summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/fpu
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/x86/kernel/fpu
parentInitial commit. (diff)
downloadlinux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz
linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip
Adding upstream version 6.1.76.upstream/6.1.76
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
-rw-r--r--arch/x86/kernel/fpu/Makefile6
-rw-r--r--arch/x86/kernel/fpu/bugs.c59
-rw-r--r--arch/x86/kernel/fpu/context.h82
-rw-r--r--arch/x86/kernel/fpu/core.c865
-rw-r--r--arch/x86/kernel/fpu/init.c229
-rw-r--r--arch/x86/kernel/fpu/internal.h28
-rw-r--r--arch/x86/kernel/fpu/legacy.h111
-rw-r--r--arch/x86/kernel/fpu/regset.c386
-rw-r--r--arch/x86/kernel/fpu/signal.c542
-rw-r--r--arch/x86/kernel/fpu/xstate.c1843
-rw-r--r--arch/x86/kernel/fpu/xstate.h327
11 files changed, 4478 insertions, 0 deletions
diff --git a/arch/x86/kernel/fpu/Makefile b/arch/x86/kernel/fpu/Makefile
new file mode 100644
index 000000000..78c562145
--- /dev/null
+++ b/arch/x86/kernel/fpu/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Build rules for the FPU support code:
+#
+
+obj-y += init.o bugs.o core.o regset.o signal.o xstate.o
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
new file mode 100644
index 000000000..794e70151
--- /dev/null
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * x86 FPU bug checks:
+ */
+#include <asm/fpu/api.h>
+
+/*
+ * Boot time CPU/FPU FDIV bug detection code:
+ */
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+void __init fpu__init_check_bugs(void)
+{
+ s32 fdiv_bug;
+
+ /* kernel_fpu_begin/end() relies on patched alternative instructions. */
+ if (!boot_cpu_has(X86_FEATURE_FPU))
+ return;
+
+ kernel_fpu_begin();
+
+ /*
+ * trap_init() enabled FXSR and company _before_ testing for FP
+ * problems here.
+ *
+ * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
+ */
+ __asm__("fninit\n\t"
+ "fldl %1\n\t"
+ "fdivl %2\n\t"
+ "fmull %2\n\t"
+ "fldl %1\n\t"
+ "fsubp %%st,%%st(1)\n\t"
+ "fistpl %0\n\t"
+ "fwait\n\t"
+ "fninit"
+ : "=m" (*&fdiv_bug)
+ : "m" (*&x), "m" (*&y));
+
+ kernel_fpu_end();
+
+ if (fdiv_bug) {
+ set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
+ pr_warn("Hmm, FPU with FDIV bug\n");
+ }
+}
diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h
new file mode 100644
index 000000000..71b5059e0
--- /dev/null
+++ b/arch/x86/kernel/fpu/context.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_CONTEXT_H
+#define __X86_KERNEL_FPU_CONTEXT_H
+
+#include <asm/fpu/xstate.h>
+#include <asm/trace/fpu.h>
+
+/* Functions related to FPU context tracking */
+
+/*
+ * The in-register FPU state for an FPU context on a CPU is assumed to be
+ * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx
+ * matches the FPU.
+ *
+ * If the FPU register state is valid, the kernel can skip restoring the
+ * FPU state from memory.
+ *
+ * Any code that clobbers the FPU registers or updates the in-memory
+ * FPU state for a task MUST let the rest of the kernel know that the
+ * FPU registers are no longer valid for this task.
+ *
+ * Invalidate a resource you control: CPU if using the CPU for something else
+ * (with preemption disabled), FPU for the current task, or a task that
+ * is prevented from running by the current task.
+ */
+static inline void __cpu_invalidate_fpregs_state(void)
+{
+ __this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
+{
+ fpu->last_cpu = -1;
+}
+
+static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
+{
+ return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+ __this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+ trace_x86_fpu_regs_deactivated(fpu);
+}
+
+static inline void fpregs_activate(struct fpu *fpu)
+{
+ __this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+ trace_x86_fpu_regs_activated(fpu);
+}
+
+/* Internal helper for switch_fpu_return() and signal frame setup */
+static inline void fpregs_restore_userregs(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+ int cpu = smp_processor_id();
+
+ if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER)))
+ return;
+
+ if (!fpregs_state_valid(fpu, cpu)) {
+ /*
+ * This restores _all_ xstate which has not been
+ * established yet.
+ *
+ * If PKRU is enabled, then the PKRU value is already
+ * correct because it was either set in switch_to() or in
+ * flush_thread(). So it is excluded because it might be
+ * not up to date in current->thread.fpu.xsave state.
+ *
+ * XFD state is handled in restore_fpregs_from_fpstate().
+ */
+ restore_fpregs_from_fpstate(fpu->fpstate, XFEATURE_MASK_FPSTATE);
+
+ fpregs_activate(fpu);
+ fpu->last_cpu = cpu;
+ }
+ clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+
+#endif
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
new file mode 100644
index 000000000..1d190761d
--- /dev/null
+++ b/arch/x86/kernel/fpu/core.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+#include <asm/fpu/api.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/sched.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/types.h>
+#include <asm/traps.h>
+#include <asm/irq_regs.h>
+
+#include <uapi/asm/kvm.h>
+
+#include <linux/hardirq.h>
+#include <linux/pkeys.h>
+#include <linux/vmalloc.h>
+
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/fpu.h>
+
+#ifdef CONFIG_X86_64
+DEFINE_STATIC_KEY_FALSE(__fpu_state_size_dynamic);
+DEFINE_PER_CPU(u64, xfd_state);
+#endif
+
+/* The FPU state configuration data for kernel and user space */
+struct fpu_state_config fpu_kernel_cfg __ro_after_init;
+struct fpu_state_config fpu_user_cfg __ro_after_init;
+
+/*
+ * Represents the initial FPU state. It's mostly (but not completely) zeroes,
+ * depending on the FPU hardware format:
+ */
+struct fpstate init_fpstate __ro_after_init;
+
+/* Track in-kernel FPU usage */
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+/*
+ * Track which context is using the FPU on the CPU:
+ */
+DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ */
+bool irq_fpu_usable(void)
+{
+ if (WARN_ON_ONCE(in_nmi()))
+ return false;
+
+ /* In kernel FPU usage already active? */
+ if (this_cpu_read(in_kernel_fpu))
+ return false;
+
+ /*
+ * When not in NMI or hard interrupt context, FPU can be used in:
+ *
+ * - Task context except from within fpregs_lock()'ed critical
+ * regions.
+ *
+ * - Soft interrupt processing context which cannot happen
+ * while in a fpregs_lock()'ed critical region.
+ */
+ if (!in_hardirq())
+ return true;
+
+ /*
+ * In hard interrupt context it's safe when soft interrupts
+ * are enabled, which means the interrupt did not hit in
+ * a fpregs_lock()'ed critical region.
+ */
+ return !softirq_count();
+}
+EXPORT_SYMBOL(irq_fpu_usable);
+
+/*
+ * Track AVX512 state use because it is known to slow the max clock
+ * speed of the core.
+ */
+static void update_avx_timestamp(struct fpu *fpu)
+{
+
+#define AVX512_TRACKING_MASK (XFEATURE_MASK_ZMM_Hi256 | XFEATURE_MASK_Hi16_ZMM)
+
+ if (fpu->fpstate->regs.xsave.header.xfeatures & AVX512_TRACKING_MASK)
+ fpu->avx512_timestamp = jiffies;
+}
+
+/*
+ * Save the FPU register state in fpu->fpstate->regs. The register state is
+ * preserved.
+ *
+ * Must be called with fpregs_lock() held.
+ *
+ * The legacy FNSAVE instruction clears all FPU state unconditionally, so
+ * register state has to be reloaded. That might be a pointless exercise
+ * when the FPU is going to be used by another task right after that. But
+ * this only affects 20+ years old 32bit systems and avoids conditionals all
+ * over the place.
+ *
+ * FXSAVE and all XSAVE variants preserve the FPU register state.
+ */
+void save_fpregs_to_fpstate(struct fpu *fpu)
+{
+ if (likely(use_xsave())) {
+ os_xsave(fpu->fpstate);
+ update_avx_timestamp(fpu);
+ return;
+ }
+
+ if (likely(use_fxsr())) {
+ fxsave(&fpu->fpstate->regs.fxsave);
+ return;
+ }
+
+ /*
+ * Legacy FPU register saving, FNSAVE always clears FPU registers,
+ * so we have to reload them from the memory state.
+ */
+ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->fpstate->regs.fsave));
+ frstor(&fpu->fpstate->regs.fsave);
+}
+
+void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask)
+{
+ /*
+ * AMD K7/K8 and later CPUs up to Zen don't save/restore
+ * FDP/FIP/FOP unless an exception is pending. Clear the x87 state
+ * here by setting it to fixed values. "m" is a random variable
+ * that should be in L1.
+ */
+ if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) {
+ asm volatile(
+ "fnclex\n\t"
+ "emms\n\t"
+ "fildl %P[addr]" /* set F?P to defined value */
+ : : [addr] "m" (fpstate));
+ }
+
+ if (use_xsave()) {
+ /*
+ * Dynamically enabled features are enabled in XCR0, but
+ * usage requires also that the corresponding bits in XFD
+ * are cleared. If the bits are set then using a related
+ * instruction will raise #NM. This allows to do the
+ * allocation of the larger FPU buffer lazy from #NM or if
+ * the task has no permission to kill it which would happen
+ * via #UD if the feature is disabled in XCR0.
+ *
+ * XFD state is following the same life time rules as
+ * XSTATE and to restore state correctly XFD has to be
+ * updated before XRSTORS otherwise the component would
+ * stay in or go into init state even if the bits are set
+ * in fpstate::regs::xsave::xfeatures.
+ */
+ xfd_update_state(fpstate);
+
+ /*
+ * Restoring state always needs to modify all features
+ * which are in @mask even if the current task cannot use
+ * extended features.
+ *
+ * So fpstate->xfeatures cannot be used here, because then
+ * a feature for which the task has no permission but was
+ * used by the previous task would not go into init state.
+ */
+ mask = fpu_kernel_cfg.max_features & mask;
+
+ os_xrstor(fpstate, mask);
+ } else {
+ if (use_fxsr())
+ fxrstor(&fpstate->regs.fxsave);
+ else
+ frstor(&fpstate->regs.fsave);
+ }
+}
+
+void fpu_reset_from_exception_fixup(void)
+{
+ restore_fpregs_from_fpstate(&init_fpstate, XFEATURE_MASK_FPSTATE);
+}
+
+#if IS_ENABLED(CONFIG_KVM)
+static void __fpstate_reset(struct fpstate *fpstate, u64 xfd);
+
+static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
+{
+ struct fpu_state_perm *fpuperm;
+ u64 perm;
+
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ spin_lock_irq(&current->sighand->siglock);
+ fpuperm = &current->group_leader->thread.fpu.guest_perm;
+ perm = fpuperm->__state_perm;
+
+ /* First fpstate allocation locks down permissions. */
+ WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED);
+
+ spin_unlock_irq(&current->sighand->siglock);
+
+ gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED;
+}
+
+bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
+{
+ struct fpstate *fpstate;
+ unsigned int size;
+
+ size = fpu_user_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+ fpstate = vzalloc(size);
+ if (!fpstate)
+ return false;
+
+ /* Leave xfd to 0 (the reset value defined by spec) */
+ __fpstate_reset(fpstate, 0);
+ fpstate_init_user(fpstate);
+ fpstate->is_valloc = true;
+ fpstate->is_guest = true;
+
+ gfpu->fpstate = fpstate;
+ gfpu->xfeatures = fpu_user_cfg.default_features;
+ gfpu->perm = fpu_user_cfg.default_features;
+
+ /*
+ * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state
+ * to userspace, even when XSAVE is unsupported, so that restoring FPU
+ * state on a different CPU that does support XSAVE can cleanly load
+ * the incoming state using its natural XSAVE. In other words, KVM's
+ * uABI size may be larger than this host's default size. Conversely,
+ * the default size should never be larger than KVM's base uABI size;
+ * all features that can expand the uABI size must be opt-in.
+ */
+ gfpu->uabi_size = sizeof(struct kvm_xsave);
+ if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size))
+ gfpu->uabi_size = fpu_user_cfg.default_size;
+
+ fpu_init_guest_permissions(gfpu);
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate);
+
+void fpu_free_guest_fpstate(struct fpu_guest *gfpu)
+{
+ struct fpstate *fps = gfpu->fpstate;
+
+ if (!fps)
+ return;
+
+ if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use))
+ return;
+
+ gfpu->fpstate = NULL;
+ vfree(fps);
+}
+EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate);
+
+/*
+ * fpu_enable_guest_xfd_features - Check xfeatures against guest perm and enable
+ * @guest_fpu: Pointer to the guest FPU container
+ * @xfeatures: Features requested by guest CPUID
+ *
+ * Enable all dynamic xfeatures according to guest perm and requested CPUID.
