diff options
Diffstat (limited to '')
| -rw-r--r-- | debian/patches-rt/0242-crypto-limit-more-FPU-enabled-sections.patch | 74 |
1 files changed, 74 insertions, 0 deletions
diff --git a/debian/patches-rt/0242-crypto-limit-more-FPU-enabled-sections.patch b/debian/patches-rt/0242-crypto-limit-more-FPU-enabled-sections.patch new file mode 100644 index 000000000..9f98cd223 --- /dev/null +++ b/debian/patches-rt/0242-crypto-limit-more-FPU-enabled-sections.patch @@ -0,0 +1,74 @@ +From dd8a48342b4ff4b80a32a4ae49115db93ad069c1 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 30 Nov 2017 13:40:10 +0100 +Subject: [PATCH 242/323] crypto: limit more FPU-enabled sections +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/5.10/older/patches-5.10.204-rt100.tar.xz + +Those crypto drivers use SSE/AVX/… for their crypto work and in order to +do so in kernel they need to enable the "FPU" in kernel mode which +disables preemption. +There are two problems with the way they are used: +- the while loop which processes X bytes may create latency spikes and + should be avoided or limited. +- the cipher-walk-next part may allocate/free memory and may use + kmap_atomic(). + +The whole kernel_fpu_begin()/end() processing isn't probably that cheap. +It most likely makes sense to process as much of those as possible in one +go. The new *_fpu_sched_rt() schedules only if a RT task is pending. + +Probably we should measure the performance those ciphers in pure SW +mode and with this optimisations to see if it makes sense to keep them +for RT. + +This kernel_fpu_resched() makes the code more preemptible which might hurt +performance. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + arch/x86/include/asm/fpu/api.h | 1 + + arch/x86/kernel/fpu/core.c | 12 ++++++++++++ + 2 files changed, 13 insertions(+) + +diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h +index ad2fee785310..d31b0886592a 100644 +--- a/arch/x86/include/asm/fpu/api.h ++++ b/arch/x86/include/asm/fpu/api.h +@@ -28,6 +28,7 @@ extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); + extern void kernel_fpu_end(void); + extern bool irq_fpu_usable(void); + extern void fpregs_mark_activate(void); ++extern void kernel_fpu_resched(void); + + /* Code that is unaware of kernel_fpu_begin_mask() can use this */ + static inline void kernel_fpu_begin(void) +diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c +index 835b948095cd..8cfc2f972fe5 100644 +--- a/arch/x86/kernel/fpu/core.c ++++ b/arch/x86/kernel/fpu/core.c +@@ -144,6 +144,18 @@ void kernel_fpu_end(void) + } + EXPORT_SYMBOL_GPL(kernel_fpu_end); + ++void kernel_fpu_resched(void) ++{ ++ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); ++ ++ if (should_resched(PREEMPT_OFFSET)) { ++ kernel_fpu_end(); ++ cond_resched(); ++ kernel_fpu_begin(); ++ } ++} ++EXPORT_SYMBOL_GPL(kernel_fpu_resched); ++ + /* + * Save the FPU state (mark it for reload if necessary): + * +-- +2.43.0 + |