summaryrefslogtreecommitdiffstats
path: root/arch/arm64/include/asm/fpsimd.h
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
commit2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch)
tree848558de17fb3008cdf4d861b01ac7781903ce39 /arch/arm64/include/asm/fpsimd.h
parentInitial commit. (diff)
downloadlinux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz
linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip
Adding upstream version 6.1.76.upstream/6.1.76upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/arm64/include/asm/fpsimd.h')
-rw-r--r--arch/arm64/include/asm/fpsimd.h389
1 files changed, 389 insertions, 0 deletions
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
new file mode 100644
index 000000000..d720b6f7e
--- /dev/null
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -0,0 +1,389 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_FP_H
+#define __ASM_FP_H
+
+#include <asm/errno.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitmap.h>
+#include <linux/build_bug.h>
+#include <linux/bug.h>
+#include <linux/cache.h>
+#include <linux/init.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_COMPAT
+/* Masks for extracting the FPSR and FPCR from the FPSCR */
+#define VFP_FPSCR_STAT_MASK 0xf800009f
+#define VFP_FPSCR_CTRL_MASK 0x07f79f00
+/*
+ * The VFP state has 32x64-bit registers and a single 32-bit
+ * control/status register.
+ */
+#define VFP_STATE_SIZE ((32 * 8) + 4)
+#endif
+
+/*
+ * When we defined the maximum SVE vector length we defined the ABI so
+ * that the maximum vector length included all the reserved for future
+ * expansion bits in ZCR rather than those just currently defined by
+ * the architecture. While SME follows a similar pattern the fact that
+ * it includes a square matrix means that any allocations that attempt
+ * to cover the maximum potential vector length (such as happen with
+ * the regset used for ptrace) end up being extremely large. Define
+ * the much lower actual limit for use in such situations.
+ */
+#define SME_VQ_MAX 16
+
+struct task_struct;
+
+extern void fpsimd_save_state(struct user_fpsimd_state *state);
+extern void fpsimd_load_state(struct user_fpsimd_state *state);
+
+extern void fpsimd_thread_switch(struct task_struct *next);
+extern void fpsimd_flush_thread(void);
+
+extern void fpsimd_signal_preserve_current_state(void);
+extern void fpsimd_preserve_current_state(void);
+extern void fpsimd_restore_current_state(void);
+extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
+
+extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
+ void *sve_state, unsigned int sve_vl,
+ void *za_state, unsigned int sme_vl,
+ u64 *svcr);
+
+extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void fpsimd_save_and_flush_cpu_state(void);
+
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+ return system_supports_sme() && (thread->svcr & SVCR_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+ return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK);
+}
+
+/* Maximum VL that SVE/SME VL-agnostic software can transparently support */
+#define VL_ARCH_MAX 0x100
+
+/* Offset of FFR in the SVE register dump */
+static inline size_t sve_ffr_offset(int vl)
+{
+ return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET;
+}
+
+static inline void *sve_pffr(struct thread_struct *thread)
+{
+ unsigned int vl;
+
+ if (system_supports_sme() && thread_sm_enabled(thread))
+ vl = thread_get_sme_vl(thread);
+ else
+ vl = thread_get_sve_vl(thread);
+
+ return (char *)thread->sve_state + sve_ffr_offset(vl);
+}
+
+extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
+extern void sve_load_state(void const *state, u32 const *pfpsr,
+ int restore_ffr);
+extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
+extern unsigned int sve_get_vl(void);
+extern void sve_set_vq(unsigned long vq_minus_1);
+extern void sme_set_vq(unsigned long vq_minus_1);
+extern void za_save_state(void *state);
+extern void za_load_state(void const *state);
+
+struct arm64_cpu_capabilities;
+extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+
+extern u64 read_zcr_features(void);
+extern u64 read_smcr_features(void);
+
+/*
+ * Helpers to translate bit indices in sve_vq_map to VQ values (and
+ * vice versa). This allows find_next_bit() to be used to find the
+ * _maximum_ VQ not exceeding a certain value.
+ */
+static inline unsigned int __vq_to_bit(unsigned int vq)
+{
+ return SVE_VQ_MAX - vq;
+}
+
+static inline unsigned int __bit_to_vq(unsigned int bit)
+{
+ return SVE_VQ_MAX - bit;
+}
+
+
+struct vl_info {
+ enum vec_type type;
+ const char *name; /* For display purposes */
+
+ /* Minimum supported vector length across all CPUs */
+ int min_vl;
+
+ /* Maximum supported vector length across all CPUs */
+ int max_vl;
+ int max_virtualisable_vl;
+
+ /*
+ * Set of available vector lengths,
+ * where length vq encoded as bit __vq_to_bit(vq):
+ */
+ DECLARE_BITMAP(vq_map, SVE_VQ_MAX);
+
+ /* Set of vector lengths present on at least one cpu: */
+ DECLARE_BITMAP(vq_partial_map, SVE_VQ_MAX);
+};
+
+#ifdef CONFIG_ARM64_SVE
+
+extern void sve_alloc(struct task_struct *task, bool flush);
+extern void fpsimd_release_task(struct task_struct *task);
+extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void fpsimd_force_sync_to_sve(struct task_struct *task);
+extern void sve_sync_to_fpsimd(struct task_struct *task);
+extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
+
+extern int vec_set_vector_length(struct task_struct *task, enum vec_type type,
+ unsigned long vl, unsigned long flags);
+
+extern int sve_set_current_vl(unsigned long arg);
+extern int sve_get_current_vl(void);
+
+static inline void sve_user_disable(void)
+{
+ sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0);
+}
+
+static inline void sve_user_enable(void)
+{
+ sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN);
+}
+
+#define sve_cond_update_zcr_vq(val, reg) \
+ do { \
+ u64 __zcr = read_sysreg_s((reg)); \
+ u64 __new = __zcr & ~ZCR_ELx_LEN_MASK; \
+ __new |= (val) & ZCR_ELx_LEN_MASK; \
+ if (__zcr != __new) \
+ write_sysreg_s(__new, (reg)); \
+ } while (0)
+
+/*
+ * Probing and setup functions.
