From 9b19700e623f96222c69ecb2adecb1a3e3664cc0 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 8 Dec 2023 12:32:20 +0100 Subject: arm64: fpsimd: Drop unneeded 'busy' flag Kernel mode NEON will preserve the user mode FPSIMD state by saving it into the task struct before clobbering the registers. In order to avoid the need for preserving kernel mode state too, we disallow nested use of kernel mode NEON, i..e, use in softirq context while the interrupted task context was using kernel mode NEON too. Originally, this policy was implemented using a per-CPU flag which was exposed via may_use_simd(), requiring the users of the kernel mode NEON to deal with the possibility that it might return false, and having NEON and non-NEON code paths. This policy was changed by commit 13150149aa6ded1 ("arm64: fpsimd: run kernel mode NEON with softirqs disabled"), and now, softirq processing is disabled entirely instead, and so may_use_simd() can never fail when called from task or softirq context. This means we can drop the fpsimd_context_busy flag entirely, and instead, ensure that we disable softirq processing in places where we formerly relied on the flag for preventing races in the FPSIMD preserve routines. Signed-off-by: Ard Biesheuvel Reviewed-by: Mark Brown Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20231208113218.3001940-7-ardb@google.com [will: Folded in fix from CAMj1kXFhzbJRyWHELCivQW1yJaF=p07LLtbuyXYX3G1WtsdyQg@mail.gmail.com] Signed-off-by: Will Deacon --- arch/arm64/include/asm/simd.h | 11 +-------- arch/arm64/kernel/fpsimd.c | 55 +++++++++++-------------------------------- 2 files changed, 15 insertions(+), 51 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index 6a75d7ecdcaa..8e86c9e70e48 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -12,8 +12,6 @@ #include #include -DECLARE_PER_CPU(bool, fpsimd_context_busy); - #ifdef CONFIG_KERNEL_MODE_NEON /* @@ -28,17 +26,10 @@ static __must_check inline bool may_use_simd(void) /* * We must make sure that the SVE has been initialized properly * before using the SIMD in kernel. - * fpsimd_context_busy is only set while preemption is disabled, - * and is clear whenever preemption is enabled. Since - * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy - * cannot change under our feet -- if it's set we cannot be - * migrated, and if it's clear we cannot be migrated to a CPU - * where it is set. */ return !WARN_ON(!system_capabilities_finalized()) && system_supports_fpsimd() && - !in_hardirq() && !irqs_disabled() && !in_nmi() && - !this_cpu_read(fpsimd_context_busy); + !in_hardirq() && !irqs_disabled() && !in_nmi(); } #else /* ! CONFIG_KERNEL_MODE_NEON */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 1559c706d32d..37ee261b117d 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -85,13 +85,13 @@ * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and * flag the register state as invalid. * - * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may - * save the task's FPSIMD context back to task_struct from softirq context. - * To prevent this from racing with the manipulation of the task's FPSIMD state - * from task context and thereby corrupting the state, it is necessary to - * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE - * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to - * run but prevent them to use FPSIMD. + * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be + * called from softirq context, which will save the task's FPSIMD context back + * to task_struct. To prevent this from racing with the manipulation of the + * task's FPSIMD state from task context and thereby corrupting the state, it + * is necessary to protect any manipulation of a task's fpsimd_state or + * TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend + * softirq servicing entirely until put_cpu_fpsimd_context() is called. * * For a certain task, the sequence may look something like this: * - the task gets scheduled in; if both the task's fpsimd_cpu field @@ -209,27 +209,14 @@ static inline void sme_free(struct task_struct *t) { } #endif -DEFINE_PER_CPU(bool, fpsimd_context_busy); -EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); - static void fpsimd_bind_task_to_cpu(void); -static void __get_cpu_fpsimd_context(void) -{ - bool busy = __this_cpu_xchg(fpsimd_context_busy, true); - - WARN_ON(busy); -} - /* * Claim ownership of the CPU FPSIMD context for use by the calling context. * * The caller may freely manipulate