diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 026a7c7fc30b..5655fe1ced46 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -20,6 +20,8 @@ #ifndef __ASSEMBLY__ +#include + /* * FP/SIMD storage area has: * - FPSR and FPCR @@ -72,6 +74,20 @@ extern void sve_load_state(void const *state, u32 const *pfpsr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); +#ifdef CONFIG_ARM64_SVE + +extern size_t sve_state_size(struct task_struct const *task); + +extern void sve_alloc(struct task_struct *task); +extern void fpsimd_release_task(struct task_struct *task); + +#else /* ! CONFIG_ARM64_SVE */ + +static inline void sve_alloc(struct task_struct *task) { } +static inline void fpsimd_release_task(struct task_struct *task) { } + +#endif /* ! CONFIG_ARM64_SVE */ + /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 7dddca21fc64..e2f575dbdddd 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -105,6 +105,8 @@ struct thread_struct { unsigned long tp2_value; #endif struct fpsimd_state fpsimd_state; + void *sve_state; /* SVE registers, if any */ + unsigned int sve_vl; /* SVE vector length */ unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index ddded6497a8a..92b7b48576c8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -63,6 +63,8 @@ struct thread_info { void arch_setup_new_exec(void); #define arch_setup_new_exec arch_setup_new_exec +void arch_release_task_struct(struct task_struct *tsk); + #endif /* @@ -92,6 +94,7 @@ void arch_setup_new_exec(void); #define TIF_RESTORE_SIGMASK 20 #define TIF_SINGLESTEP 21 #define TIF_32BIT 22 /* 32bit process */ +#define TIF_SVE 23 /* Scalable Vector Extension in use */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) @@ -105,6 +108,7 @@ void arch_setup_new_exec(void); #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_FSCHECK (1 << TIF_FSCHECK) #define _TIF_32BIT (1 << TIF_32BIT) +#define _TIF_SVE (1 << TIF_SVE) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 45e3da34bdc4..1696f9de9359 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -34,6 +34,8 @@ struct undef_hook { void register_undef_hook(struct undef_hook *hook); void unregister_undef_hook(struct undef_hook *hook); +void force_signal_inject(int signal, int code, struct pt_regs *regs, + unsigned long address); void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index bfa4bd09110a..a989e234dc32 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -599,6 +599,8 @@ el0_sync: b.eq el0_ia cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access b.eq el0_fpsimd_acc + cmp x24, #ESR_ELx_EC_SVE // SVE access + b.eq el0_sve_acc cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception b.eq el0_fpsimd_exc cmp x24, #ESR_ELx_EC_SYS64 // configurable trap @@ -650,6 +652,7 @@ el0_svc_compat: /* * AArch32 syscall handling */ + ldr x16, [tsk, #TSK_TI_FLAGS] // load thread flags adrp stbl, compat_sys_call_table // load compat syscall table pointer mov wscno, w7 // syscall number in w7 (r7) mov wsc_nr, #__NR_compat_syscalls @@ -699,9 +702,19 @@ el0_fpsimd_acc: mov x1, sp bl do_fpsimd_acc b ret_to_user +el0_sve_acc: + /* + * Scalable Vector Extension access + */ + enable_daif + ct_user_exit + mov x0, x25 + mov x1, sp + bl do_sve_acc + b ret_to_user el0_fpsimd_exc: /* - * Floating Point or Advanced SIMD exception + * Floating Point, Advanced SIMD or SVE exception */ enable_daif ct_user_exit @@ -849,16 +862,36 @@ ENDPROC(ret_to_user) */ .align 6 el0_svc: + ldr x16, [tsk, #TSK_TI_FLAGS] // load thread flags adrp stbl, sys_call_table // load syscall table pointer mov wscno, w8 // syscall number in w8 mov wsc_nr, #__NR_syscalls + +#ifndef CONFIG_ARM64_SVE + b el0_svc_naked +#else + tbz x16, #TIF_SVE, el0_svc_naked // Skip unless TIF_SVE set: + bic x16, x16, #_TIF_SVE // discard SVE state + str x16, [tsk, #TSK_TI_FLAGS] + + /* + * task_fpsimd_load() won't be called to update CPACR_EL1 in + * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only + * happens if a context switch or kernel_neon_begin() or context + * modification (sigreturn, ptrace) intervenes. + * So, ensure that CPACR_EL1 is already correct for the fast-path case: + */ + mrs x9, cpacr_el1 + bic x9, x9, #CPACR_EL1_ZEN_EL0EN // disable SVE for el0 + msr cpacr_el1, x9 // synchronised by eret to el0 +#endif /* CONFIG_ARM64_SVE */ + el0_svc_naked: // compat entry point stp x0, xscno, [sp, #S_ORIG_X0] // save the original x0 and syscall number enable_daif ct_user_exit 1 - ldr