From 9cc63f8bcd560c760d0b12e15bba8f81c86237cf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 14 Aug 2026 15:43:51 -0700 Subject: Merge branches 'expcb.2026.07.24a', 'misc.2026.07.30a', 'rcu-tasks.2026.07.30a', 'srcu.2026.08.11a' and 'torture.2026.08.14a' into HEAD Changes: Make expedited grace periods expedite normal RCU callbacks Miscellaneous fixes: * Improve diagnostic output with character task states. * Mark accesses to inform KCSAN of concurrency design. * Move from kmalloc() to kmalloc_obj(). * Documentation updates. * Improve handling of RCU deferred quiescent states. * Clean up unused function arguments and structure fields. * Reduce show_rcu_gp_kthreads() stack space. Tasks RCU updates: * Clean up after SRCU re-implementation of Tasks Trace RCU. * Mark accesses to inform KCSAN of concurrency design. * Add ->lazy_timer status to diagnostic output. * Remove an unnecessary memory barrier. * Fix a data race, courtesy of KCSAN. * Documentation updates. * Convert cond_resched_tasks_rcu_qs() from macro to static inline function. SRCU updates: * Add Rust helpers for SRCU. * Avoid losing queued work at cleanup_srcu_struct() time. Torture-test updates: * Preparation work for immediate RCU priority deboosting. * Test RCU readers from real interrupt handlers (as opposed to softirq). * Simplify code through use of cpumask_next_wrap(). * Improve diagnostic output with character task states. * Add rcutorture.nwriters parameter to allow lightweight stall testing, and rcutorture.stall_only to make doing so easier. * Test an RCU Tasks Trace grace period implying an RCU grace period. * Make RCU Tasks Trace torturing track reader batches. * Fix a data race, courtesy of KCSAN. * Plug a shuffle_tmp_mask memory leak on kthread spawn failure. --- arch/arc/lib/memcmp.S | 149 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 149 insertions(+) create mode 100644 arch/arc/lib/memcmp.S (limited to 'arch/arc/lib/memcmp.S') diff --git a/arch/arc/lib/memcmp.S b/arch/arc/lib/memcmp.S new file mode 100644 index 000000000..d6dc5e9bc --- /dev/null +++ b/arch/arc/lib/memcmp.S @@ -0,0 +1,149 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + */ + +#include + +#ifdef __LITTLE_ENDIAN__ +#define WORD2 r2 +#define SHIFT r3 +#else /* BIG ENDIAN */ +#define WORD2 r3 +#define SHIFT r2 +#endif + +ENTRY_CFI(memcmp) + or r12,r0,r1 + asl_s r12,r12,30 + sub r3,r2,1 + brls r2,r12,.Lbytewise + ld r4,[r0,0] + ld r5,[r1,0] + lsr.f lp_count,r3,3 +#ifdef CONFIG_ISA_ARCV2 + /* In ARCv2 a branch can't be the last instruction in a zero overhead + * loop. + * So we move the branch to the start of the loop, duplicate it + * after the end, and set up r12 so that the branch isn't taken + * initially. + */ + mov_s r12,WORD2 + lpne .Loop_end + brne WORD2,r12,.Lodd + ld WORD2,[r0,4] +#else + lpne .Loop_end + ld_s WORD2,[r0,4] +#endif + ld_s r12,[r1,4] + brne r4,r5,.Leven + ld.a r4,[r0,8] + ld.a r5,[r1,8] +#ifdef CONFIG_ISA_ARCV2 +.Loop_end: + brne WORD2,r12,.Lodd +#else + brne WORD2,r12,.Lodd +.Loop_end: +#endif + asl_s SHIFT,SHIFT,3 + bhs_s .Last_cmp + brne r4,r5,.Leven + ld r4,[r0,4] + ld r5,[r1,4] +#ifdef __LITTLE_ENDIAN__ + nop_s + ; one more load latency cycle +.Last_cmp: + xor r0,r4,r5 + bset r0,r0,SHIFT + sub_s r1,r0,1 + bic_s r1,r1,r0 + norm r1,r1 + b.d .Leven_cmp + and r1,r1,24 +.Leven: + xor r0,r4,r5 + sub_s r1,r0,1 + bic_s r1,r1,r0 + norm r1,r1 + ; slow track insn + and r1,r1,24 +.Leven_cmp: + asl r2,r4,r1 + asl r12,r5,r1 + lsr_s r2,r2,1 + lsr_s r12,r12,1 + j_s.d [blink] + sub r0,r2,r12 + .balign 4 +.Lodd: + xor r0,WORD2,r12 + sub_s r1,r0,1 + bic_s r1,r1,r0 + norm r1,r1 + ; slow track insn + and r1,r1,24 + asl_s r2,r2,r1 + asl_s r12,r12,r1 + lsr_s r2,r2,1 + lsr_s r12,r12,1 + j_s.d [blink] + sub r0,r2,r12 +#else /* BIG ENDIAN */ +.Last_cmp: + neg_s SHIFT,SHIFT + lsr r4,r4,SHIFT + lsr r5,r5,SHIFT + ; slow track insn +.Leven: + sub.f r0,r4,r5 + mov.ne r0,1 + j_s.d [blink] + bset.cs r0,r0,31 +.Lodd: + cmp_s WORD2,r12 + mov_s r0,1 + j_s.d [blink] + bset.cs r0,r0,31 +#endif /* ENDIAN */ + .balign 4 +.Lbytewise: + breq r2,0,.Lnil + ldb r4,[r0,0] + ldb r5,[r1,0] + lsr.f lp_count,r3 +#ifdef CONFIG_ISA_ARCV2 + mov r12,r3 + lpne .Lbyte_end + brne r3,r12,.Lbyte_odd +#else + lpne .Lbyte_end +#endif + ldb_s r3,[r0,1] + ldb r12,[r1,1] + brne r4,r5,.Lbyte_even + ldb.a r4,[r0,2] + ldb.a r5,[r1,2] +#ifdef CONFIG_ISA_ARCV2 +.Lbyte_end: + brne r3,r12,.Lbyte_odd +#else + brne r3,r12,.Lbyte_odd +.Lbyte_end: +#endif + bcc .Lbyte_even + brne r4,r5,.Lbyte_even + ldb_s r3,[r0,1] + ldb_s r12,[r1,1] +.Lbyte_odd: + j_s.d [blink] + sub r0,r3,r12 +.Lbyte_even: + j_s.d [blink] + sub r0,r4,r5 +.Lnil: + j_s.d [blink] + mov r0,0 +END_CFI(memcmp) -- cgit v1.3.1