*/
#include <linux/bitmap.h>
+#include <linux/bitops.h>
#include <linux/bottom_half.h>
#include <linux/bug.h>
#include <linux/cache.h>
#include <linux/slab.h>
#include <linux/stddef.h>
#include <linux/sysctl.h>
+#include <linux/swab.h>
#include <asm/esr.h>
#include <asm/fpsimd.h>
#include <asm/sigcontext.h>
#include <asm/sysreg.h>
#include <asm/traps.h>
+#include <asm/virt.h>
#define FPEXC_IOF (1 << 0)
#define FPEXC_DZF (1 << 1)
*/
struct fpsimd_last_state_struct {
struct user_fpsimd_state *st;
+ void *sve_state;
+ unsigned int sve_vl;
};
static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
/* Maximum supported vector length across all CPUs (initially poisoned) */
int __ro_after_init sve_max_vl = SVE_VL_MIN;
-/* Set of available vector lengths, as vq_to_bit(vq): */
-static __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN;
+
+/*
+ * Set of available vector lengths,
+ * where length vq encoded as bit __vq_to_bit(vq):
+ */
+__ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+/* Set of vector lengths present on at least one cpu: */
+static __ro_after_init DECLARE_BITMAP(sve_vq_partial_map, SVE_VQ_MAX);
+
static void __percpu *efi_sve_state;
#else /* ! CONFIG_ARM64_SVE */
/* Dummy declaration for code that will be optimised out: */
extern __ro_after_init DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX);
+extern __ro_after_init DECLARE_BITMAP(sve_vq_partial_map, SVE_VQ_MAX);
extern void __percpu *efi_sve_state;
#endif /* ! CONFIG_ARM64_SVE */
*/
void fpsimd_save(void)
{
- struct user_fpsimd_state *st = __this_cpu_read(fpsimd_last_state.st);
+ struct fpsimd_last_state_struct const *last =
+ this_cpu_ptr(&fpsimd_last_state);
/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
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)) {
+ if (WARN_ON(sve_get_vl() != last->sve_vl)) {
/*
* Can't save the user regs, so current would
* re-enter user with corrupt state.
return;
}
- sve_save_state(sve_pffr(¤t->thread), &st->fpsr);
+ sve_save_state((char *)last->sve_state +
+ sve_ffr_offset(last->sve_vl),
+ &last->st->fpsr);
} else
- fpsimd_save_state(st);
+ fpsimd_save_state(last->st);
}
}
-/*
- * 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 unsigned int vq_to_bit(unsigned int vq)
-{
- return SVE_VQ_MAX - vq;
-}
-
-static unsigned int bit_to_vq(unsigned int bit)
-{
- if (WARN_ON(bit >= SVE_VQ_MAX))
- bit = SVE_VQ_MAX - 1;
-
- return SVE_VQ_MAX - bit;
-}
-
/*
* All vector length selection from userspace comes through here.
* We're on a slow path, so some sanity-checks are included.
vl = max_vl;
bit = find_next_bit(sve_vq_map, SVE_VQ_MAX,
- vq_to_bit(sve_vq_from_vl(vl)));
- return sve_vl_from_vq(bit_to_vq(bit));
+ __vq_to_bit(sve_vq_from_vl(vl)));
+ return sve_vl_from_vq(__bit_to_vq(bit));
}
#ifdef CONFIG_SYSCTL
#define ZREG(sve_state, vq, n) ((char *)(sve_state) + \
(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
+#ifdef CONFIG_CPU_BIG_ENDIAN
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+ u64 a = swab64(x);
+ u64 b = swab64(x >> 64);
+
+ return ((__uint128_t)a << 64) | b;
+}
+#else
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+ return x;
+}
+#endif
+
+#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)
+
/*
* Transfer the FPSIMD state in task->thread.uw.fpsimd_state to
* task->thread.sve_state.