the FPSIMD context metadata until * put_cpu_fpsimd_context() is called. * - * The double-underscore version must only be called if you know the task - * can't be preempted. - * * On RT kernels local_bh_disable() is not sufficient because it only * serializes soft interrupt related sections via a local lock, but stays * preemptible. Disabling preemption is the right choice here as bottom @@ -242,14 +229,6 @@ static void get_cpu_fpsimd_context(void) local_bh_disable(); else preempt_disable(); - __get_cpu_fpsimd_context(); -} - -static void __put_cpu_fpsimd_context(void) -{ - bool busy = __this_cpu_xchg(fpsimd_context_busy, false); - - WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */ } /* @@ -261,18 +240,12 @@ static void __put_cpu_fpsimd_context(void) */ static void put_cpu_fpsimd_context(void) { - __put_cpu_fpsimd_context(); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_enable(); else preempt_enable(); } -static bool have_cpu_fpsimd_context(void) -{ - return !preemptible() && __this_cpu_read(fpsimd_context_busy); -} - unsigned int task_get_vl(const struct task_struct *task, enum vec_type type) { return task->thread.vl[type]; @@ -383,7 +356,7 @@ static void task_fpsimd_load(void) bool restore_ffr; WARN_ON(!system_supports_fpsimd()); - WARN_ON(!have_cpu_fpsimd_context()); + WARN_ON(preemptible()); if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { @@ -467,7 +440,7 @@ static void fpsimd_save(void) unsigned int vl; WARN_ON(!system_supports_fpsimd()); - WARN_ON(!have_cpu_fpsimd_context()); + WARN_ON(preemptible()); if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; @@ -1507,7 +1480,7 @@ void fpsimd_thread_switch(struct task_struct *next) if (!system_supports_fpsimd()) return; - __get_cpu_fpsimd_context(); + WARN_ON_ONCE(!irqs_disabled()); /* Save unsaved fpsimd state, if any: */ fpsimd_save(); @@ -1523,8 +1496,6 @@ void fpsimd_thread_switch(struct task_struct *next) update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, wrong_task || wrong_cpu); - - __put_cpu_fpsimd_context(); } static void fpsimd_flush_thread_vl(enum vec_type type) @@ -1826,13 +1797,15 @@ static void fpsimd_flush_cpu_state(void) */ void fpsimd_save_and_flush_cpu_state(void) { + unsigned long flags; + if (!system_supports_fpsimd()) return; WARN_ON(preemptible()); - __get_cpu_fpsimd_context(); + local_irq_save(flags); fpsimd_save(); fpsimd_flush_cpu_state(); - __put_cpu_fpsimd_context(); + local_irq_restore(flags); } #ifdef CONFIG_KERNEL_MODE_NEON -- cgit v1.2.3-58-ga151 From aefbab8e77eb16b56e18f24b85a09ebf4dc60e93 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 8 Dec 2023 12:32:21 +0100 Subject: arm64: fpsimd: Preserve/restore kernel mode NEON at context switch Currently, the FPSIMD register file is not preserved and restored along with the general registers on exception entry/exit or context switch. For this reason, we disable preemption when enabling FPSIMD for kernel mode use in task context, and suspend the processing of softirqs so that there are no concurrent uses in the kernel. (Kernel mode FPSIMD may not be used at all in other contexts). Disabling preemption while doing CPU intensive work on inputs of potentially unbounded size is bad for real-time performance, which is why we try and ensure that SIMD crypto code does not operate on more than ~4k at a time, which is an arbitrary limit and requires assembler code to implement efficiently. We can avoid the need for disabling preemption if we can ensure that any in-kernel users of the NEON will not lose the FPSIMD register state across a context switch. And given that disabling softirqs implicitly disables preemption as well, we will also have to ensure that a softirq that runs code using FPSIMD can safely interrupt an in-kernel user. So introduce a thread_info flag TIF_KERNEL_FPSTATE, and modify the context switch hook for FPSIMD to preserve and restore the kernel mode FPSIMD to/from struct thread_struct when it is set. This avoids any scheduling blackouts due to prolonged use of FPSIMD in kernel mode, without the need for manual yielding. In order to support softirq processing while FPSIMD is being used in kernel task context, use the same flag to decide whether the kernel mode FPSIMD state needs to be preserved and restored before allowing FPSIMD to be used in softirq context. Signed-off-by: Ard Biesheuvel Reviewed-by: Mark Brown Reviewed-by: Mark Rutland Link: https://lore.kernel.org/r/20231208113218.3001940-8-ardb@google.