+ *
+ * Return: 0 on success, error code otherwise
+ */
+int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures)
+{
+ lockdep_assert_preemption_enabled();
+
+ /* Nothing to do if all requested features are already enabled. */
+ xfeatures &= ~guest_fpu->xfeatures;
+ if (!xfeatures)
+ return 0;
+
+ return __xfd_enable_feature(xfeatures, guest_fpu);
+}
+EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features);
+
+#ifdef CONFIG_X86_64
+void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd)
+{
+ fpregs_lock();
+ guest_fpu->fpstate->xfd = xfd;
+ if (guest_fpu->fpstate->in_use)
+ xfd_update_state(guest_fpu->fpstate);
+ fpregs_unlock();
+}
+EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
+
+/**
+ * fpu_sync_guest_vmexit_xfd_state - Synchronize XFD MSR and software state
+ *
+ * Must be invoked from KVM after a VMEXIT before enabling interrupts when
+ * XFD write emulation is disabled. This is required because the guest can
+ * freely modify XFD and the state at VMEXIT is not guaranteed to be the
+ * same as the state on VMENTER. So software state has to be udpated before
+ * any operation which depends on it can take place.
+ *
+ * Note: It can be invoked unconditionally even when write emulation is
+ * enabled for the price of a then pointless MSR read.
+ */
+void fpu_sync_guest_vmexit_xfd_state(void)
+{
+ struct fpstate *fps = current->thread.fpu.fpstate;
+
+ lockdep_assert_irqs_disabled();
+ if (fpu_state_size_dynamic()) {
+ rdmsrl(MSR_IA32_XFD, fps->xfd);
+ __this_cpu_write(xfd_state, fps->xfd);
+ }
+}
+EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
+#endif /* CONFIG_X86_64 */
+
+int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
+{
+ struct fpstate *guest_fps = guest_fpu->fpstate;
+ struct fpu *fpu = &current->thread.fpu;
+ struct fpstate *cur_fps = fpu->fpstate;
+
+ fpregs_lock();
+ if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD))
+ save_fpregs_to_fpstate(fpu);
+
+ /* Swap fpstate */
+ if (enter_guest) {
+ fpu->__task_fpstate = cur_fps;
+ fpu->fpstate = guest_fps;
+ guest_fps->in_use = true;
+ } else {
+ guest_fps->in_use = false;
+ fpu->fpstate = fpu->__task_fpstate;
+ fpu->__task_fpstate = NULL;
+ }
+
+ cur_fps = fpu->fpstate;
+
+ if (!cur_fps->is_confidential) {
+ /* Includes XFD update */
+ restore_fpregs_from_fpstate(cur_fps, XFEATURE_MASK_FPSTATE);
+ } else {
+ /*
+ * XSTATE is restored by firmware from encrypted
+ * memory. Make sure XFD state is correct while
+ * running with guest fpstate
+ */
+ xfd_update_state(cur_fps);
+ }
+
+ fpregs_mark_activate();
+ fpregs_unlock();
+ return 0;
+}
+EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
+
+void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+ unsigned int size, u64 xfeatures, u32 pkru)
+{
+ struct fpstate *kstate = gfpu->fpstate;
+ union fpregs_state *ustate = buf;
+ struct membuf mb = { .p = buf, .left = size };
+
+ if (cpu_feature_enabled(X86_FEATURE_XSAVE)) {
+ __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru,
+ XSTATE_COPY_XSAVE);
+ } else {
+ memcpy(&ustate->fxsave, &kstate->regs.fxsave,
+ sizeof(ustate->fxsave));
+ /* Make it restorable on a XSAVE enabled host */
+ ustate->xsave.header.xfeatures = XFEATURE_MASK_FPSSE;
+ }
+}
+EXPORT_SYMBOL_GPL(fpu_copy_guest_fpstate_to_uabi);
+
+int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
+ u64 xcr0, u32 *vpkru)
+{
+ struct fpstate *kstate = gfpu->fpstate;
+ const union fpregs_state *ustate = buf;
+
+ if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) {
+ if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE)
+ return -EINVAL;
+ if (ustate->fxsave.mxcsr & ~mxcsr_feature_mask)
+ return -EINVAL;
+ memcpy(&kstate->regs.fxsave, &ustate->fxsave, sizeof(ustate->fxsave));
+ return 0;
+ }
+
+ if (ustate->xsave.header.xfeatures & ~xcr0)
+ return -EINVAL;
+
+ /*
+ * Nullify @vpkru to preserve its current value if PKRU's bit isn't set
+ * in the header. KVM's odd ABI is to leave PKRU untouched in this
+ * case (all other components are eventually re-initialized).
+ */
+ if (!(ustate->xsave.header.xfeatures & XFEATURE_MASK_PKRU))
+ vpkru = NULL;
+
+ return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru);
+}
+EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
+#endif /* CONFIG_KVM */
+
+void kernel_fpu_begin_mask(unsigned int kfpu_mask)
+{
+ preempt_disable();
+
+ WARN_ON_FPU(!irq_fpu_usable());
+ WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
+
+ this_cpu_write(in_kernel_fpu, true);
+
+ if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+ !test_thread_flag(TIF_NEED_FPU_LOAD)) {
+ set_thread_flag(TIF_NEED_FPU_LOAD);
+ save_fpregs_to_fpstate(&current->thread.fpu);
+ }
+ __cpu_invalidate_fpregs_state();
+
+ /* Put sane initial values into the control registers. */
+ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM))
+ ldmxcsr(MXCSR_DEFAULT);
+
+ if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU))
+ asm volatile ("fninit");
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask);
+
+void kernel_fpu_end(void)
+{
+ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+
+ this_cpu_write(in_kernel_fpu, false);
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
+/*
+ * Sync the FPU register state to current's memory register state when the
+ * current task owns the FPU. The hardware register state is preserved.
+ */
+void fpu_sync_fpstate(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != &current->thread.fpu);
+
+ fpregs_lock();
+ trace_x86_fpu_before_save(fpu);
+
+ if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+ save_fpregs_to_fpstate(fpu);
+
+ trace_x86_fpu_after_save(fpu);
+ fpregs_unlock();
+}
+
+static inline unsigned int init_fpstate_copy_size(void)
+{
+ if (!use_xsave())
+ return fpu_kernel_cfg.default_size;
+
+ /* XSAVE(S) just needs the legacy and the xstate header part */
+ return sizeof(init_fpstate.regs.xsave);
+}
+
+static inline void fpstate_init_fxstate(struct fpstate *fpstate)
+{
+ fpstate->regs.fxsave.cwd = 0x37f;
+ fpstate->regs.fxsave.mxcsr = MXCSR_DEFAULT;
+}
+
+/*
+ * Legacy x87 fpstate state init:
+ */
+static inline void fpstate_init_fstate(struct fpstate *fpstate)
+{
+ fpstate->regs.fsave.cwd = 0xffff037fu;
+ fpstate->regs.fsave.swd = 0xffff0000u;
+ fpstate->regs.fsave.twd = 0xffffffffu;
+ fpstate->regs.fsave.fos = 0xffff0000u;
+}
+
+/*
+ * Used in two places:
+ * 1) Early boot to setup init_fpstate for non XSAVE systems
+ * 2) fpu_init_fpstate_user() which is invoked from KVM
+ */
+void fpstate_init_user(struct fpstate *fpstate)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
+ fpstate_init_soft(&fpstate->regs.soft);
+ return;
+ }
+
+ xstate_init_xcomp_bv(&fpstate->regs.xsave, fpstate->xfeatures);
+
+ if (cpu_feature_enabled(X86_FEATURE_FXSR))
+ fpstate_init_fxstate(fpstate);
+ else
+ fpstate_init_fstate(fpstate);
+}
+
+static void __fpstate_reset(struct fpstate *fpstate, u64 xfd)
+{
+ /* Initialize sizes and feature masks */
+ fpstate->size = fpu_kernel_cfg.default_size;
+ fpstate->user_size = fpu_user_cfg.default_size;
+ fpstate->xfeatures = fpu_kernel_cfg.default_features;
+ fpstate->user_xfeatures = fpu_user_cfg.default_features;
+ fpstate->xfd = xfd;
+}
+
+void fpstate_reset(struct fpu *fpu)
+{
+ /* Set the fpstate pointer to the default fpstate */
+ fpu->fpstate = &fpu->__fpstate;
+ __fpstate_reset(fpu->fpstate, init_fpstate.xfd);
+
+ /* Initialize the permission related info in fpu */
+ fpu->perm.__state_perm = fpu_kernel_cfg.default_features;
+ fpu->perm.__state_size = fpu_kernel_cfg.default_size;
+ fpu->perm.__user_state_size = fpu_user_cfg.default_size;
+ /* Same defaults for guests */
+ fpu->guest_perm = fpu->perm;
+}
+
+static inline void fpu_inherit_perms(struct fpu *dst_fpu)
+{
+ if (fpu_state_size_dynamic()) {
+ struct fpu *src_fpu = &current->group_leader->thread.fpu;
+
+ spin_lock_irq(&current->sighand->siglock);
+ /* Fork also inherits the permissions of the parent */
+ dst_fpu->perm = src_fpu->perm;
+ dst_fpu->guest_perm = src_fpu->guest_perm;
+ spin_unlock_irq(&current->sighand->siglock);
+ }
+}
+
+/* Clone current's FPU state on fork */
+int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal)
+{
+ struct fpu *src_fpu = &current->thread.fpu;
+ struct fpu *dst_fpu = &dst->thread.fpu;
+
+ /* The new task's FPU state cannot be valid in the hardware. */
+ dst_fpu->last_cpu = -1;
+
+ fpstate_reset(dst_fpu);
+
+ if (!cpu_feature_enabled(X86_FEATURE_FPU))
+ return 0;
+
+ /*
+ * Enforce reload for user space tasks and prevent kernel threads
+ * from trying to save the FPU registers on context switch.
+ */
+ set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD);
+
+ /*
+ * No FPU state inheritance for kernel threads and IO
+ * worker threads.
+ */
+ if (minimal) {
+ /* Clear out the minimal state */
+ memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs,
+ init_fpstate_copy_size());
+ return 0;
+ }
+
+ /*
+ * If a new feature is added, ensure all dynamic features are
+ * caller-saved from here!
+ */
+ BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA);
+
+ /*
+ * Save the default portion of the current FPU state into the
+ * clone. Assume all dynamic features to be defined as caller-
+ * saved, which enables skipping both the expansion of fpstate
+ * and the copying of any dynamic state.
+ *
+ * Do not use memcpy() when TIF_NEED_FPU_LOAD is set because
+ * copying is not valid when current uses non-default states.
+ */
+ fpregs_lock();
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ fpregs_restore_userregs();
+ save_fpregs_to_fpstate(dst_fpu);
+ fpregs_unlock();
+ if (!(clone_flags & CLONE_THREAD))
+ fpu_inherit_perms(dst_fpu);
+
+ /*
+ * Children never inherit PASID state.
+ * Force it to have its init value:
+ */
+ if (use_xsave())
+ dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID;
+
+ trace_x86_fpu_copy_src(src_fpu);
+ trace_x86_fpu_copy_dst(dst_fpu);
+
+ return 0;
+}
+
+/*
+ * Whitelist the FPU register state embedded into task_struct for hardened
+ * usercopy.
+ */
+void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
+{
+ *offset = offsetof(struct thread_struct, fpu.__fpstate.regs);
+ *size = fpu_kernel_cfg.default_size;
+}
+
+/*
+ * Drops current FPU state: deactivates the fpregs and
+ * the fpstate. NOTE: it still leaves previous contents
+ * in the fpregs in the eager-FPU case.
+ *
+ * This function can be used in cases where we know that
+ * a state-restore is coming: either an explicit one,
+ * or a reschedule.
+ */
+void fpu__drop(struct fpu *fpu)
+{
+ preempt_disable();
+
+ if (fpu == &current->thread.fpu) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ fpregs_deactivate(fpu);
+ }
+
+ trace_x86_fpu_dropped(fpu);
+
+ preempt_enable();
+}
+
+/*
+ * Clear FPU registers by setting them up from the init fpstate.
+ * Caller must do fpregs_[un]lock() around it.
+ */
+static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
+{
+ if (use_xsave())
+ os_xrstor(&init_fpstate, features_mask);
+ else if (use_fxsr())
+ fxrstor(&init_fpstate.regs.fxsave);
+ else
+ frstor(&init_fpstate.regs.fsave);
+
+ pkru_write_default();
+}
+
+/*
+ * Reset current->fpu memory state to the init values.
+ */
+static void fpu_reset_fpregs(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+
+ fpregs_lock();
+ __fpu_invalidate_fpregs_state(fpu);
+ /*
+ * This does not change the actual hardware registers. It just
+ * resets the memory image and sets TIF_NEED_FPU_LOAD so a
+ * subsequent return to usermode will reload the registers from the
+ * task's memory image.
+ *
+ * Do not use fpstate_init() here. Just copy init_fpstate which has
+ * the correct content already except for PKRU.