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
unsigned int i;
+ __uint128_t *p;
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]));
+ for (i = 0; i < 32; ++i) {
+ p = (__uint128_t *)ZREG(sst, vq, i);
+ *p = arm64_cpu_to_le128(fst->vregs[i]);
+ }
}
/*
void const *sst = task->thread.sve_state;
struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
unsigned int i;
+ __uint128_t const *p;
if (!system_supports_sve())
return;
vq = sve_vq_from_vl(task->thread.sve_vl);
- for (i = 0; i < 32; ++i)
- memcpy(&fst->vregs[i], ZREG(sst, vq, i),
- sizeof(fst->vregs[i]));
+ for (i = 0; i < 32; ++i) {
+ p = (__uint128_t const *)ZREG(sst, vq, i);
+ fst->vregs[i] = arm64_le128_to_cpu(*p);
+ }
}
#ifdef CONFIG_ARM64_SVE
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
unsigned int i;
+ __uint128_t *p;
if (!test_tsk_thread_flag(task, TIF_SVE))
return;
memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
- for (i = 0; i < 32; ++i)
- memcpy(ZREG(sst, vq, i), &fst->vregs[i],
- sizeof(fst->vregs[i]));
+ for (i = 0; i < 32; ++i) {
+ p = (__uint128_t *)ZREG(sst, vq, i);
+ *p = arm64_cpu_to_le128(fst->vregs[i]);
+ }
}
int sve_set_vector_length(struct task_struct *task,
local_bh_disable();
fpsimd_save();
- set_thread_flag(TIF_FOREIGN_FPSTATE);
}
fpsimd_flush_task_state(task);
return sve_prctl_status(0);
}
-/*
- * Bitmap for temporary storage of the per-CPU set of supported vector lengths
- * during secondary boot.
- */
-static DECLARE_BITMAP(sve_secondary_vq_map, SVE_VQ_MAX);
-
static void sve_probe_vqs(DECLARE_BITMAP(map, SVE_VQ_MAX))
{
unsigned int vq, vl;
write_sysreg_s(zcr | (vq - 1), SYS_ZCR_EL1); /* self-syncing */
vl = sve_get_vl();
vq = sve_vq_from_vl(vl); /* skip intervening lengths */
- set_bit(vq_to_bit(vq), map);
+ set_bit(__vq_to_bit(vq), map);
}
}
+/*
+ * Initialise the set of known supported VQs for the boot CPU.
+ * This is called during kernel boot, before secondary CPUs are brought up.
+ */
void __init sve_init_vq_map(void)
{
sve_probe_vqs(sve_vq_map);
+ bitmap_copy(sve_vq_partial_map, sve_vq_map, SVE_VQ_MAX);
}
/*
* If we haven't committed to the set of supported VQs yet, filter out
* those not supported by the current CPU.
+ * This function is called during the bring-up of early secondary CPUs only.
*/
void sve_update_vq_map(void)
{
- sve_probe_vqs(sve_secondary_vq_map);
- bitmap_and(sve_vq_map, sve_vq_map, sve_secondary_vq_map, SVE_VQ_MAX);
+ DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+
+ sve_probe_vqs(tmp_map);
+ bitmap_and(sve_vq_map, sve_vq_map, tmp_map, SVE_VQ_MAX);
+ bitmap_or(sve_vq_partial_map, sve_vq_partial_map, tmp_map, SVE_VQ_MAX);
}
-/* Check whether the current CPU supports all VQs in the committed set */
+/*
+ * Check whether the current CPU supports all VQs in the committed set.
+ * This function is called during the bring-up of late secondary CPUs only.
+ */
int sve_verify_vq_map(void)
{
- int ret = 0;
+ DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+ unsigned long b;
- sve_probe_vqs(sve_secondary_vq_map);
- bitmap_andnot(sve_secondary_vq_map, sve_vq_map, sve_secondary_vq_map,
- SVE_VQ_MAX);
- if (!bitmap_empty(sve_secondary_vq_map, SVE_VQ_MAX)) {
+ sve_probe_vqs(tmp_map);
+
+ bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
+ if (bitmap_intersects(tmp_map, sve_vq_map, SVE_VQ_MAX)) {
pr_warn("SVE: cpu%d: Required vector length(s) missing\n",
smp_processor_id());
- ret = -EINVAL;
+ return -EINVAL;
}
- return ret;
+ if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available())
+ return 0;
+
+ /*
+ * For KVM, it is necessary to ensure that this CPU doesn't
+ * support any vector length that guests may have probed as
+ * unsupported.
+ */
+
+ /* Recover the set of supported VQs: */
+ bitmap_complement(tmp_map, tmp_map, SVE_VQ_MAX);
+ /* Find VQs supported that are not globally supported: */
+ bitmap_andnot(tmp_map, tmp_map, sve_vq_map, SVE_VQ_MAX);
+
+ /* Find the lowest such VQ, if any: */
+ b = find_last_bit(tmp_map, SVE_VQ_MAX);
+ if (b >= SVE_VQ_MAX)
+ return 0; /* no mismatches */
+
+ /*
+ * Mismatches above sve_max_virtualisable_vl are fine, since
+ * no guest is allowed to configure ZCR_EL2.LEN to exceed this:
+ */
+ if (sve_vl_from_vq(__bit_to_vq(b)) <= sve_max_virtualisable_vl) {
+ pr_warn("SVE: cpu%d: Unsupported vector length(s) present\n",
+ smp_processor_id());
+ return -EINVAL;
+ }
+
+ return 0;
}
static void __init sve_efi_setup(void)
void __init sve_setup(void)
{
u64 zcr;
+ DECLARE_BITMAP(tmp_map, SVE_VQ_MAX);
+ unsigned long b;
if (!system_supports_sve())
return;
* so sve_vq_map must have at least SVE_VQ_MIN set.