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/processor.h | 2 + arch/arm64/include/asm/thread_info.h | 1 + arch/arm64/kernel/fpsimd.c | 92 +++++++++++++++++++++++++++++------- 3 files changed, 77 insertions(+), 18 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index e5bc54522e71..ce6eebd6c08b 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -167,6 +167,8 @@ struct thread_struct { unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ + + struct user_fpsimd_state kernel_fpsimd_state; #ifdef CONFIG_ARM64_PTR_AUTH struct ptrauth_keys_user keys_user; #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 553d1bc559c6..e72a3bf9e563 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -80,6 +80,7 @@ void arch_setup_new_exec(void); #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ #define TIF_SME 27 /* SME in use */ #define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */ +#define TIF_KERNEL_FPSTATE 29 /* Task is in a kernel mode FPSIMD section */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 37ee261b117d..e4595a8d731f 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -357,6 +357,7 @@ static void task_fpsimd_load(void) WARN_ON(!system_supports_fpsimd()); WARN_ON(preemptible()); + WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { @@ -379,7 +380,7 @@ static void task_fpsimd_load(void) default: /* * This indicates either a bug in - * fpsimd_save() or memory corruption, we + * fpsimd_save_user_state() or memory corruption, we * should always record an explicit format * when we save. We always at least have the * memory allocated for FPSMID registers so @@ -430,7 +431,7 @@ static void task_fpsimd_load(void) * than via current, if we are saving KVM state then it will have * ensured that the type of registers to save is set in last->to_save. */ -static void fpsimd_save(void) +static void fpsimd_save_user_state(void) { struct cpu_fp_state const *last = this_cpu_ptr(&fpsimd_last_state); @@ -861,7 +862,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, if (task == current) { get_cpu_fpsimd_context(); - fpsimd_save(); + fpsimd_save_user_state(); } fpsimd_flush_task_state(task); @@ -1473,6 +1474,16 @@ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs) current); } +static void fpsimd_load_kernel_state(struct task_struct *task) +{ + fpsimd_load_state(&task->thread.kernel_fpsimd_state); +} + +static void fpsimd_save_kernel_state(struct task_struct *task) +{ + fpsimd_save_state(&task->thread.kernel_fpsimd_state); +} + void fpsimd_thread_switch(struct task_struct *next) { bool wrong_task, wrong_cpu; @@ -1483,19 +1494,28 @@ void fpsimd_thread_switch(struct task_struct *next) WARN_ON_ONCE(!irqs_disabled()); /* Save unsaved fpsimd state, if any: */ - fpsimd_save(); + if (test_thread_flag(TIF_KERNEL_FPSTATE)) + fpsimd_save_kernel_state(current); + else + fpsimd_save_user_state(); - /* - * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's - * state. For kernel threads, FPSIMD registers are never loaded - * and wrong_task and wrong_cpu will always be true. - */ - wrong_task = __this_cpu_read(fpsimd_last_state.st) != - &next->thread.uw.fpsimd_state; - wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id(); + if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) { + fpsimd_load_kernel_state(next); + set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE); + } else { + /* + * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's + * state. For kernel threads, FPSIMD registers are never + * loaded with user mode FPSIMD state and so wrong_task and + * wrong_cpu will always be true. + */ + wrong_task = __this_cpu_read(fpsimd_last_state.st) != + &next->thread.uw.fpsimd_state; + wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id(); - update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, - wrong_task || wrong_cpu); + update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, + wrong_task || wrong_cpu); + } } static void fpsimd_flush_thread_vl(enum vec_type type) @@ -1585,7 +1605,7 @@ void fpsimd_preserve_current_state(void) return; get_cpu_fpsimd_context(); - fpsimd_save(); + fpsimd_save_user_state(); put_cpu_fpsimd_context(); } @@ -1803,7 +1823,7 @@ void fpsimd_save_and_flush_cpu_state(void) return; WARN_ON(preemptible()); local_irq_save(flags); - fpsimd_save(); + fpsimd_save_user_state(); fpsimd_flush_cpu_state(); local_irq_restore(flags); } @@ -1837,10 +1857,37 @@ void kernel_neon_begin(void) get_cpu_fpsimd_context(); /* Save unsaved fpsimd