+ *
+ * PKRU handling does not rely on the xstate when restoring for
+ * user space as PKRU is eagerly written in switch_to() and
+ * flush_thread().
+ */
+ memcpy(&fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size());
+ set_thread_flag(TIF_NEED_FPU_LOAD);
+ fpregs_unlock();
+}
+
+/*
+ * Reset current's user FPU states to the init states. current's
+ * supervisor states, if any, are not modified by this function. The
+ * caller guarantees that the XSTATE header in memory is intact.
+ */
+void fpu__clear_user_states(struct fpu *fpu)
+{
+ WARN_ON_FPU(fpu != &current->thread.fpu);
+
+ fpregs_lock();
+ if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
+ fpu_reset_fpregs();
+ fpregs_unlock();
+ return;
+ }
+
+ /*
+ * Ensure that current's supervisor states are loaded into their
+ * corresponding registers.
+ */
+ if (xfeatures_mask_supervisor() &&
+ !fpregs_state_valid(fpu, smp_processor_id()))
+ os_xrstor_supervisor(fpu->fpstate);
+
+ /* Reset user states in registers. */
+ restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE);
+
+ /*
+ * Now all FPU registers have their desired values. Inform the FPU
+ * state machine that current's FPU registers are in the hardware
+ * registers. The memory image does not need to be updated because
+ * any operation relying on it has to save the registers first when
+ * current's FPU is marked active.
+ */
+ fpregs_mark_activate();
+ fpregs_unlock();
+}
+
+void fpu_flush_thread(void)
+{
+ fpstate_reset(&current->thread.fpu);
+ fpu_reset_fpregs();
+}
+/*
+ * Load FPU context before returning to userspace.
+ */
+void switch_fpu_return(void)
+{
+ if (!static_cpu_has(X86_FEATURE_FPU))
+ return;
+
+ fpregs_restore_userregs();
+}
+EXPORT_SYMBOL_GPL(switch_fpu_return);
+
+#ifdef CONFIG_X86_DEBUG_FPU
+/*
+ * If current FPU state according to its tracking (loaded FPU context on this
+ * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is
+ * loaded on return to userland.
+ */
+void fpregs_assert_state_consistent(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ return;
+
+ WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id()));
+}
+EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent);
+#endif
+
+void fpregs_mark_activate(void)
+{
+ struct fpu *fpu = &current->thread.fpu;
+
+ fpregs_activate(fpu);
+ fpu->last_cpu = smp_processor_id();
+ clear_thread_flag(TIF_NEED_FPU_LOAD);
+}
+
+/*
+ * x87 math exception handling:
+ */
+
+int fpu__exception_code(struct fpu *fpu, int trap_nr)
+{
+ int err;
+
+ if (trap_nr == X86_TRAP_MF) {
+ unsigned short cwd, swd;
+ /*
+ * (~cwd & swd) will mask out exceptions that are not set to unmasked
+ * status. 0x3f is the exception bits in these regs, 0x200 is the
+ * C1 reg you need in case of a stack fault, 0x040 is the stack
+ * fault bit. We should only be taking one exception at a time,
+ * so if this combination doesn't produce any single exception,
+ * then we have a bad program that isn't synchronizing its FPU usage
+ * and it will suffer the consequences since we won't be able to
+ * fully reproduce the context of the exception.
+ */
+ if (boot_cpu_has(X86_FEATURE_FXSR)) {
+ cwd = fpu->fpstate->regs.fxsave.cwd;
+ swd = fpu->fpstate->regs.fxsave.swd;
+ } else {
+ cwd = (unsigned short)fpu->fpstate->regs.fsave.cwd;
+ swd = (unsigned short)fpu->fpstate->regs.fsave.swd;
+ }
+
+ err = swd & ~cwd;
+ } else {
+ /*
+ * The SIMD FPU exceptions are handled a little differently, as there
+ * is only a single status/control register. Thus, to determine which
+ * unmasked exception was caught we must mask the exception mask bits
+ * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+ */
+ unsigned short mxcsr = MXCSR_DEFAULT;
+
+ if (boot_cpu_has(X86_FEATURE_XMM))
+ mxcsr = fpu->fpstate->regs.fxsave.mxcsr;
+
+ err = ~(mxcsr >> 7) & mxcsr;
+ }
+
+ if (err & 0x001) { /* Invalid op */
+ /*
+ * swd & 0x240 == 0x040: Stack Underflow
+ * swd & 0x240 == 0x240: Stack Overflow
+ * User must clear the SF bit (0x40) if set
+ */
+ return FPE_FLTINV;
+ } else if (err & 0x004) { /* Divide by Zero */
+ return FPE_FLTDIV;
+ } else if (err & 0x008) { /* Overflow */
+ return FPE_FLTOVF;
+ } else if (err & 0x012) { /* Denormal, Underflow */
+ return FPE_FLTUND;
+ } else if (err & 0x020) { /* Precision */
+ return FPE_FLTRES;
+ }
+
+ /*
+ * If we're using IRQ 13, or supposedly even some trap
+ * X86_TRAP_MF implementations, it's possible
+ * we get a spurious trap, which is not an error.
+ */
+ return 0;
+}
+
+/*
+ * Initialize register state that may prevent from entering low-power idle.
+ * This function will be invoked from the cpuidle driver only when needed.
+ */
+noinstr void fpu_idle_fpregs(void)
+{
+ /* Note: AMX_TILE being enabled implies XGETBV1 support */
+ if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) &&
+ (xfeatures_in_use() & XFEATURE_MASK_XTILE)) {
+ tile_release();
+ __this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+ }
+}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
new file mode 100644
index 000000000..998a08f17
--- /dev/null
+++ b/arch/x86/kernel/fpu/init.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * x86 FPU boot time init code:
+ */
+#include <asm/fpu/api.h>
+#include <asm/tlbflush.h>
+#include <asm/setup.h>
+
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/init.h>
+
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
+
+/*
+ * Initialize the registers found in all CPUs, CR0 and CR4:
+ */
+static void fpu__init_cpu_generic(void)
+{
+ unsigned long cr0;
+ unsigned long cr4_mask = 0;
+
+ if (boot_cpu_has(X86_FEATURE_FXSR))
+ cr4_mask |= X86_CR4_OSFXSR;
+ if (boot_cpu_has(X86_FEATURE_XMM))
+ cr4_mask |= X86_CR4_OSXMMEXCPT;
+ if (cr4_mask)
+ cr4_set_bits(cr4_mask);
+
+ cr0 = read_cr0();
+ cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+ if (!boot_cpu_has(X86_FEATURE_FPU))
+ cr0 |= X86_CR0_EM;
+ write_cr0(cr0);
+
+ /* Flush out any pending x87 state: */
+#ifdef CONFIG_MATH_EMULATION
+ if (!boot_cpu_has(X86_FEATURE_FPU))
+ fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+ else
+#endif
+ asm volatile ("fninit");
+}
+
+/*
+ * Enable all supported FPU features. Called when a CPU is brought online:
+ */
+void fpu__init_cpu(void)
+{
+ fpu__init_cpu_generic();
+ fpu__init_cpu_xstate();
+}
+
+static bool __init fpu__probe_without_cpuid(void)
+{
+ unsigned long cr0;
+ u16 fsw, fcw;
+
+ fsw = fcw = 0xffff;
+
+ cr0 = read_cr0();
+ cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
+ write_cr0(cr0);
+
+ asm volatile("fninit ; fnstsw %0 ; fnstcw %1" : "+m" (fsw), "+m" (fcw));
+
+ pr_info("x86/fpu: Probing for FPU: FSW=0x%04hx FCW=0x%04hx\n", fsw, fcw);
+
+ return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+static void __init fpu__init_system_early_generic(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_CPUID) &&
+ !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
+ if (fpu__probe_without_cpuid())
+ setup_force_cpu_cap(X86_FEATURE_FPU);
+ else
+ setup_clear_cpu_cap(X86_FEATURE_FPU);
+ }
+
+#ifndef CONFIG_MATH_EMULATION
+ if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_FPU)) {
+ pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
+ for (;;)
+ asm volatile("hlt");
+ }
+#endif
+}
+
+/*
+ * Boot time FPU feature detection code:
+ */
+unsigned int mxcsr_feature_mask __ro_after_init = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
+
+static void __init fpu__init_system_mxcsr(void)
+{
+ unsigned int mask = 0;
+
+ if (boot_cpu_has(X86_FEATURE_FXSR)) {
+ /* Static because GCC does not get 16-byte stack alignment right: */
+ static struct fxregs_state fxregs __initdata;
+
+ asm volatile("fxsave %0" : "+m" (fxregs));
+
+ mask = fxregs.mxcsr_mask;
+
+ /*
+ * If zero then use the default features mask,
+ * which has all features set, except the
+ * denormals-are-zero feature bit:
+ */
+ if (mask == 0)
+ mask = 0x0000ffbf;
+ }
+ mxcsr_feature_mask &= mask;
+}
+
+/*
+ * Once per bootup FPU initialization sequences that will run on most x86 CPUs:
+ */
+static void __init fpu__init_system_generic(void)
+{
+ /*
+ * Set up the legacy init FPU context. Will be updated when the
+ * CPU supports XSAVE[S].
+ */
+ fpstate_init_user(&init_fpstate);
+
+ fpu__init_system_mxcsr();
+}
+
+/*
+ * Enforce that 'MEMBER' is the last field of 'TYPE'.
+ *
+ * Align the computed size with alignment of the TYPE,
+ * because that's how C aligns structs.
+ */
+#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
+ BUILD_BUG_ON(sizeof(TYPE) != \
+ ALIGN(offsetofend(TYPE, MEMBER), _Alignof(TYPE)))
+
+/*
+ * We append the 'struct fpu' to the task_struct:
+ */
+static void __init fpu__init_task_struct_size(void)
+{
+ int task_size = sizeof(struct task_struct);
+
+ /*
+ * Subtract off the static size of the register state.
+ * It potentially has a bunch of padding.
+ */
+ task_size -= sizeof(current->thread.fpu.__fpstate.regs);
+
+ /*
+ * Add back the dynamically-calculated register state
+ * size.
+ */
+ task_size += fpu_kernel_cfg.default_size;
+
+ /*
+ * We dynamically size 'struct fpu', so we require that
+ * it be at the end of 'thread_struct' and that
+ * 'thread_struct' be at the end of 'task_struct'. If
+ * you hit a compile error here, check the structure to
+ * see if something got added to the end.
+ */
+ CHECK_MEMBER_AT_END_OF(struct fpu, __fpstate);
+ CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
+ CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
+
+ arch_task_struct_size = task_size;
+}
+
+/*
+ * Set up the user and kernel xstate sizes based on the legacy FPU context size.
+ *
+ * We set this up first, and later it will be overwritten by
+ * fpu__init_system_xstate() if the CPU knows about xstates.
+ */
+static void __init fpu__init_system_xstate_size_legacy(void)
+{
+ unsigned int size;
+
+ /*
+ * Note that the size configuration might be overwritten later
+ * during fpu__init_system_xstate().
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
+ size = sizeof(struct swregs_state);
+ } else if (cpu_feature_enabled(X86_FEATURE_FXSR)) {
+ size = sizeof(struct fxregs_state);
+ fpu_user_cfg.legacy_features = XFEATURE_MASK_FPSSE;
+ } else {
+ size = sizeof(struct fregs_state);
+ fpu_user_cfg.legacy_features = XFEATURE_MASK_FP;
+ }
+
+ fpu_kernel_cfg.max_size = size;
+ fpu_kernel_cfg.default_size = size;
+ fpu_user_cfg.max_size = size;
+ fpu_user_cfg.default_size = size;
+ fpstate_reset(&current->thread.fpu);
+}
+
+/*
+ * Called on the boot CPU once per system bootup, to set up the initial
+ * FPU state that is later cloned into all processes:
+ */
+void __init fpu__init_system(void)
+{
+ fpstate_reset(&current->thread.fpu);
+ fpu__init_system_early_generic();
+
+ /*
+ * The FPU has to be operational for some of the
+ * later FPU init activities:
+ */
+ fpu__init_cpu();
+
+ fpu__init_system_generic();
+ fpu__init_system_xstate_size_legacy();
+ fpu__init_system_xstate(fpu_kernel_cfg.max_size);
+ fpu__init_task_struct_size();
+}
diff --git a/arch/x86/kernel/fpu/internal.h b/arch/x86/kernel/fpu/internal.h
new file mode 100644
index 000000000..dbdb31f55
--- /dev/null
+++ b/arch/x86/kernel/fpu/internal.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_INTERNAL_H
+#define __X86_KERNEL_FPU_INTERNAL_H
+
+extern struct fpstate init_fpstate;
+
+/* CPU feature check wrappers */
+static __always_inline __pure bool use_xsave(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_FXSR);
+}
+
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/* Used in init.c */
+extern void fpstate_init_user(struct fpstate *fpstate);
+extern void fpstate_reset(struct fpu *fpu);
+
+#endif
diff --git a/arch/x86/kernel/fpu/legacy.h b/arch/x86/kernel/fpu/legacy.h
new file mode 100644
index 000000000..098f367bb
--- /dev/null
+++ b/arch/x86/kernel/fpu/legacy.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_LEGACY_H
+#define __X86_KERNEL_FPU_LEGACY_H
+
+#include <asm/fpu/types.h>
+
+extern unsigned int mxcsr_feature_mask;
+
+static inline void ldmxcsr(u32 mxcsr)
+{
+ asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
+/*
+ * Returns 0 on success or the trap number when the operation raises an
+ * exception.