+ * Calls to these functions must be serialised with one another.
+ */
+enum vec_type;
+
+extern void __init vec_init_vq_map(enum vec_type type);
+extern void vec_update_vq_map(enum vec_type type);
+extern int vec_verify_vq_map(enum vec_type type);
+extern void __init sve_setup(void);
+
+extern __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX];
+
+static inline void write_vl(enum vec_type type, u64 val)
+{
+ u64 tmp;
+
+ switch (type) {
+#ifdef CONFIG_ARM64_SVE
+ case ARM64_VEC_SVE:
+ tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK;
+ write_sysreg_s(tmp | val, SYS_ZCR_EL1);
+ break;
+#endif
+#ifdef CONFIG_ARM64_SME
+ case ARM64_VEC_SME:
+ tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK;
+ write_sysreg_s(tmp | val, SYS_SMCR_EL1);
+ break;
+#endif
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
+}
+
+static inline int vec_max_vl(enum vec_type type)
+{
+ return vl_info[type].max_vl;
+}
+
+static inline int vec_max_virtualisable_vl(enum vec_type type)
+{
+ return vl_info[type].max_virtualisable_vl;
+}
+
+static inline int sve_max_vl(void)
+{
+ return vec_max_vl(ARM64_VEC_SVE);
+}
+
+static inline int sve_max_virtualisable_vl(void)
+{
+ return vec_max_virtualisable_vl(ARM64_VEC_SVE);
+}
+
+/* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */
+static inline bool vq_available(enum vec_type type, unsigned int vq)
+{
+ return test_bit(__vq_to_bit(vq), vl_info[type].vq_map);
+}
+
+static inline bool sve_vq_available(unsigned int vq)
+{
+ return vq_available(ARM64_VEC_SVE, vq);
+}
+
+size_t sve_state_size(struct task_struct const *task);
+
+#else /* ! CONFIG_ARM64_SVE */
+
+static inline void sve_alloc(struct task_struct *task, bool flush) { }
+static inline void fpsimd_release_task(struct task_struct *task) { }
+static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
+static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
+
+static inline int sve_max_virtualisable_vl(void)
+{
+ return 0;
+}
+
+static inline int sve_set_current_vl(unsigned long arg)
+{
+ return -EINVAL;
+}
+
+static inline int sve_get_current_vl(void)
+{
+ return -EINVAL;
+}
+
+static inline int sve_max_vl(void)
+{
+ return -EINVAL;
+}
+
+static inline bool sve_vq_available(unsigned int vq) { return false; }
+
+static inline void sve_user_disable(void) { BUILD_BUG(); }
+static inline void sve_user_enable(void) { BUILD_BUG(); }
+
+#define sve_cond_update_zcr_vq(val, reg) do { } while (0)
+
+static inline void vec_init_vq_map(enum vec_type t) { }
+static inline void vec_update_vq_map(enum vec_type t) { }
+static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
+static inline void sve_setup(void) { }
+
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+ return 0;
+}
+
+#endif /* ! CONFIG_ARM64_SVE */
+
+#ifdef CONFIG_ARM64_SME
+
+static inline void sme_user_disable(void)
+{
+ sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0);
+}
+
+static inline void sme_user_enable(void)
+{
+ sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN);
+}
+
+static inline void sme_smstart_sm(void)
+{
+ asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop_sm(void)
+{
+ asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop(void)
+{
+ asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr"));
+}
+
+extern void __init sme_setup(void);
+
+static inline int sme_max_vl(void)
+{
+ return vec_max_vl(ARM64_VEC_SME);
+}
+
+static inline int sme_max_virtualisable_vl(void)
+{
+ return vec_max_virtualisable_vl(ARM64_VEC_SME);
+}
+
+extern void sme_alloc(struct task_struct *task, bool flush);
+extern unsigned int sme_get_vl(void);
+extern int sme_set_current_vl(unsigned long arg);
+extern int sme_get_current_vl(void);
+
+/*
+ * Return how many bytes of memory are required to store the full SME
+ * specific state (currently just ZA) for task, given task's currently
+ * configured vector length.
+ */
+static inline size_t za_state_size(struct task_struct const *task)
+{
+ unsigned int vl = task_get_sme_vl(task);
+
+ return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
+#else
+
+static inline void sme_user_disable(void) { BUILD_BUG(); }
+static inline void sme_user_enable(void) { BUILD_BUG(); }
+
+static inline void sme_smstart_sm(void) { }
+static inline void sme_smstop_sm(void) { }
+static inline void sme_smstop(void) { }
+
+static inline void sme_alloc(struct task_struct *task, bool flush) { }
+static inline void sme_setup(void) { }
+static inline unsigned int sme_get_vl(void) { return 0; }
+static inline int sme_max_vl(void) { return 0; }
+static inline int sme_max_virtualisable_vl(void) { return 0; }
+static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
+static inline int sme_get_current_vl(void) { return -EINVAL; }
+
+static inline size_t za_state_size(struct task_struct const *task)
+{
+ return 0;
+}
+
+#endif /* ! CONFIG_ARM64_SME */
+
+/* For use by EFI runtime services calls only */
+extern void __efi_fpsimd_begin(void);
+extern void __efi_fpsimd_end(void);
+
+#endif
+
+#endif