* If something went wrong, at least try to patch it up:
*/
- if (WARN_ON(!test_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
- set_bit(vq_to_bit(SVE_VQ_MIN), sve_vq_map);
+ if (WARN_ON(!test_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map)))
+ set_bit(__vq_to_bit(SVE_VQ_MIN), sve_vq_map);
zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
sve_max_vl = sve_vl_from_vq((zcr & ZCR_ELx_LEN_MASK) + 1);
*/
sve_default_vl = find_supported_vector_length(64);
+ bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map,
+ SVE_VQ_MAX);
+
+ b = find_last_bit(tmp_map, SVE_VQ_MAX);
+ if (b >= SVE_VQ_MAX)
+ /* No non-virtualisable VLs found */
+ sve_max_virtualisable_vl = SVE_VQ_MAX;
+ else if (WARN_ON(b == SVE_VQ_MAX - 1))
+ /* No virtualisable VLs? This is architecturally forbidden. */
+ sve_max_virtualisable_vl = SVE_VQ_MIN;
+ else /* b + 1 < SVE_VQ_MAX */
+ sve_max_virtualisable_vl = sve_vl_from_vq(__bit_to_vq(b + 1));
+
+ if (sve_max_virtualisable_vl > sve_max_vl)
+ sve_max_virtualisable_vl = sve_max_vl;
+
pr_info("SVE: maximum available vector length %u bytes per vector\n",
sve_max_vl);
pr_info("SVE: default vector length %u bytes per vector\n",
sve_default_vl);
+ /* KVM decides whether to support mismatched systems. Just warn here: */
+ if (sve_max_virtualisable_vl < sve_max_vl)
+ pr_warn("SVE: unvirtualisable vector lengths present\n");
+
sve_efi_setup();
}
local_bh_disable();
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);
+ fpsimd_to_sve(current);
if (test_and_set_thread_flag(TIF_SVE))
WARN_ON(1); /* SVE access shouldn't have trapped */
local_bh_disable();
+ fpsimd_flush_task_state(current);
memset(¤t->thread.uw.fpsimd_state, 0,
sizeof(current->thread.uw.fpsimd_state));
- fpsimd_flush_task_state(current);
if (system_supports_sve()) {
clear_thread_flag(TIF_SVE);
current->thread.sve_vl_onexec = 0;
}
- set_thread_flag(TIF_FOREIGN_FPSTATE);
-
local_bh_enable();
}
this_cpu_ptr(&fpsimd_last_state);
last->st = ¤t->thread.uw.fpsimd_state;
+ last->sve_state = current->thread.sve_state;
+ last->sve_vl = current->thread.sve_vl;
current->thread.fpsimd_cpu = smp_processor_id();
if (system_supports_sve()) {
}
}
-void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st)
+void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
+ unsigned int sve_vl)
{
struct fpsimd_last_state_struct *last =
this_cpu_ptr(&fpsimd_last_state);
WARN_ON(!in_softirq() && !irqs_disabled());
last->st = st;
+ last->sve_state = sve_state;
+ last->sve_vl = sve_vl;
}
/*
/*
* Invalidate live CPU copies of task t's FPSIMD state
+ *
+ * This function may be called with preemption enabled. The barrier()
+ * ensures that the assignment to fpsimd_cpu is visible to any
+ * preemption/softirq that could race with set_tsk_thread_flag(), so
+ * that TIF_FOREIGN_FPSTATE cannot be spuriously re-cleared.
+ *
+ * The final barrier ensures that TIF_FOREIGN_FPSTATE is seen set by any
+ * subsequent code.
*/
void fpsimd_flush_task_state(struct task_struct *t)
{
t->thread.fpsimd_cpu = NR_CPUS;
+
+ barrier();
+ set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE);
+
+ barrier();
}
+/*
+ * Invalidate any task's FPSIMD state that is present on this cpu.
+ * This function must be called with softirqs disabled.
+ */
void fpsimd_flush_cpu_state(void)
{
__this_cpu_write(fpsimd_last_state.st, NULL);
projects / thirdparty / linux.git / blobdiff