+ */
+#define user_insn(insn, output, input...) \
+({ \
+ int err; \
+ \
+ might_fault(); \
+ \
+ asm volatile(ASM_STAC "\n" \
+ "1: " #insn "\n" \
+ "2: " ASM_CLAC "\n" \
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \
+ : [err] "=a" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define kernel_insn_err(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[err]) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define kernel_insn(insn, output, input...) \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FPU_RESTORE) \
+ : output : input)
+
+static inline int fnsave_to_user_sigframe(struct fregs_state __user *fx)
+{
+ return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int fxsave_to_user_sigframe(struct fxregs_state __user *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+ else
+ return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+}
+
+static inline void fxrstor(struct fxregs_state *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else
+ kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int fxrstor_safe(struct fxregs_state *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else
+ return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int fxrstor_from_user_sigframe(struct fxregs_state __user *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else
+ return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void frstor(struct fregs_state *fx)
+{
+ kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int frstor_safe(struct fregs_state *fx)
+{
+ return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int frstor_from_user_sigframe(struct fregs_state __user *fx)
+{
+ return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void fxsave(struct fxregs_state *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx));
+ else
+ asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx));
+}
+
+#endif
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
new file mode 100644
index 000000000..6d056b68f
--- /dev/null
+++ b/arch/x86/kernel/fpu/regset.c
@@ -0,0 +1,386 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FPU register's regset abstraction, for ptrace, core dumps, etc.
+ */
+#include <linux/sched/task_stack.h>
+#include <linux/vmalloc.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
+
+/*
+ * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
+ * as the "regset->n" for the xstate regset will be updated based on the feature
+ * capabilities supported by the xsave.
+ */
+int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+ return regset->n;
+}
+
+int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (boot_cpu_has(X86_FEATURE_FXSR))
+ return regset->n;
+ else
+ return 0;
+}
+
+/*
+ * The regset get() functions are invoked from:
+ *
+ * - coredump to dump the current task's fpstate. If the current task
+ * owns the FPU then the memory state has to be synchronized and the
+ * FPU register state preserved. Otherwise fpstate is already in sync.
+ *
+ * - ptrace to dump fpstate of a stopped task, in which case the registers
+ * have already been saved to fpstate on context switch.
+ */
+static void sync_fpstate(struct fpu *fpu)
+{
+ if (fpu == &current->thread.fpu)
+ fpu_sync_fpstate(fpu);
+}
+
+/*
+ * Invalidate cached FPU registers before modifying the stopped target
+ * task's fpstate.
+ *
+ * This forces the target task on resume to restore the FPU registers from
+ * modified fpstate. Otherwise the task might skip the restore and operate
+ * with the cached FPU registers which discards the modifications.
+ */
+static void fpu_force_restore(struct fpu *fpu)
+{
+ /*
+ * Only stopped child tasks can be used to modify the FPU
+ * state in the fpstate buffer:
+ */
+ WARN_ON_FPU(fpu == &current->thread.fpu);
+
+ __fpu_invalidate_fpregs_state(fpu);
+}
+
+int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ struct fpu *fpu = &target->thread.fpu;
+
+ if (!cpu_feature_enabled(X86_FEATURE_FXSR))
+ return -ENODEV;
+
+ sync_fpstate(fpu);
+
+ if (!use_xsave()) {
+ return membuf_write(&to, &fpu->fpstate->regs.fxsave,
+ sizeof(fpu->fpstate->regs.fxsave));
+ }
+
+ copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_FX);
+ return 0;
+}
+
+int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct fxregs_state newstate;
+ int ret;
+
+ if (!cpu_feature_enabled(X86_FEATURE_FXSR))
+ return -ENODEV;
+
+ /* No funny business with partial or oversized writes is permitted. */
+ if (pos != 0 || count != sizeof(newstate))
+ return -EINVAL;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
+ if (ret)
+ return ret;
+
+ /* Do not allow an invalid MXCSR value. */
+ if (newstate.mxcsr & ~mxcsr_feature_mask)
+ return -EINVAL;
+
+ fpu_force_restore(fpu);
+
+ /* Copy the state */
+ memcpy(&fpu->fpstate->regs.fxsave, &newstate, sizeof(newstate));
+
+ /* Clear xmm8..15 for 32-bit callers */
+ BUILD_BUG_ON(sizeof(fpu->__fpstate.regs.fxsave.xmm_space) != 16 * 16);
+ if (in_ia32_syscall())
+ memset(&fpu->fpstate->regs.fxsave.xmm_space[8*4], 0, 8 * 16);
+
+ /* Mark FP and SSE as in use when XSAVE is enabled */
+ if (use_xsave())
+ fpu->fpstate->regs.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
+
+ return 0;
+}
+
+int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_XSAVE))
+ return -ENODEV;
+
+ sync_fpstate(&target->thread.fpu);
+
+ copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_XSAVE);
+ return 0;
+}
+
+int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct xregs_state *tmpbuf = NULL;
+ int ret;
+
+ if (!cpu_feature_enabled(X86_FEATURE_XSAVE))
+ return -ENODEV;
+
+ /*
+ * A whole standard-format XSAVE buffer is needed:
+ */
+ if (pos != 0 || count != fpu_user_cfg.max_size)
+ return -EFAULT;
+
+ if (!kbuf) {
+ tmpbuf = vmalloc(count);
+ if (!tmpbuf)
+ return -ENOMEM;
+
+ if (copy_from_user(tmpbuf, ubuf, count)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+ fpu_force_restore(fpu);
+ ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf, &target->thread.pkru);
+
+out:
+ vfree(tmpbuf);
+ return ret;
+}
+
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+ unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+ /* Transform each pair of bits into 01 (valid) or 00 (empty) */
+ tmp = ~twd;
+ tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+ /* and move the valid bits to the lower byte. */
+ tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+ tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+ tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+
+ return tmp;
+}
+
+#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16)
+#define FP_EXP_TAG_VALID 0
+#define FP_EXP_TAG_ZERO 1
+#define FP_EXP_TAG_SPECIAL 2
+#define FP_EXP_TAG_EMPTY 3
+
+static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave)
+{
+ struct _fpxreg *st;
+ u32 tos = (fxsave->swd >> 11) & 7;
+ u32 twd = (unsigned long) fxsave->twd;
+ u32 tag;
+ u32 ret = 0xffff0000u;
+ int i;
+
+ for (i = 0; i < 8; i++, twd >>= 1) {
+ if (twd & 0x1) {
+ st = FPREG_ADDR(fxsave, (i - tos) & 7);
+
+ switch (st->exponent & 0x7fff) {
+ case 0x7fff:
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ case 0x0000:
+ if (!st->significand[0] &&
+ !st->significand[1] &&
+ !st->significand[2] &&
+ !st->significand[3])
+ tag = FP_EXP_TAG_ZERO;
+ else
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ default:
+ if (st->significand[3] & 0x8000)
+ tag = FP_EXP_TAG_VALID;
+ else
+ tag = FP_EXP_TAG_SPECIAL;
+ break;
+ }
+ } else {
+ tag = FP_EXP_TAG_EMPTY;
+ }
+ ret |= tag << (2 * i);
+ }
+ return ret;
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+static void __convert_from_fxsr(struct user_i387_ia32_struct *env,
+ struct task_struct *tsk,
+ struct fxregs_state *fxsave)
+{
+ struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
+ struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
+ int i;
+
+ env->cwd = fxsave->cwd | 0xffff0000u;
+ env->swd = fxsave->swd | 0xffff0000u;
+ env->twd = twd_fxsr_to_i387(fxsave);
+
+#ifdef CONFIG_X86_64
+ env->fip = fxsave->rip;
+ env->foo = fxsave->rdp;
+ /*
+ * should be actually ds/cs at fpu exception time, but
+ * that information is not available in 64bit mode.
+ */
+ env->fcs = task_pt_regs(tsk)->cs;
+ if (tsk == current) {
+ savesegment(ds, env->fos);
+ } else {
+ env->fos = tsk->thread.ds;
+ }
+ env->fos |= 0xffff0000;
+#else
+ env->fip = fxsave->fip;
+ env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
+ env->foo = fxsave->foo;
+ env->fos = fxsave->fos;
+#endif
+
+ for (i = 0; i < 8; ++i)
+ memcpy(&to[i], &from[i], sizeof(to[0]));
+}
+
+void
+convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
+{
+ __convert_from_fxsr(env, tsk, &tsk->thread.fpu.fpstate->regs.fxsave);
+}
+
+void convert_to_fxsr(struct fxregs_state *fxsave,
+ const struct user_i387_ia32_struct *env)
+
+{
+ struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
+ struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
+ int i;
+
+ fxsave->cwd = env->cwd;
+ fxsave->swd = env->swd;
+ fxsave->twd = twd_i387_to_fxsr(env->twd);
+ fxsave->fop = (u16) ((u32) env->fcs >> 16);
+#ifdef CONFIG_X86_64
+ fxsave->rip = env->fip;
+ fxsave->rdp = env->foo;
+ /* cs and ds ignored */
+#else
+ fxsave->fip = env->fip;
+ fxsave->fcs = (env->fcs & 0xffff);
+ fxsave->foo = env->foo;
+ fxsave->fos = env->fos;
+#endif
+
+ for (i = 0; i < 8; ++i)
+ memcpy(&to[i], &from[i], sizeof(from[0]));
+}
+
+int fpregs_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct user_i387_ia32_struct env;
+ struct fxregs_state fxsave, *fx;
+
+ sync_fpstate(fpu);
+
+ if (!cpu_feature_enabled(X86_FEATURE_FPU))
+ return fpregs_soft_get(target, regset, to);
+
+ if (!cpu_feature_enabled(X86_FEATURE_FXSR)) {
+ return membuf_write(&to, &fpu->fpstate->regs.fsave,
+ sizeof(struct fregs_state));
+ }
+
+ if (use_xsave()) {
+ struct membuf mb = { .p = &fxsave, .left = sizeof(fxsave) };
+
+ /* Handle init state optimized xstate correctly */
+ copy_xstate_to_uabi_buf(mb, target, XSTATE_COPY_FP);
+ fx = &fxsave;
+ } else {
+ fx = &fpu->fpstate->regs.fxsave;
+ }
+
+ __convert_from_fxsr(&env, target, fx);
+ return membuf_write(&to, &env, sizeof(env));
+}
+
+int fpregs_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct fpu *fpu = &target->thread.fpu;
+ struct user_i387_ia32_struct env;
+ int ret;
+
+ /* No funny business with partial or oversized writes is permitted. */
+ if (pos != 0 || count != sizeof(struct user_i387_ia32_struct))
+ return -EINVAL;
+
+ if (!cpu_feature_enabled(X86_FEATURE_FPU))
+ return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+ if (ret)
+ return ret;
+
+ fpu_force_restore(fpu);
+
+ if (cpu_feature_enabled(X86_FEATURE_FXSR))
+ convert_to_fxsr(&fpu->fpstate->regs.fxsave, &env);
+ else
+ memcpy(&fpu->fpstate->regs.fsave, &env, sizeof(env));
+
+ /*
+ * Update the header bit in the xsave header, indicating the
+ * presence of FP.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XSAVE))
+ fpu->fpstate->regs.xsave.header.xfeatures |= XFEATURE_MASK_FP;
+
+ return 0;
+}
+
+#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
new file mode 100644
index 000000000..558076dbd
--- /dev/null
+++ b/arch/x86/kernel/fpu/signal.c
@@ -0,0 +1,542 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FPU signal frame handling routines.
+ */
+
+#include <linux/compat.h>
+#include <linux/cpu.h>
+#include <linux/pagemap.h>
+
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/xstate.h>
+
+#include <asm/sigframe.h>
+#include <asm/trapnr.h>
+#include <asm/trace/fpu.h>
+
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
+
+/*
+ * Check for the presence of extended state information in the
+ * user fpstate pointer in the sigcontext.
+ */
+static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
+ struct _fpx_sw_bytes *fx_sw)
+{
+ int min_xstate_size = sizeof(struct fxregs_state) +
+ sizeof(struct xstate_header);
+ void __user *fpstate = fxbuf;
+ unsigned int magic2;
+
+ if (__copy_from_user(fx_sw, &fxbuf->sw_reserved[0], sizeof(*fx_sw)))
+ return false;
+
+ /* Check for the first magic field and other error scenarios. */
+ if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+ fx_sw->xstate_size < min_xstate_size ||
+ fx_sw->xstate_size > current->thread.fpu.fpstate->user_size ||
+ fx_sw->xstate_size > fx_sw->extended_size)
+ goto setfx;
+
+ /*
+ * Check for the presence of second magic word at the end of memory
+ * layout. This detects the case where the user just copied the legacy
+ * fpstate layout with out copying the extended state information
+ * in the memory layout.
