignments are fixed up - Some non-urgent fixups to Airoha AN7581 and AN7583 registers and pin assignments, missing features etc" * tag 'pinctrl-v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl: (130 commits) dt-bindings: pinctrl: Convert TI DA850 pupd to DT schema pinctrl: meson: sync some modify from A4 pinctrl: meson: a4: Add input enable pin configuration pinctrl: realtek: rtd1625: remove unused group name spdif_sel pinctrl: realtek: rtd1625: fix base_bit for VE4 GPIO 13 dt-bindings: pinctrl: microchip,pic32mzda-pinctrl: Convert to DT schema Revert "Merge branch 'ib-rsk7204' into devel" pinctrl: rockchip: Add RV1106 pinctrl support dt-bindings: pinctrl: rockchip: Add RV1106 compatible pinctrl: rockchip: Decode drive strength in the get function pinctrl: fix PINCTRL_GENERIC_MUX not always being selectable pinctrl: airoha: add support of an7563 SoC dt-bindings: pinctrl: airoha: add support of an7563 pin controller pinctrl: airoha: try to find chip scu node by phandle first pinctrl: airoha: add support of en7523 SoC dt-bindings: pinctrl: airoha: add support of en7523 pin controller pinctrl: airoha: an7583: add support for olt pinmux pinctrl: airoha: an7583: add support for pon_alt pinmux pinctrl: airoha: an7583: add support for npu_uart pinmux dt-bindings: pinctrl: airoha: an7583: add missed features ...
Diffstat (limited to 'arch/arc/lib/memset-archs.S')
-rw-r--r--arch/arc/lib/memset-archs.S144
1 files changed, 144 insertions, 0 deletions
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
new file mode 100644
index 000000000..d0a5cec4c
--- /dev/null
+++ b/arch/arc/lib/memset-archs.S
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/linkage.h>
+#include <asm/cache.h>
+
+/*
+ * The memset implementation below is optimized to use prefetchw and prealloc
+ * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6)
+ * If you want to implement optimized memset for other possible L1 data cache
+ * line lengths (32B and 128B) you should rewrite code carefully checking
+ * we don't call any prefetchw/prealloc instruction for L1 cache lines which
+ * don't belongs to memset area.
+ */
+
+#if L1_CACHE_SHIFT == 6
+
+.macro PREALLOC_INSTR reg, off
+ prealloc [\reg, \off]
+.endm
+
+.macro PREFETCHW_INSTR reg, off
+ prefetchw [\reg, \off]
+.endm
+
+#else
+
+.macro PREALLOC_INSTR reg, off
+.endm
+
+.macro PREFETCHW_INSTR reg, off
+.endm
+
+#endif
+
+ENTRY_CFI(memset)
+ mov.f 0, r2
+;;; if size is zero
+ jz.d [blink]
+ mov r3, r0 ; don't clobber ret val
+
+ PREFETCHW_INSTR r0, 0 ; Prefetch the first write location
+
+;;; if length < 8
+ brls.d.nt r2, 8, .Lsmallchunk
+ mov.f lp_count,r2
+
+ and.f r4, r0, 0x03
+ rsub lp_count, r4, 4
+ lpnz @.Laligndestination
+ ;; LOOP BEGIN
+ stb.ab r1, [r3,1]
+ sub r2, r2, 1
+.Laligndestination:
+
+;;; Destination is aligned
+ and r1, r1, 0xFF
+ asl r4, r1, 8
+ or r4, r4, r1
+ asl r5, r4, 16
+ or r5, r5, r4
+ mov r4, r5
+
+ sub3 lp_count, r2, 8
+ cmp r2, 64
+ bmsk.hi r2, r2, 5
+ mov.ls lp_count, 0
+ add3.hi r2, r2, 8
+
+;;; Convert len to Dwords, unfold x8
+ lsr.f lp_count, lp_count, 6
+
+ lpnz @.Lset64bytes
+ ;; LOOP START
+ PREALLOC_INSTR r3, 64 ; alloc next line w/o fetching
+
+#ifdef CONFIG_ARC_HAS_LL64
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+#else
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+#endif
+.Lset64bytes:
+
+ lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes
+ lpnz .Lset32bytes
+ ;; LOOP START
+#ifdef CONFIG_ARC_HAS_LL64
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+ std.ab r4, [r3, 8]
+#else
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+ st.ab r4, [r3, 4]
+#endif
+.Lset32bytes:
+
+ and.f lp_count, r2, 0x1F ;Last remaining 31 bytes
+.Lsmallchunk:
+ lpnz .Lcopy3bytes
+ ;; LOOP START
+ stb.ab r1, [r3, 1]
+.Lcopy3bytes:
+
+ j [blink]
+
+END_CFI(memset)
+
+ENTRY_CFI(memzero)
+ ; adjust bzero args to memset args
+ mov r2, r1
+ b.d memset ;tail call so need to tinker with blink
+ mov r1, 0
+END_CFI(memzero)