x16, [tsk, #TSK_TI_FLAGS] // check for syscall hooks - tst x16, #_TIF_SYSCALL_WORK + tst x16, #_TIF_SYSCALL_WORK // check for syscall hooks b.ne __sys_trace cmp wscno, wsc_nr // check upper syscall limit b.hs ni_sys diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 901078a9cbe5..000b5f9215c6 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -18,19 +18,28 @@ */ #include +#include +#include #include #include #include #include +#include #include #include #include +#include #include +#include #include +#include #include #include #include +#include +#include +#include #define FPEXC_IOF (1 << 0) #define FPEXC_DZF (1 << 1) @@ -40,6 +49,8 @@ #define FPEXC_IDF (1 << 7) /* + * (Note: in this discussion, statements about FPSIMD apply equally to SVE.) + * * In order to reduce the number of times the FPSIMD state is needlessly saved * and restored, we need to keep track of two things: * (a) for each task, we need to remember which CPU was the last one to have @@ -100,6 +111,279 @@ */ static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state); +/* + * Call __sve_free() directly only if you know task can't be scheduled + * or preempted. + */ +static void __sve_free(struct task_struct *task) +{ + kfree(task->thread.sve_state); + task->thread.sve_state = NULL; +} + +static void sve_free(struct task_struct *task) +{ + WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); + + __sve_free(task); +} + + +/* Offset of FFR in the SVE register dump */ +static size_t sve_ffr_offset(int vl) +{ + return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET; +} + +static void *sve_pffr(struct task_struct *task) +{ + return (char *)task->thread.sve_state + + sve_ffr_offset(task->thread.sve_vl); +} + +static void change_cpacr(u64 val, u64 mask) +{ + u64 cpacr = read_sysreg(CPACR_EL1); + u64 new = (cpacr & ~mask) | val; + + if (new != cpacr) + write_sysreg(new, CPACR_EL1); +} + +static void sve_user_disable(void) +{ + change_cpacr(0, CPACR_EL1_ZEN_EL0EN); +} + +static void sve_user_enable(void) +{ + change_cpacr(CPACR_EL1_ZEN_EL0EN, CPACR_EL1_ZEN_EL0EN); +} + +/* + * TIF_SVE controls whether a task can use SVE without trapping while + * in userspace, and also the way a task's FPSIMD/SVE state is stored + * in thread_struct. + * + * The kernel uses this flag to track whether a user task is actively + * using SVE, and therefore whether full SVE register state needs to + * be tracked. If not, the cheaper FPSIMD context handling code can + * be used instead of the more costly SVE equivalents. + * + * * TIF_SVE set: + * + * The task can execute SVE instructions while in userspace without + * trapping to the kernel. + * + * When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the + * corresponding Zn), P0-P15 and FFR are encoded in in + * task->thread.sve_state, formatted appropriately for vector + * length task->thread.sve_vl. + * + * task->thread.sve_state must point to a valid buffer at least + * sve_state_size(task) bytes in size. + * + * During any syscall, the kernel may optionally clear TIF_SVE and + * discard the vector state except for the FPSIMD subset. + * + * * TIF_SVE clear: + * + * An attempt by the user task to execute an SVE instruction causes + * do_sve_acc() to be called, which does some preparation and then + * sets TIF_SVE. + * + * When stored, FPSIMD registers V0-V31 are encoded in + * task->fpsimd_state; bits [max : 128] for each of Z0-Z31 are + * logically zero but not stored anywhere; P0-P15 and FFR are not + * stored and have unspecified values from userspace's point of + * view. For hygiene purposes, the kernel zeroes them on next use, + * but userspace is discouraged from relying on this. + * + * task->thread.sve_state does not need to be non-NULL, valid or any + * particular size: it must not be dereferenced. + * + * * FPSR and FPCR are always stored in task->fpsimd_state irrespctive of + * whether TIF_SVE is clear or set, since these are not vector length + * dependent. + */ + +/* + * Update current's FPSIMD/SVE registers from thread_struct. + * + * This function should be called only when the FPSIMD/SVE state in + * thread_struct is known to be up to date, when preparing to enter + * userspace. + * + * Softirqs (and preemption) must be disabled. + */ +static void task_fpsimd_load(void) +{ + WARN_ON(!in_softirq() && !irqs_disabled()); + + if (system_supports_sve() && test_thread_flag(TIF_SVE)) + sve_load_state(sve_pffr(current), + ¤t->thread.fpsimd_state.fpsr, + sve_vq_from_vl(current->thread.sve_vl) - 