state, if any: */ - fpsimd_save(); + if (test_thread_flag(TIF_KERNEL_FPSTATE)) { + BUG_ON(IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()); + fpsimd_save_kernel_state(current); + } else { + fpsimd_save_user_state(); + + /* + * Set the thread flag so that the kernel mode FPSIMD state + * will be context switched along with the rest of the task + * state. + * + * On non-PREEMPT_RT, softirqs may interrupt task level kernel + * mode FPSIMD, but the task will not be preemptible so setting + * TIF_KERNEL_FPSTATE for those would be both wrong (as it + * would mark the task context FPSIMD state as requiring a + * context switch) and unnecessary. + * + * On PREEMPT_RT, softirqs are serviced from a separate thread, + * which is scheduled as usual, and this guarantees that these + * softirqs are not interrupting use of the FPSIMD in kernel + * mode in task context. So in this case, setting the flag here + * is always appropriate. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()) + set_thread_flag(TIF_KERNEL_FPSTATE); + } /* Invalidate any task state remaining in the fpsimd regs: */ fpsimd_flush_cpu_state(); + + put_cpu_fpsimd_context(); } EXPORT_SYMBOL_GPL(kernel_neon_begin); @@ -1858,7 +1905,16 @@ void kernel_neon_end(void) if (!system_supports_fpsimd()) return; - put_cpu_fpsimd_context(); + /* + * If we are returning from a nested use of kernel mode FPSIMD, restore + * the task context kernel mode FPSIMD state. This can only happen when + * running in softirq context on non-PREEMPT_RT. + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && in_serving_softirq() && + test_thread_flag(TIF_KERNEL_FPSTATE)) + fpsimd_load_kernel_state(current); + else + clear_thread_flag(TIF_KERNEL_FPSTATE); } EXPORT_SYMBOL_GPL(kernel_neon_end); -- cgit v1.2.3-58-ga151 From 2632e25217696712681dd1f3ecc0d71624ea3b23 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 8 Dec 2023 12:32:22 +0100 Subject: arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD Now that kernel mode FPSIMD state is context switched along with other task state, we can enable the existing logic that keeps track of which task's FPSIMD state the CPU is holding in its registers. If it is the context of the task that we are switching to, we can elide the reload of the FPSIMD state from memory. Note that we also need to check whether the FPSIMD state on this CPU is the most recent: if a task gets migrated away and back again, the state in memory may be more recent than the state in the CPU. So add another CPU id field to task_struct to keep track of this. (We could reuse the existing CPU id field used for user mode context, but that might result in user state to be discarded unnecessarily, given that two distinct CPUs could be holding the most recent user mode state and the most recent kernel mode state) Signed-off-by: Ard Biesheuvel Reviewed-by: Mark Brown Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20231208113218.3001940-9-ardb@google.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/processor.h | 1 + arch/arm64/kernel/fpsimd.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index ce6eebd6c08b..5b0a04810b23 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -169,6 +169,7 @@ struct thread_struct { struct debug_info debug; /* debugging */ struct user_fpsimd_state kernel_fpsimd_state; + unsigned int kernel_fpsimd_cpu; #ifdef CONFIG_ARM64_PTR_AUTH struct ptrauth_keys_user keys_user; #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index e4595a8d731f..e714d0cd5d1e 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1476,12 +1476,30 @@ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs) static void fpsimd_load_kernel_state(struct task_struct *task) { + struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); + + /* + * Elide the load if this CPU holds the most recent kernel mode + * FPSIMD context of the current task. + */ + if (last->st == &task->thread.kernel_fpsimd_state && + task->thread.kernel_fpsimd_cpu == smp_processor_id()) + return; + fpsimd_load_state(&task->thread.kernel_fpsimd_state); } static void fpsimd_save_kernel_state(struct task_struct *task) { + struct cpu_fp_state cpu_fp_state = { + .st = &task->thread.kernel_fpsimd_state, + .to_save = FP_STATE_FPSIMD, + }; + fpsimd_save_state(&task->thread.kernel_fpsimd_state); + fpsimd_bind_state_to_cpu(&cpu_fp_state); + + task->thread.kernel_fpsimd_cpu = smp_processor_id(); } void fpsimd_thread_switch(struct task_struct *next) -- cgit v1.2.3-58-ga151