+ */
+ if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)))
+ return false;
+
+ if (likely(magic2 == FP_XSTATE_MAGIC2))
+ return true;
+setfx:
+ trace_x86_fpu_xstate_check_failed(&current->thread.fpu);
+
+ /* Set the parameters for fx only state */
+ fx_sw->magic1 = 0;
+ fx_sw->xstate_size = sizeof(struct fxregs_state);
+ fx_sw->xfeatures = XFEATURE_MASK_FPSSE;
+ return true;
+}
+
+/*
+ * Signal frame handlers.
+ */
+static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+ if (use_fxsr()) {
+ struct xregs_state *xsave = &tsk->thread.fpu.fpstate->regs.xsave;
+ struct user_i387_ia32_struct env;
+ struct _fpstate_32 __user *fp = buf;
+
+ fpregs_lock();
+ if (!test_thread_flag(TIF_NEED_FPU_LOAD))
+ fxsave(&tsk->thread.fpu.fpstate->regs.fxsave);
+ fpregs_unlock();
+
+ convert_from_fxsr(&env, tsk);
+
+ if (__copy_to_user(buf, &env, sizeof(env)) ||
+ __put_user(xsave->i387.swd, &fp->status) ||
+ __put_user(X86_FXSR_MAGIC, &fp->magic))
+ return false;
+ } else {
+ struct fregs_state __user *fp = buf;
+ u32 swd;
+
+ if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
+ return false;
+ }
+
+ return true;
+}
+
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed to by the fpstate pointer in the sigcontext.
+ * This is saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+static inline void save_sw_bytes(struct _fpx_sw_bytes *sw_bytes, bool ia32_frame,
+ struct fpstate *fpstate)
+{
+ sw_bytes->magic1 = FP_XSTATE_MAGIC1;
+ sw_bytes->extended_size = fpstate->user_size + FP_XSTATE_MAGIC2_SIZE;
+ sw_bytes->xfeatures = fpstate->user_xfeatures;
+ sw_bytes->xstate_size = fpstate->user_size;
+
+ if (ia32_frame)
+ sw_bytes->extended_size += sizeof(struct fregs_state);
+}
+
+static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
+ struct fpstate *fpstate)
+{
+ struct xregs_state __user *x = buf;
+ struct _fpx_sw_bytes sw_bytes = {};
+ u32 xfeatures;
+ int err;
+
+ /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+ save_sw_bytes(&sw_bytes, ia32_frame, fpstate);
+ err = __copy_to_user(&x->i387.sw_reserved, &sw_bytes, sizeof(sw_bytes));
+
+ if (!use_xsave())
+ return !err;
+
+ err |= __put_user(FP_XSTATE_MAGIC2,
+ (__u32 __user *)(buf + fpstate->user_size));
+
+ /*
+ * Read the xfeatures which we copied (directly from the cpu or
+ * from the state in task struct) to the user buffers.
+ */
+ err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
+
+ /*
+ * For legacy compatible, we always set FP/SSE bits in the bit
+ * vector while saving the state to the user context. This will
+ * enable us capturing any changes(during sigreturn) to
+ * the FP/SSE bits by the legacy applications which don't touch
+ * xfeatures in the xsave header.
+ *
+ * xsave aware apps can change the xfeatures in the xsave
+ * header as well as change any contents in the memory layout.
+ * xrestore as part of sigreturn will capture all the changes.
+ */
+ xfeatures |= XFEATURE_MASK_FPSSE;
+
+ err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
+
+ return !err;
+}
+
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+{
+ if (use_xsave())
+ return xsave_to_user_sigframe(buf);
+ if (use_fxsr())
+ return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);
+ else
+ return fnsave_to_user_sigframe((struct fregs_state __user *) buf);
+}
+
+/*
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ * state is copied.
+ * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ * buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ * buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * Save it directly to the user frame with disabled page fault handler. If
+ * that faults, try to clear the frame which handles the page fault.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
+ */
+bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+{
+ struct task_struct *tsk = current;
+ struct fpstate *fpstate = tsk->thread.fpu.fpstate;
+ bool ia32_fxstate = (buf != buf_fx);
+ int ret;
+
+ ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
+ IS_ENABLED(CONFIG_IA32_EMULATION));
+
+ if (!static_cpu_has(X86_FEATURE_FPU)) {
+ struct user_i387_ia32_struct fp;
+
+ fpregs_soft_get(current, NULL, (struct membuf){.p = &fp,
+ .left = sizeof(fp)});
+ return !copy_to_user(buf, &fp, sizeof(fp));
+ }
+
+ if (!access_ok(buf, size))
+ return false;
+
+ if (use_xsave()) {
+ struct xregs_state __user *xbuf = buf_fx;
+
+ /*
+ * Clear the xsave header first, so that reserved fields are
+ * initialized to zero.
+ */
+ if (__clear_user(&xbuf->header, sizeof(xbuf->header)))
+ return false;
+ }
+retry:
+ /*
+ * Load the FPU registers if they are not valid for the current task.
+ * With a valid FPU state we can attempt to save the state directly to
+ * userland's stack frame which will likely succeed. If it does not,
+ * resolve the fault in the user memory and try again.
+ */
+ fpregs_lock();
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ fpregs_restore_userregs();
+
+ pagefault_disable();
+ ret = copy_fpregs_to_sigframe(buf_fx);
+ pagefault_enable();
+ fpregs_unlock();
+
+ if (ret) {
+ if (!__clear_user(buf_fx, fpstate->user_size))
+ goto retry;
+ return false;
+ }
+
+ /* Save the fsave header for the 32-bit frames. */
+ if ((ia32_fxstate || !use_fxsr()) && !save_fsave_header(tsk, buf))
+ return false;
+
+ if (use_fxsr() && !save_xstate_epilog(buf_fx, ia32_fxstate, fpstate))
+ return false;
+
+ return true;
+}
+
+static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
+ u64 xrestore, bool fx_only)
+{
+ if (use_xsave()) {
+ u64 init_bv = ufeatures & ~xrestore;
+ int ret;
+
+ if (likely(!fx_only))
+ ret = xrstor_from_user_sigframe(buf, xrestore);
+ else
+ ret = fxrstor_from_user_sigframe(buf);
+
+ if (!ret && unlikely(init_bv))
+ os_xrstor(&init_fpstate, init_bv);
+ return ret;
+ } else if (use_fxsr()) {
+ return fxrstor_from_user_sigframe(buf);
+ } else {
+ return frstor_from_user_sigframe(buf);
+ }
+}
+
+/*
+ * Attempt to restore the FPU registers directly from user memory.
+ * Pagefaults are handled and any errors returned are fatal.
+ */
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
+ bool fx_only, unsigned int size)
+{
+ struct fpu *fpu = &current->thread.fpu;
+ int ret;
+
+retry:
+ fpregs_lock();
+ /* Ensure that XFD is up to date */
+ xfd_update_state(fpu->fpstate);
+ pagefault_disable();
+ ret = __restore_fpregs_from_user(buf, fpu->fpstate->user_xfeatures,
+ xrestore, fx_only);
+ pagefault_enable();
+
+ if (unlikely(ret)) {
+ /*
+ * The above did an FPU restore operation, restricted to
+ * the user portion of the registers, and failed, but the
+ * microcode might have modified the FPU registers
+ * nevertheless.
+ *
+ * If the FPU registers do not belong to current, then
+ * invalidate the FPU register state otherwise the task
+ * might preempt current and return to user space with
+ * corrupted FPU registers.
+ */
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ __cpu_invalidate_fpregs_state();
+ fpregs_unlock();
+
+ /* Try to handle #PF, but anything else is fatal. */
+ if (ret != X86_TRAP_PF)
+ return false;
+
+ if (!fault_in_readable(buf, size))
+ goto retry;
+ return false;
+ }
+
+ /*
+ * Restore supervisor states: previous context switch etc has done
+ * XSAVES and saved the supervisor states in the kernel buffer from
+ * which they can be restored now.
+ *
+ * It would be optimal to handle this with a single XRSTORS, but
+ * this does not work because the rest of the FPU registers have
+ * been restored from a user buffer directly.
+ */
+ if (test_thread_flag(TIF_NEED_FPU_LOAD) && xfeatures_mask_supervisor())
+ os_xrstor_supervisor(fpu->fpstate);
+
+ fpregs_mark_activate();
+ fpregs_unlock();
+ return true;
+}
+
+static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
+ bool ia32_fxstate)
+{
+ struct task_struct *tsk = current;
+ struct fpu *fpu = &tsk->thread.fpu;
+ struct user_i387_ia32_struct env;
+ bool success, fx_only = false;
+ union fpregs_state *fpregs;
+ unsigned int state_size;
+ u64 user_xfeatures = 0;
+
+ if (use_xsave()) {
+ struct _fpx_sw_bytes fx_sw_user;
+
+ if (!check_xstate_in_sigframe(buf_fx, &fx_sw_user))
+ return false;
+
+ fx_only = !fx_sw_user.magic1;
+ state_size = fx_sw_user.xstate_size;
+ user_xfeatures = fx_sw_user.xfeatures;
+ } else {
+ user_xfeatures = XFEATURE_MASK_FPSSE;
+ state_size = fpu->fpstate->user_size;
+ }
+
+ if (likely(!ia32_fxstate)) {
+ /* Restore the FPU registers directly from user memory. */
+ return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
+ state_size);
+ }
+
+ /*
+ * Copy the legacy state because the FP portion of the FX frame has
+ * to be ignored for histerical raisins. The legacy state is folded
+ * in once the larger state has been copied.
+ */
+ if (__copy_from_user(&env, buf, sizeof(env)))
+ return false;
+
+ /*
+ * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is
+ * not modified on context switch and that the xstate is considered
+ * to be loaded again on return to userland (overriding last_cpu avoids
+ * the optimisation).
+ */
+ fpregs_lock();
+ if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+ /*
+ * If supervisor states are available then save the
+ * hardware state in current's fpstate so that the
+ * supervisor state is preserved. Save the full state for
+ * simplicity. There is no point in optimizing this by only
+ * saving the supervisor states and then shuffle them to
+ * the right place in memory. It's ia32 mode. Shrug.
+ */
+ if (xfeatures_mask_supervisor())
+ os_xsave(fpu->fpstate);
+ set_thread_flag(TIF_NEED_FPU_LOAD);
+ }
+ __fpu_invalidate_fpregs_state(fpu);
+ __cpu_invalidate_fpregs_state();
+ fpregs_unlock();
+
+ fpregs = &fpu->fpstate->regs;
+ if (use_xsave() && !fx_only) {
+ if (copy_sigframe_from_user_to_xstate(tsk, buf_fx))
+ return false;
+ } else {
+ if (__copy_from_user(&fpregs->fxsave, buf_fx,
+ sizeof(fpregs->fxsave)))
+ return false;
+
+ if (IS_ENABLED(CONFIG_X86_64)) {
+ /* Reject invalid MXCSR values. */
+ if (fpregs->fxsave.mxcsr & ~mxcsr_feature_mask)
+ return false;
+ } else {
+ /* Mask invalid bits out for historical reasons (broken hardware). */
+ fpregs->fxsave.mxcsr &= mxcsr_feature_mask;
+ }
+
+ /* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */
+ if (use_xsave())
+ fpregs->xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
+ }
+
+ /* Fold the legacy FP storage */
+ convert_to_fxsr(&fpregs->fxsave, &env);
+
+ fpregs_lock();
+ if (use_xsave()) {
+ /*
+ * Remove all UABI feature bits not set in user_xfeatures
+ * from the memory xstate header which makes the full
+ * restore below bring them into init state. This works for
+ * fx_only mode as well because that has only FP and SSE
+ * set in user_xfeatures.
+ *
+ * Preserve supervisor states!
+ */
+ u64 mask = user_xfeatures | xfeatures_mask_supervisor();
+
+ fpregs->xsave.header.xfeatures &= mask;
+ success = !os_xrstor_safe(fpu->fpstate,
+ fpu_kernel_cfg.max_features);
+ } else {
+ success = !fxrstor_safe(&fpregs->fxsave);
+ }
+
+ if (likely(success))
+ fpregs_mark_activate();
+
+ fpregs_unlock();
+ return success;
+}
+
+static inline unsigned int xstate_sigframe_size(struct fpstate *fpstate)
+{
+ unsigned int size = fpstate->user_size;
+
+ return use_xsave() ? size + FP_XSTATE_MAGIC2_SIZE : size;
+}
+
+/*
+ * Restore FPU state from a sigframe:
+ */
+bool fpu__restore_sig(void __user *buf, int ia32_frame)
+{
+ struct fpu *fpu = &current->thread.fpu;
+ void __user *buf_fx = buf;
+ bool ia32_fxstate = false;
+ bool success = false;
+ unsigned int size;
+
+ if (unlikely(!buf)) {
+ fpu__clear_user_states(fpu);
+ return true;
+ }
+
+ size = xstate_sigframe_size(fpu->fpstate);
+
+ ia32_frame &= (IS_ENABLED(CONFIG_X86_32) ||
+ IS_ENABLED(CONFIG_IA32_EMULATION));
+
+ /*
+ * Only FXSR enabled systems need the FX state quirk.