1); + else + fpsimd_load_state(¤t->thread.fpsimd_state); + + if (system_supports_sve()) { + /* Toggle SVE trapping for userspace if needed */ + if (test_thread_flag(TIF_SVE)) + sve_user_enable(); + else + sve_user_disable(); + + /* Serialised by exception return to user */ + } +} + +/* + * Ensure current's FPSIMD/SVE storage in thread_struct is up to date + * with respect to the CPU registers. + * + * Softirqs (and preemption) must be disabled. + */ +static void task_fpsimd_save(void) +{ + WARN_ON(!in_softirq() && !irqs_disabled()); + + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { + if (system_supports_sve() && test_thread_flag(TIF_SVE)) { + if (WARN_ON(sve_get_vl() != current->thread.sve_vl)) { + /* + * Can't save the user regs, so current would + * re-enter user with corrupt state. + * There's no way to recover, so kill it: + */ + force_signal_inject( + SIGKILL, 0, current_pt_regs(), 0); + return; + } + + sve_save_state(sve_pffr(current), + ¤t->thread.fpsimd_state.fpsr); + } else + fpsimd_save_state(¤t->thread.fpsimd_state); + } +} + +#define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ + (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) + +/* + * Transfer the FPSIMD state in task->thread.fpsimd_state to + * task->thread.sve_state. + * + * Task can be a non-runnable task, or current. In the latter case, + * softirqs (and preemption) must be disabled. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + * task->thread.fpsimd_state must be up to date before calling this function. + */ +static void fpsimd_to_sve(struct task_struct *task) +{ + unsigned int vq; + void *sst = task->thread.sve_state; + struct fpsimd_state const *fst = &task->thread.fpsimd_state; + unsigned int i; + + if (!system_supports_sve()) + return; + + vq = sve_vq_from_vl(task->thread.sve_vl); + for (i = 0; i < 32; ++i) + memcpy(ZREG(sst, vq, i), &fst->vregs[i], + sizeof(fst->vregs[i])); +} + +#ifdef CONFIG_ARM64_SVE + +/* + * Return how many bytes of memory are required to store the full SVE + * state for task, given task's currently configured vector length. + */ +size_t sve_state_size(struct task_struct const *task) +{ + return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task->thread.sve_vl)); +} + +/* + * Ensure that task->thread.sve_state is allocated and sufficiently large. + * + * This function should be used only in preparation for replacing + * task->thread.sve_state with new data. The memory is always zeroed + * here to prevent stale data from showing through: this is done in + * the interest of testability and predictability: except in the + * do_sve_acc() case, there is no ABI requirement to hide stale data + * written previously be task. + */ +void sve_alloc(struct task_struct *task) +{ + if (task->thread.sve_state) { + memset(task->thread.sve_state, 0, sve_state_size(current)); + return; + } + + /* This is a small allocation (maximum ~8KB) and Should Not Fail. */ + task->thread.sve_state = + kzalloc(sve_state_size(task), GFP_KERNEL); + + /* + * If future SVE revisions can have larger vectors though, + * this may cease to be true: + */ + BUG_ON(!task->thread.sve_state); +} + +/* + * Called from the put_task_struct() path, which cannot get here + * unless dead_task is really dead and not schedulable. + */ +void fpsimd_release_task(struct task_struct *dead_task) +{ + __sve_free(dead_task); +} + +#endif /* CONFIG_ARM64_SVE */ + +/* + * Trapped SVE access + * + * Storage is allocated for the full SVE state, the current FPSIMD + * register contents are migrated across, and TIF_SVE is set so that + * the SVE access trap will be disabled the next time this task + * reaches ret_to_user. + * + * TIF_SVE should be clear on entry: otherwise, task_fpsimd_load() + * would have disabled the SVE access trap for userspace during + * ret_to_user, making an SVE access trap impossible in that case. + */ +asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) +{ + /* Even if we chose not to use SVE, the hardware could still trap: */ + if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); + return; + } + + sve_alloc(current); + + local_bh_disable(); + + task_fpsimd_save(); + fpsimd_to_sve(current); + + /* Force ret_to_user to reload the registers: */ + fpsimd_flush_task_state(current); + set_thread_flag(TIF_FOREIGN_FPSTATE); + + if (test_and_set_thread_flag(TIF_SVE)) + WARN_ON(1); /* SVE access shouldn't