From: Ard Biesheuvel <ardb@xxxxxxxxxx> Currently, kernel mode NEON (SIMD) support is implemented in a way that requires preemption to be disabled while the SIMD registers are live. The reason for this is that those registers are not in the set that is preserved/restored on exception entry/exit and context switch, as this would impact performance generally, even for workloads where kernel mode SIMD is not the bottleneck. However, doing substantial work with preemption disabled is not great, as it affects scheduling latency, which is especially problematic for real-time use cases. So ideally, we should keep preemption enabled when we can, and find another way to ensure that this does not corrupt the NEON register state of in-kernel SIMD users. This series implements a suggestion by Mark Rutland, and introduces a thread_info flag TIF_USING_KMODE_FPSIMD, which indicates to the thread switch machinery that the task in question has live kernel mode SIMD state which needs to be preserved and restored. The space needed for this is allocated in thread_struct. (*) Given that currently, we run kernel mode NEON with softirqs disabled (to avoid the need for preserving kernel mode NEON context belonging to task context while the SIMD unit is being used by code running in softirq context), just removing the preempt_disable/enable calls is not sufficient, and we also need to leave softirqs enabled. This means that we may need to preserve kernel mode NEON state not only on a context switch, but also when code running in softirq context takes ownership of the SIMD unit, but this is straight-forward once we add the scratch space to thread_struct. (On PREEMPT_RT, softirqs execute with preemption enabled, making kernel mode FPSIMD in softirq context preemptible as well. We rely on the fact that the task that hosts the softirq dispatch logic does not itself use kernel mode FPSIMD in task context to ensure that there is only a single kernel mode FPSIMD state that may need to be preserved and restored.) (*) We might decide to allocate this space (~512 bytes) dynamically, if the thread_struct memory footprint causes issues. However, we should also explore doing the same for the user space FPSIMD state, as kernel threads never return to user space and have no need for this allocation. v3: - add patch to drop yield logic from crypto C glue code - add R-b from Mark v2: - tweak some commit logs for clarity - integrate with the existing lazy restore logic - add Mark's R-b to patch #1 Cc: Marc Zyngier <maz@xxxxxxxxxx> Cc: Will Deacon <will@xxxxxxxxxx> Cc: Mark Rutland <mark.rutland@xxxxxxx> Cc: Kees Cook <keescook@xxxxxxxxxxxx> Cc: Catalin Marinas <catalin.marinas@xxxxxxx> Cc: Mark Brown <broonie@xxxxxxxxxx> Cc: Eric Biggers <ebiggers@xxxxxxxxxx> Cc: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx> Ard Biesheuvel (5): arm64: fpsimd: Drop unneeded 'busy' flag arm64: fpsimd: Preserve/restore kernel mode NEON at context switch arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD arm64: crypto: Remove conditional yield logic arm64: crypto: Remove FPSIMD yield logic from glue code arch/arm64/crypto/aes-ce-ccm-glue.c | 5 - arch/arm64/crypto/aes-glue.c | 21 +-- arch/arm64/crypto/aes-modes.S | 2 - arch/arm64/crypto/chacha-neon-glue.c | 14 +- arch/arm64/crypto/crct10dif-ce-glue.c | 30 +--- arch/arm64/crypto/nhpoly1305-neon-glue.c | 12 +- arch/arm64/crypto/poly1305-glue.c | 15 +- arch/arm64/crypto/polyval-ce-glue.c | 5 +- arch/arm64/crypto/sha1-ce-core.S | 6 +- arch/arm64/crypto/sha1-ce-glue.c | 19 +-- arch/arm64/crypto/sha2-ce-core.S | 6 +- arch/arm64/crypto/sha2-ce-glue.c | 19 +-- arch/arm64/crypto/sha3-ce-core.S | 6 +- arch/arm64/crypto/sha3-ce-glue.c | 14 +- arch/arm64/crypto/sha512-ce-core.S | 8 +- arch/arm64/crypto/sha512-ce-glue.c | 16 +- arch/arm64/include/asm/assembler.h | 29 ---- arch/arm64/include/asm/processor.h | 3 + arch/arm64/include/asm/simd.h | 11 +- arch/arm64/include/asm/thread_info.h | 1 + arch/arm64/kernel/asm-offsets.c | 4 - arch/arm64/kernel/fpsimd.c | 163 +++++++++++++------- 22 files changed, 165 insertions(+), 244 deletions(-) -- 2.43.0.rc1.413.gea7ed67945-goog