+ * FRSTOR does not need it and can use the fast path.
+ */
+ if (ia32_frame && use_fxsr()) {
+ buf_fx = buf + sizeof(struct fregs_state);
+ size += sizeof(struct fregs_state);
+ ia32_fxstate = true;
+ }
+
+ if (!access_ok(buf, size))
+ goto out;
+
+ if (!IS_ENABLED(CONFIG_X86_64) && !cpu_feature_enabled(X86_FEATURE_FPU)) {
+ success = !fpregs_soft_set(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct),
+ NULL, buf);
+ } else {
+ success = __fpu_restore_sig(buf, buf_fx, ia32_fxstate);
+ }
+
+out:
+ if (unlikely(!success))
+ fpu__clear_user_states(fpu);
+ return success;
+}
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+ unsigned long *buf_fx, unsigned long *size)
+{
+ unsigned long frame_size = xstate_sigframe_size(current->thread.fpu.fpstate);
+
+ *buf_fx = sp = round_down(sp - frame_size, 64);
+ if (ia32_frame && use_fxsr()) {
+ frame_size += sizeof(struct fregs_state);
+ sp -= sizeof(struct fregs_state);
+ }
+
+ *size = frame_size;
+
+ return sp;
+}
+
+unsigned long __init fpu__get_fpstate_size(void)
+{
+ unsigned long ret = fpu_user_cfg.max_size;
+
+ if (use_xsave())
+ ret += FP_XSTATE_MAGIC2_SIZE;
+
+ /*
+ * This space is needed on (most) 32-bit kernels, or when a 32-bit
+ * app is running on a 64-bit kernel. To keep things simple, just
+ * assume the worst case and always include space for 'freg_state',
+ * even for 64-bit apps on 64-bit kernels. This wastes a bit of
+ * space, but keeps the code simple.
+ */
+ if ((IS_ENABLED(CONFIG_IA32_EMULATION) ||
+ IS_ENABLED(CONFIG_X86_32)) && use_fxsr())
+ ret += sizeof(struct fregs_state);
+
+ return ret;
+}
+
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
new file mode 100644
index 000000000..ebe698f8a
--- /dev/null
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -0,0 +1,1843 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * xsave/xrstor support.
+ *
+ * Author: Suresh Siddha <suresh.b.siddha@intel.com>
+ */
+#include <linux/bitops.h>
+#include <linux/compat.h>
+#include <linux/cpu.h>
+#include <linux/mman.h>
+#include <linux/nospec.h>
+#include <linux/pkeys.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/vmalloc.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/xcr.h>
+
+#include <asm/tlbflush.h>
+#include <asm/prctl.h>
+#include <asm/elf.h>
+
+#include "context.h"
+#include "internal.h"
+#include "legacy.h"
+#include "xstate.h"
+
+#define for_each_extended_xfeature(bit, mask) \
+ (bit) = FIRST_EXTENDED_XFEATURE; \
+ for_each_set_bit_from(bit, (unsigned long *)&(mask), 8 * sizeof(mask))
+
+/*
+ * Although we spell it out in here, the Processor Trace
+ * xfeature is completely unused. We use other mechanisms
+ * to save/restore PT state in Linux.
+ */
+static const char *xfeature_names[] =
+{
+ "x87 floating point registers" ,
+ "SSE registers" ,
+ "AVX registers" ,
+ "MPX bounds registers" ,
+ "MPX CSR" ,
+ "AVX-512 opmask" ,
+ "AVX-512 Hi256" ,
+ "AVX-512 ZMM_Hi256" ,
+ "Processor Trace (unused)" ,
+ "Protection Keys User registers",
+ "PASID state",
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "unknown xstate feature" ,
+ "AMX Tile config" ,
+ "AMX Tile data" ,
+ "unknown xstate feature" ,
+};
+
+static unsigned short xsave_cpuid_features[] __initdata = {
+ [XFEATURE_FP] = X86_FEATURE_FPU,
+ [XFEATURE_SSE] = X86_FEATURE_XMM,
+ [XFEATURE_YMM] = X86_FEATURE_AVX,
+ [XFEATURE_BNDREGS] = X86_FEATURE_MPX,
+ [XFEATURE_BNDCSR] = X86_FEATURE_MPX,
+ [XFEATURE_OPMASK] = X86_FEATURE_AVX512F,
+ [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F,
+ [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F,
+ [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT,
+ [XFEATURE_PKRU] = X86_FEATURE_PKU,
+ [XFEATURE_PASID] = X86_FEATURE_ENQCMD,
+ [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE,
+ [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE,
+};
+
+static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
+ { [ 0 ... XFEATURE_MAX - 1] = -1};
+static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
+ { [ 0 ... XFEATURE_MAX - 1] = -1};
+static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init;
+
+#define XSTATE_FLAG_SUPERVISOR BIT(0)
+#define XSTATE_FLAG_ALIGNED64 BIT(1)
+
+/*
+ * Return whether the system supports a given xfeature.
+ *
+ * Also return the name of the (most advanced) feature that the caller requested:
+ */
+int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
+{
+ u64 xfeatures_missing = xfeatures_needed & ~fpu_kernel_cfg.max_features;
+
+ if (unlikely(feature_name)) {
+ long xfeature_idx, max_idx;
+ u64 xfeatures_print;
+ /*
+ * So we use FLS here to be able to print the most advanced
+ * feature that was requested but is missing. So if a driver
+ * asks about "XFEATURE_MASK_SSE | XFEATURE_MASK_YMM" we'll print the
+ * missing AVX feature - this is the most informative message
+ * to users:
+ */
+ if (xfeatures_missing)
+ xfeatures_print = xfeatures_missing;
+ else
+ xfeatures_print = xfeatures_needed;
+
+ xfeature_idx = fls64(xfeatures_print)-1;
+ max_idx = ARRAY_SIZE(xfeature_names)-1;
+ xfeature_idx = min(xfeature_idx, max_idx);
+
+ *feature_name = xfeature_names[xfeature_idx];
+ }
+
+ if (xfeatures_missing)
+ return 0;
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
+
+static bool xfeature_is_aligned64(int xfeature_nr)
+{
+ return xstate_flags[xfeature_nr] & XSTATE_FLAG_ALIGNED64;
+}
+
+static bool xfeature_is_supervisor(int xfeature_nr)
+{
+ return xstate_flags[xfeature_nr] & XSTATE_FLAG_SUPERVISOR;
+}
+
+static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature)
+{
+ unsigned int offs, i;
+
+ /*
+ * Non-compacted format and legacy features use the cached fixed
+ * offsets.
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_XCOMPACTED) ||
+ xfeature <= XFEATURE_SSE)
+ return xstate_offsets[xfeature];
+
+ /*
+ * Compacted format offsets depend on the actual content of the
+ * compacted xsave area which is determined by the xcomp_bv header
+ * field.
+ */
+ offs = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ for_each_extended_xfeature(i, xcomp_bv) {
+ if (xfeature_is_aligned64(i))
+ offs = ALIGN(offs, 64);
+ if (i == xfeature)
+ break;
+ offs += xstate_sizes[i];
+ }
+ return offs;
+}
+
+/*
+ * Enable the extended processor state save/restore feature.
+ * Called once per CPU onlining.
+ */
+void fpu__init_cpu_xstate(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_XSAVE) || !fpu_kernel_cfg.max_features)
+ return;
+
+ cr4_set_bits(X86_CR4_OSXSAVE);
+
+ /*
+ * Must happen after CR4 setup and before xsetbv() to allow KVM
+ * lazy passthrough. Write independent of the dynamic state static
+ * key as that does not work on the boot CPU. This also ensures
+ * that any stale state is wiped out from XFD.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XFD))
+ wrmsrl(MSR_IA32_XFD, init_fpstate.xfd);
+
+ /*
+ * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features
+ * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user
+ * states can be set here.
+ */
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features);
+
+ /*
+ * MSR_IA32_XSS sets supervisor states managed by XSAVES.
+ */
+ if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+ xfeatures_mask_independent());
+ }
+}
+
+static bool xfeature_enabled(enum xfeature xfeature)
+{
+ return fpu_kernel_cfg.max_features & BIT_ULL(xfeature);
+}
+
+/*
+ * Record the offsets and sizes of various xstates contained
+ * in the XSAVE state memory layout.
+ */
+static void __init setup_xstate_cache(void)
+{
+ u32 eax, ebx, ecx, edx, i;
+ /* start at the beginning of the "extended state" */
+ unsigned int last_good_offset = offsetof(struct xregs_state,
+ extended_state_area);
+ /*
+ * The FP xstates and SSE xstates are legacy states. They are always
+ * in the fixed offsets in the xsave area in either compacted form
+ * or standard form.
+ */
+ xstate_offsets[XFEATURE_FP] = 0;
+ xstate_sizes[XFEATURE_FP] = offsetof(struct fxregs_state,
+ xmm_space);
+
+ xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP];
+ xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state,
+ xmm_space);
+
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
+ cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+
+ xstate_sizes[i] = eax;
+ xstate_flags[i] = ecx;
+
+ /*
+ * If an xfeature is supervisor state, the offset in EBX is
+ * invalid, leave it to -1.
+ */
+ if (xfeature_is_supervisor(i))
+ continue;
+
+ xstate_offsets[i] = ebx;
+
+ /*
+ * In our xstate size checks, we assume that the highest-numbered
+ * xstate feature has the highest offset in the buffer. Ensure
+ * it does.
+ */
+ WARN_ONCE(last_good_offset > xstate_offsets[i],
+ "x86/fpu: misordered xstate at %d\n", last_good_offset);
+
+ last_good_offset = xstate_offsets[i];
+ }
+}
+
+static void __init print_xstate_feature(u64 xstate_mask)
+{
+ const char *feature_name;
+
+ if (cpu_has_xfeatures(xstate_mask, &feature_name))
+ pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name);
+}
+
+/*
+ * Print out all the supported xstate features:
+ */
+static void __init print_xstate_features(void)
+{
+ print_xstate_feature(XFEATURE_MASK_FP);
+ print_xstate_feature(XFEATURE_MASK_SSE);
+ print_xstate_feature(XFEATURE_MASK_YMM);
+ print_xstate_feature(XFEATURE_MASK_BNDREGS);
+ print_xstate_feature(XFEATURE_MASK_BNDCSR);
+ print_xstate_feature(XFEATURE_MASK_OPMASK);
+ print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
+ print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
+ print_xstate_feature(XFEATURE_MASK_PKRU);
+ print_xstate_feature(XFEATURE_MASK_PASID);
+ print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
+ print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
+}
+
+/*
+ * This check is important because it is easy to get XSTATE_*
+ * confused with XSTATE_BIT_*.
+ */
+#define CHECK_XFEATURE(nr) do { \
+ WARN_ON(nr < FIRST_EXTENDED_XFEATURE); \
+ WARN_ON(nr >= XFEATURE_MAX); \
+} while (0)
+
+/*
+ * Print out xstate component offsets and sizes
+ */
+static void __init print_xstate_offset_size(void)
+{
+ int i;
+
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
+ pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n",
+ i, xfeature_get_offset(fpu_kernel_cfg.max_features, i),
+ i, xstate_sizes[i]);
+ }
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static __init void os_xrstor_booting(struct xregs_state *xstate)
+{
+ u64 mask = fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSTATE;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ if (cpu_feature_enabled(X86_FEATURE_XSAVES))
+ XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+ else
+ XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+ /*
+ * We should never fault when copying from a kernel buffer, and the FPU
+ * state we set at boot time should be valid.
+ */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * All supported features have either init state all zeros or are
+ * handled in setup_init_fpu() individually. This is an explicit
+ * feature list and does not use XFEATURE_MASK*SUPPORTED to catch
+ * newly added supported features at build time and make people
+ * actually look at the init state for the new feature.
+ */
+#define XFEATURES_INIT_FPSTATE_HANDLED \
+ (XFEATURE_MASK_FP | \
+ XFEATURE_MASK_SSE | \
+ XFEATURE_MASK_YMM | \
+ XFEATURE_MASK_OPMASK | \
+ XFEATURE_MASK_ZMM_Hi256 | \
+ XFEATURE_MASK_Hi16_ZMM | \
+ XFEATURE_MASK_PKRU | \
+ XFEATURE_MASK_BNDREGS | \
+ XFEATURE_MASK_BNDCSR | \
+ XFEATURE_MASK_PASID | \
+ XFEATURE_MASK_XTILE)
+
+/*
+ * setup the xstate image representing the init state
+ */
+static void __init setup_init_fpu_buf(void)
+{
+ BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED |
+ XFEATURE_MASK_SUPERVISOR_SUPPORTED) !=
+ XFEATURES_INIT_FPSTATE_HANDLED);
+
+ if (!boot_cpu_has(X86_FEATURE_XSAVE))
+ return;
+
+ print_xstate_features();
+
+ xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures);
+
+ /*
+ * Init all the features state with header.xfeatures being 0x0
+ */
+ os_xrstor_booting(&init_fpstate.regs.xsave);
+
+ /*
+ * All components are now in init state. Read the state back so
+ * that init_fpstate contains all non-zero init state. This only
+ * works with XSAVE, but not with XSAVEOPT and XSAVEC/S because
+ * those use the init optimization which skips writing data for
+ * components in init state.