have trapped */ + + local_bh_enable(); +} + /* * Trapped FP/ASIMD access. */ @@ -145,8 +429,8 @@ void fpsimd_thread_switch(struct task_struct *next) * the registers is in fact the most recent userland FPSIMD state of * 'current'. */ - if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE)) - fpsimd_save_state(¤t->thread.fpsimd_state); + if (current->mm) + task_fpsimd_save(); if (next->mm) { /* @@ -168,6 +452,8 @@ void fpsimd_thread_switch(struct task_struct *next) void fpsimd_flush_thread(void) { + int vl; + if (!system_supports_fpsimd()) return; @@ -175,6 +461,30 @@ void fpsimd_flush_thread(void) memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state)); fpsimd_flush_task_state(current); + + if (system_supports_sve()) { + clear_thread_flag(TIF_SVE); + sve_free(current); + + /* + * Reset the task vector length as required. + * This is where we ensure that all user tasks have a valid + * vector length configured: no kernel task can become a user + * task without an exec and hence a call to this function. + * If a bug causes this to go wrong, we make some noise and + * try to fudge thread.sve_vl to a safe value here. + */ + vl = current->thread.sve_vl; + + if (vl == 0) + vl = SVE_VL_MIN; + + if (WARN_ON(!sve_vl_valid(vl))) + vl = SVE_VL_MIN; + + current->thread.sve_vl = vl; + } + set_thread_flag(TIF_FOREIGN_FPSTATE); local_bh_enable(); @@ -183,6 +493,9 @@ void fpsimd_flush_thread(void) /* * Save the userland FPSIMD state of 'current' to memory, but only if the state * currently held in the registers does in fact belong to 'current' + * + * Currently, SVE tasks can't exist, so just WARN in that case. + * Subsequent patches will add full SVE support here. */ void fpsimd_preserve_current_state(void) { @@ -194,6 +507,8 @@ void fpsimd_preserve_current_state(void) if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) fpsimd_save_state(¤t->thread.fpsimd_state); + WARN_ON_ONCE(test_and_clear_thread_flag(TIF_SVE)); + local_bh_enable(); } @@ -212,7 +527,7 @@ void fpsimd_restore_current_state(void) if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { struct fpsimd_state *st = ¤t->thread.fpsimd_state; - fpsimd_load_state(st); + task_fpsimd_load(); __this_cpu_write(fpsimd_last_state, st); st->cpu = smp_processor_id(); } @@ -381,8 +696,8 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self, { switch (cmd) { case CPU_PM_ENTER: - if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE)) - fpsimd_save_state(¤t->thread.fpsimd_state); + if (current->mm) + task_fpsimd_save(); this_cpu_write(fpsimd_last_state, NULL); break; case CPU_PM_EXIT: diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index c15ec41e9f84..b2adcce7bc18 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -273,11 +274,27 @@ void release_thread(struct task_struct *dead_task) { } +void arch_release_task_struct(struct task_struct *tsk) +{ + fpsimd_release_task(tsk); +} + +/* + * src and dst may temporarily have aliased sve_state after task_struct + * is copied. We cannot fix this properly here, because src may have + * live SVE state and dst's thread_info may not exist yet, so tweaking + * either src's or dst's TIF_SVE is not safe. + * + * The unaliasing is done in copy_thread() instead. This works because + * dst is not schedulable or traceable until both of these functions + * have been called. + */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { if (current->mm) fpsimd_preserve_current_state(); *dst = *src; + return 0; } @@ -290,6 +307,13 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); + /* + * Unalias p->thread.sve_state (if any) from the parent task + * and disable discard SVE state for p: + */ + clear_tsk_thread_flag(p, TIF_SVE); + p->thread.sve_state = NULL; + if (likely(!(p->flags & PF_KTHREAD))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 3408b33f6e7c..03f8f8ef542d 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -311,8 +311,8 @@ exit: return fn ? fn(regs, instr) : 1; } -static void force_signal_inject(int signal, int code, struct pt_regs *regs, - unsigned long address) +void force_signal_inject(int signal, int code, struct pt_regs *regs, + unsigned long address) { siginfo_t info; void __user *pc = (void __user *)instruction_pointer(regs); @@ -326,7 +326,7 @@ static void force_signal_inject(int signal, int code, struct pt_regs *regs, desc = "illegal memory access"; break; default: - desc = "bad mode"; + desc = "unknown or unrecoverable error"; break; }