+ *
+ * XSAVE could be used, but that would require to reshuffle the
+ * data when XSAVEC/S is available because XSAVEC/S uses xstate
+ * compaction. But doing so is a pointless exercise because most
+ * components have an all zeros init state except for the legacy
+ * ones (FP and SSE). Those can be saved with FXSAVE into the
+ * legacy area. Adding new features requires to ensure that init
+ * state is all zeroes or if not to add the necessary handling
+ * here.
+ */
+ fxsave(&init_fpstate.regs.fxsave);
+}
+
+int xfeature_size(int xfeature_nr)
+{
+ u32 eax, ebx, ecx, edx;
+
+ CHECK_XFEATURE(xfeature_nr);
+ cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx);
+ return eax;
+}
+
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+static int validate_user_xstate_header(const struct xstate_header *hdr,
+ struct fpstate *fpstate)
+{
+ /* No unknown or supervisor features may be set */
+ if (hdr->xfeatures & ~fpstate->user_xfeatures)
+ return -EINVAL;
+
+ /* Userspace must use the uncompacted format */
+ if (hdr->xcomp_bv)
+ return -EINVAL;
+
+ /*
+ * If 'reserved' is shrunken to add a new field, make sure to validate
+ * that new field here!
+ */
+ BUILD_BUG_ON(sizeof(hdr->reserved) != 48);
+
+ /* No reserved bits may be set */
+ if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved)))
+ return -EINVAL;
+
+ return 0;
+}
+
+static void __init __xstate_dump_leaves(void)
+{
+ int i;
+ u32 eax, ebx, ecx, edx;
+ static int should_dump = 1;
+
+ if (!should_dump)
+ return;
+ should_dump = 0;
+ /*
+ * Dump out a few leaves past the ones that we support
+ * just in case there are some goodies up there
+ */
+ for (i = 0; i < XFEATURE_MAX + 10; i++) {
+ cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+ pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n",
+ XSTATE_CPUID, i, eax, ebx, ecx, edx);
+ }
+}
+
+#define XSTATE_WARN_ON(x, fmt, ...) do { \
+ if (WARN_ONCE(x, "XSAVE consistency problem: " fmt, ##__VA_ARGS__)) { \
+ __xstate_dump_leaves(); \
+ } \
+} while (0)
+
+#define XCHECK_SZ(sz, nr, nr_macro, __struct) do { \
+ if ((nr == nr_macro) && \
+ WARN_ONCE(sz != sizeof(__struct), \
+ "%s: struct is %zu bytes, cpu state %d bytes\n", \
+ __stringify(nr_macro), sizeof(__struct), sz)) { \
+ __xstate_dump_leaves(); \
+ } \
+} while (0)
+
+/**
+ * check_xtile_data_against_struct - Check tile data state size.
+ *
+ * Calculate the state size by multiplying the single tile size which is
+ * recorded in a C struct, and the number of tiles that the CPU informs.
+ * Compare the provided size with the calculation.
+ *
+ * @size: The tile data state size
+ *
+ * Returns: 0 on success, -EINVAL on mismatch.
+ */
+static int __init check_xtile_data_against_struct(int size)
+{
+ u32 max_palid, palid, state_size;
+ u32 eax, ebx, ecx, edx;
+ u16 max_tile;
+
+ /*
+ * Check the maximum palette id:
+ * eax: the highest numbered palette subleaf.
+ */
+ cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx);
+
+ /*
+ * Cross-check each tile size and find the maximum number of
+ * supported tiles.
+ */
+ for (palid = 1, max_tile = 0; palid <= max_palid; palid++) {
+ u16 tile_size, max;
+
+ /*
+ * Check the tile size info:
+ * eax[31:16]: bytes per title
+ * ebx[31:16]: the max names (or max number of tiles)
+ */
+ cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx);
+ tile_size = eax >> 16;
+ max = ebx >> 16;
+
+ if (tile_size != sizeof(struct xtile_data)) {
+ pr_err("%s: struct is %zu bytes, cpu xtile %d bytes\n",
+ __stringify(XFEATURE_XTILE_DATA),
+ sizeof(struct xtile_data), tile_size);
+ __xstate_dump_leaves();
+ return -EINVAL;
+ }
+
+ if (max > max_tile)
+ max_tile = max;
+ }
+
+ state_size = sizeof(struct xtile_data) * max_tile;
+ if (size != state_size) {
+ pr_err("%s: calculated size is %u bytes, cpu state %d bytes\n",
+ __stringify(XFEATURE_XTILE_DATA), state_size, size);
+ __xstate_dump_leaves();
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/*
+ * We have a C struct for each 'xstate'. We need to ensure
+ * that our software representation matches what the CPU
+ * tells us about the state's size.
+ */
+static bool __init check_xstate_against_struct(int nr)
+{
+ /*
+ * Ask the CPU for the size of the state.
+ */
+ int sz = xfeature_size(nr);
+ /*
+ * Match each CPU state with the corresponding software
+ * structure.
+ */
+ XCHECK_SZ(sz, nr, XFEATURE_YMM, struct ymmh_struct);
+ XCHECK_SZ(sz, nr, XFEATURE_BNDREGS, struct mpx_bndreg_state);
+ XCHECK_SZ(sz, nr, XFEATURE_BNDCSR, struct mpx_bndcsr_state);
+ XCHECK_SZ(sz, nr, XFEATURE_OPMASK, struct avx_512_opmask_state);
+ XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
+ XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state);
+ XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state);
+ XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state);
+ XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg);
+
+ /* The tile data size varies between implementations. */
+ if (nr == XFEATURE_XTILE_DATA)
+ check_xtile_data_against_struct(sz);
+
+ /*
+ * Make *SURE* to add any feature numbers in below if
+ * there are "holes" in the xsave state component
+ * numbers.
+ */
+ if ((nr < XFEATURE_YMM) ||
+ (nr >= XFEATURE_MAX) ||
+ (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
+ ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) {
+ XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
+ return false;
+ }
+ return true;
+}
+
+static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
+{
+ unsigned int topmost = fls64(xfeatures) - 1;
+ unsigned int offset = xstate_offsets[topmost];
+
+ if (topmost <= XFEATURE_SSE)
+ return sizeof(struct xregs_state);
+
+ if (compacted)
+ offset = xfeature_get_offset(xfeatures, topmost);
+ return offset + xstate_sizes[topmost];
+}
+
+/*
+ * This essentially double-checks what the cpu told us about
+ * how large the XSAVE buffer needs to be. We are recalculating
+ * it to be safe.
+ *
+ * Independent XSAVE features allocate their own buffers and are not
+ * covered by these checks. Only the size of the buffer for task->fpu
+ * is checked here.
+ */
+static bool __init paranoid_xstate_size_valid(unsigned int kernel_size)
+{
+ bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
+ bool xsaves = cpu_feature_enabled(X86_FEATURE_XSAVES);
+ unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+ int i;
+
+ for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
+ if (!check_xstate_against_struct(i))
+ return false;
+ /*
+ * Supervisor state components can be managed only by
+ * XSAVES.
+ */
+ if (!xsaves && xfeature_is_supervisor(i)) {
+ XSTATE_WARN_ON(1, "Got supervisor feature %d, but XSAVES not advertised\n", i);
+ return false;
+ }
+ }
+ size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted);
+ XSTATE_WARN_ON(size != kernel_size,
+ "size %u != kernel_size %u\n", size, kernel_size);
+ return size == kernel_size;
+}
+
+/*
+ * Get total size of enabled xstates in XCR0 | IA32_XSS.
+ *
+ * Note the SDM's wording here. "sub-function 0" only enumerates
+ * the size of the *user* states. If we use it to size a buffer
+ * that we use 'XSAVES' on, we could potentially overflow the
+ * buffer because 'XSAVES' saves system states too.
+ *
+ * This also takes compaction into account. So this works for
+ * XSAVEC as well.
+ */
+static unsigned int __init get_compacted_size(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ /*
+ * - CPUID function 0DH, sub-function 1:
+ * EBX enumerates the size (in bytes) required by
+ * the XSAVES instruction for an XSAVE area
+ * containing all the state components
+ * corresponding to bits currently set in
+ * XCR0 | IA32_XSS.
+ *
+ * When XSAVES is not available but XSAVEC is (virt), then there
+ * are no supervisor states, but XSAVEC still uses compacted
+ * format.
+ */
+ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+ return ebx;
+}
+
+/*
+ * Get the total size of the enabled xstates without the independent supervisor
+ * features.
+ */
+static unsigned int __init get_xsave_compacted_size(void)
+{
+ u64 mask = xfeatures_mask_independent();
+ unsigned int size;
+
+ if (!mask)
+ return get_compacted_size();
+
+ /* Disable independent features. */
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+
+ /*
+ * Ask the hardware what size is required of the buffer.
+ * This is the size required for the task->fpu buffer.
+ */
+ size = get_compacted_size();
+
+ /* Re-enable independent features so XSAVES will work on them again. */
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+
+ return size;
+}
+
+static unsigned int __init get_xsave_size_user(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ /*
+ * - CPUID function 0DH, sub-function 0:
+ * EBX enumerates the size (in bytes) required by
+ * the XSAVE instruction for an XSAVE area
+ * containing all the *user* state components
+ * corresponding to bits currently set in XCR0.
+ */
+ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ return ebx;
+}
+
+static int __init init_xstate_size(void)
+{
+ /* Recompute the context size for enabled features: */
+ unsigned int user_size, kernel_size, kernel_default_size;
+ bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
+
+ /* Uncompacted user space size */
+ user_size = get_xsave_size_user();
+
+ /*
+ * XSAVES kernel size includes supervisor states and uses compacted
+ * format. XSAVEC uses compacted format, but does not save
+ * supervisor states.
+ *
+ * XSAVE[OPT] do not support supervisor states so kernel and user
+ * size is identical.
+ */
+ if (compacted)
+ kernel_size = get_xsave_compacted_size();
+ else
+ kernel_size = user_size;
+
+ kernel_default_size =
+ xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
+
+ if (!paranoid_xstate_size_valid(kernel_size))
+ return -EINVAL;
+
+ fpu_kernel_cfg.max_size = kernel_size;
+ fpu_user_cfg.max_size = user_size;
+
+ fpu_kernel_cfg.default_size = kernel_default_size;
+ fpu_user_cfg.default_size =
+ xstate_calculate_size(fpu_user_cfg.default_features, false);
+
+ return 0;
+}
+
+/*
+ * We enabled the XSAVE hardware, but something went wrong and
+ * we can not use it. Disable it.
+ */
+static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
+{
+ fpu_kernel_cfg.max_features = 0;
+ cr4_clear_bits(X86_CR4_OSXSAVE);
+ setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+
+ /* Restore the legacy size.*/
+ fpu_kernel_cfg.max_size = legacy_size;
+ fpu_kernel_cfg.default_size = legacy_size;
+ fpu_user_cfg.max_size = legacy_size;
+ fpu_user_cfg.default_size = legacy_size;
+
+ /*
+ * Prevent enabling the static branch which enables writes to the
+ * XFD MSR.
+ */
+ init_fpstate.xfd = 0;
+
+ fpstate_reset(&current->thread.fpu);
+}
+
+/*
+ * Enable and initialize the xsave feature.
+ * Called once per system bootup.
+ */
+void __init fpu__init_system_xstate(unsigned int legacy_size)
+{
+ unsigned int eax, ebx, ecx, edx;
+ u64 xfeatures;
+ int err;
+ int i;
+
+ if (!boot_cpu_has(X86_FEATURE_FPU)) {
+ pr_info("x86/fpu: No FPU detected\n");
+ return;
+ }
+
+ if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
+ pr_info("x86/fpu: x87 FPU will use %s\n",
+ boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE");
+ return;
+ }
+
+ if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
+ WARN_ON_FPU(1);
+ return;
+ }
+
+ /*
+ * Find user xstates supported by the processor.
+ */
+ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+ fpu_kernel_cfg.max_features = eax + ((u64)edx << 32);
+
+ /*
+ * Find supervisor xstates supported by the processor.
+ */
+ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx);
+ fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32);
+
+ if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) {
+ /*
+ * This indicates that something really unexpected happened
+ * with the enumeration. Disable XSAVE and try to continue
+ * booting without it. This is too early to BUG().
+ */
+ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n",
+ fpu_kernel_cfg.max_features);
+ goto out_disable;
+ }
+
+ /*
+ * Clear XSAVE features that are disabled in the normal CPUID.
+ */
+ for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) {
+ unsigned short cid = xsave_cpuid_features[i];
+
+ /* Careful: X86_FEATURE_FPU is 0! */
+ if ((i != XFEATURE_FP && !cid) || !boot_cpu_has(cid))
+ fpu_kernel_cfg.max_features &= ~BIT_ULL(i);
+ }
+
+ if (!cpu_feature_enabled(X86_FEATURE_XFD))
+ fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+
+ if (!cpu_feature_enabled(X86_FEATURE_XSAVES))
+ fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED;
+ else
+ fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED |
+ XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+
+ fpu_user_cfg.max_features = fpu_kernel_cfg.max_features;
+ fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED;
+
+ /* Clean out dynamic features from default */
+ fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features;
+ fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+
+ fpu_user_cfg.default_features = fpu_user_cfg.max_features;
+ fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+
+ /* Store it for paranoia check at the end */
+ xfeatures = fpu_kernel_cfg.max_features;
+
+ /*
+ * Initialize the default XFD state in initfp_state and enable the
+ * dynamic sizing mechanism if dynamic states are available. The
+ * static key cannot be enabled here because this runs before
+ * jump_label_init(). This is delayed to an initcall.
+ */
+ init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC;
+
+ /* Set up compaction feature bit */
+ if (cpu_feature_enabled(X86_FEATURE_XSAVEC) ||
+ cpu_feature_enabled(X86_FEATURE_XSAVES))
+ setup_force_cpu_cap(X86_FEATURE_XCOMPACTED);
+
+ /* Enable xstate instructions to be able to continue with initialization: */
+ fpu__init_cpu_xstate();
+
+ /* Cache size, offset and flags for initialization */
+ setup_xstate_cache();
+
+ err = init_xstate_size();
+ if (err)
+ goto out_disable;
+
+ /* Reset the state for the current task */
+ fpstate_reset(&current->thread.fpu);
+
+ /*
+ * Update info used for ptrace frames; use standard-format size and no
+ * supervisor xstates:
+ */
+ update_regset_xstate_info(fpu_user_cfg.max_size,
+ fpu_user_cfg.max_features);
+
+ /*
+ * init_fpstate excludes dynamic states as they are large but init
+ * state is zero.
+ */
+ init_fpstate.size = fpu_kernel_cfg.default_size;
+ init_fpstate.xfeatures = fpu_kernel_cfg.default_features;
+
+ if (init_fpstate.size > sizeof(init_fpstate.regs)) {
+ pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+ sizeof(init_fpstate.regs), init_fpstate.size);
+ goto out_disable;
+ }
+
+ setup_init_fpu_buf();
+
+ /*
+ * Paranoia check whether something in the setup modified the
+ * xfeatures mask.
+ */
+ if (xfeatures != fpu_kernel_cfg.max_features) {
+ pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n",
+ xfeatures, fpu_kernel_cfg.max_features);
+ goto out_disable;
+ }
+
+ /*
+ * CPU capabilities initialization runs before FPU init. So
+ * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely
+ * functional, set the feature bit so depending code works.
+ */
+ setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+
+ print_xstate_offset_size();
+ pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
+ fpu_kernel_cfg.max_features,
+ fpu_kernel_cfg.max_size,
+ boot_cpu_has(X86_FEATURE_XCOMPACTED) ? "compacted" : "standard");
+ return;
+
+out_disable:
+ /* something went wrong, try to boot without any XSAVE support */
+ fpu__init_disable_system_xstate(legacy_size);
+}
+
+/*
+ * Restore minimal FPU state after suspend:
+ */
+void fpu__resume_cpu(void)
+{
+ /*
+ * Restore XCR0 on xsave capable CPUs:
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XSAVE))
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features);
+
+ /*
+ * Restore IA32_XSS. The same CPUID bit enumerates support
+ * of XSAVES and MSR_IA32_XSS.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XSAVES)) {
+ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+ xfeatures_mask_independent());
+ }
+
+ if (fpu_state_size_dynamic())
+ wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
+}
+
+/*
+ * Given an xstate feature nr, calculate where in the xsave
+ * buffer the state is. Callers should ensure that the buffer
+ * is valid.
+ */
+static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
+{
+ u64 xcomp_bv = xsave->header.xcomp_bv;
+
+ if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
+ return NULL;
+
+ if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) {
+ if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr))))
+ return NULL;
+ }
+
+ return (void *)xsave + xfeature_get_offset(xcomp_bv, xfeature_nr);
+}
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Note that if there is no data for the field in the xsave buffer
+ * this will return NULL.
+ *
+ * Inputs:
+ * xstate: the thread's storage area for all FPU data
+ * xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP,
+ * XFEATURE_SSE, etc...)
+ * Output:
+ * address of the state in the xsave area, or NULL if the
+ * field is not present in the xsave buffer.
+ */
+void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
+{
+ /*
+ * Do we even *have* xsave state?
+ */
+ if (!boot_cpu_has(X86_FEATURE_XSAVE))
+ return NULL;
+
+ /*
+ * We should not ever be requesting features that we
+ * have not enabled.
+ */
+ if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
+ return NULL;
+
+ /*
+ * This assumes the last 'xsave*' instruction to
+ * have requested that 'xfeature_nr' be saved.
+ * If it did not, we might be seeing and old value
+ * of the field in the buffer.
+ *
+ * This can happen because the last 'xsave' did not
+ * request that this feature be saved (unlikely)
+ * or because the "init optimization" caused it
+ * to not be saved.
+ */
+ if (!(xsave->header.xfeatures & BIT_ULL(xfeature_nr)))
+ return NULL;
+
+ return __raw_xsave_addr(xsave, xfeature_nr);
+}
+
+#ifdef CONFIG_ARCH_HAS_PKEYS
+
+/*
+ * This will go out and modify PKRU register to set the access
+ * rights for @pkey to @init_val.
+ */
+int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+ unsigned long init_val)
+{
+ u32 old_pkru, new_pkru_bits = 0;
+ int pkey_shift;
+
+ /*
+ * This check implies XSAVE support. OSPKE only gets
+ * set if we enable XSAVE and we enable PKU in XCR0.
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+ return -EINVAL;
+
+ /*
+ * This code should only be called with valid 'pkey'
+ * values originating from in-kernel users. Complain
+ * if a bad value is observed.
+ */
+ if (WARN_ON_ONCE(pkey >= arch_max_pkey()))
+ return -EINVAL;
+
+ /* Set the bits we need in PKRU: */
+ if (init_val & PKEY_DISABLE_ACCESS)
+ new_pkru_bits |= PKRU_AD_BIT;
+ if (init_val & PKEY_DISABLE_WRITE)
+ new_pkru_bits |= PKRU_WD_BIT;
+
+ /* Shift the bits in to the correct place in PKRU for pkey: */
+ pkey_shift = pkey * PKRU_BITS_PER_PKEY;
+ new_pkru_bits <<= pkey_shift;
+
+ /* Get old PKRU and mask off any old bits in place: */
+ old_pkru = read_pkru();
+ old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
+
+ /* Write old part along with new part: */
+ write_pkru(old_pkru | new_pkru_bits);
+
+ return 0;
+}
+#endif /* ! CONFIG_ARCH_HAS_PKEYS */
+
+static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
+ void *init_xstate, unsigned int size)
+{
+ membuf_write(to, from_xstate ? xstate : init_xstate, size);
+}
+
+/**
+ * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
+ * @to: membuf descriptor
+ * @fpstate: The fpstate buffer from which to copy
+ * @xfeatures: The mask of xfeatures to save (XSAVE mode only)
+ * @pkru_val: The PKRU value to store in the PKRU component
+ * @copy_mode: The requested copy mode
+ *
+ * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming
+ * format, i.e. from the kernel internal hardware dependent storage format
+ * to the requested @mode. UABI XSTATE is always uncompacted!
+ *
+ * It supports partial copy but @to.pos always starts from zero.
+ */
+void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
+ u64 xfeatures, u32 pkru_val,
+ enum xstate_copy_mode copy_mode)
+{
+ const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
+ struct xregs_state *xinit = &init_fpstate.regs.xsave;
+ struct xregs_state *xsave = &fpstate->regs.xsave;
+ struct xstate_header header;
+ unsigned int zerofrom;
+ u64 mask;
+ int i;
+
+ memset(&header, 0, sizeof(header));
+ header.xfeatures = xsave->header.xfeatures;
+
+ /* Mask out the feature bits depending on copy mode */
+ switch (copy_mode) {
+ case XSTATE_COPY_FP:
+ header.xfeatures &= XFEATURE_MASK_FP;
+ break;
+
+ case XSTATE_COPY_FX:
+ header.xfeatures &= XFEATURE_MASK_FP | XFEATURE_MASK_SSE;
+ break;
+
+ case XSTATE_COPY_XSAVE:
+ header.xfeatures &= fpstate->user_xfeatures & xfeatures;
+ break;
+ }
+
+ /* Copy FP state up to MXCSR */
+ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387,
+ &xinit->i387, off_mxcsr);
+
+ /* Copy MXCSR when SSE or YMM are set in the feature mask */
+ copy_feature(header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM),
+ &to, &xsave->i387.mxcsr, &xinit->i387.mxcsr,
+ MXCSR_AND_FLAGS_SIZE);
+
+ /* Copy the remaining FP state */
+ copy_feature(header.xfeatures & XFEATURE_MASK_FP,
+ &to, &xsave->i387.st_space, &xinit->i387.st_space,
+ sizeof(xsave->i387.st_space));
+
+ /* Copy the SSE state - shared with YMM, but independently managed */
+ copy_feature(header.xfeatures & XFEATURE_MASK_SSE,
+ &to, &xsave->i387.xmm_space, &xinit->i387.xmm_space,
+ sizeof(xsave->i387.xmm_space));
+
+ if (copy_mode != XSTATE_COPY_XSAVE)
+ goto out;
+
+ /* Zero the padding area */
+ membuf_zero(&to, sizeof(xsave->i387.padding));
+
+ /* Copy xsave->i387.sw_reserved */
+ membuf_write(&to, xstate_fx_sw_bytes, sizeof(xsave->i387.sw_reserved));
+
+ /* Copy the user space relevant state of @xsave->header */
+ membuf_write(&to, &header, sizeof(header));
+
+ zerofrom = offsetof(struct xregs_state, extended_state_area);
+
+ /*
+ * This 'mask' indicates which states to copy from fpstate.
+ * Those extended states that are not present in fpstate are
+ * either disabled or initialized:
+ *
+ * In non-compacted format, disabled features still occupy
+ * state space but there is no state to copy from in the
+ * compacted init_fpstate. The gap tracking will zero these
+ * states.
+ *
+ * The extended features have an all zeroes init state. Thus,
+ * remove them from 'mask' to zero those features in the user
+ * buffer instead of retrieving them from init_fpstate.
+ */
+ mask = header.xfeatures;
+
+ for_each_extended_xfeature(i, mask) {
+ /*
+ * If there was a feature or alignment gap, zero the space
+ * in the destination buffer.
+ */
+ if (zerofrom < xstate_offsets[i])
+ membuf_zero(&to, xstate_offsets[i] - zerofrom);
+
+ if (i == XFEATURE_PKRU) {
+ struct pkru_state pkru = {0};
+ /*
+ * PKRU is not necessarily up to date in the
+ * XSAVE buffer. Use the provided value.
+ */
+ pkru.pkru = pkru_val;
+ membuf_write(&to, &pkru, sizeof(pkru));
+ } else {
+ membuf_write(&to,
+ __raw_xsave_addr(xsave, i),
+ xstate_sizes[i]);
+ }
+ /*
+ * Keep track of the last copied state in the non-compacted
+ * target buffer for gap zeroing.
+ */
+ zerofrom = xstate_offsets[i] + xstate_sizes[i];
+ }
+
+out:
+ if (to.left)
+ membuf_zero(&to, to.left);
+}
+
+/**
+ * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
+ * @to: membuf descriptor
+ * @tsk: The task from which to copy the saved xstate
+ * @copy_mode: The requested copy mode
+ *
+ * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming
+ * format, i.e. from the kernel internal hardware dependent storage format
+ * to the requested @mode. UABI XSTATE is always uncompacted!
+ *
+ * It supports partial copy but @to.pos always starts from zero.
+ */
+void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
+ enum xstate_copy_mode copy_mode)
+{
+ __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
+ tsk->thread.fpu.fpstate->user_xfeatures,
+ tsk->thread.pkru, copy_mode);
+}
+
+static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size,
+ const void *kbuf, const void __user *ubuf)
+{
+ if (kbuf) {
+ memcpy(dst, kbuf + offset, size);
+ } else {
+ if (copy_from_user(dst, ubuf + offset, size))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+
+/**
+ * copy_uabi_to_xstate - Copy a UABI format buffer to the kernel xstate
+ * @fpstate: The fpstate buffer to copy to
+ * @kbuf: The UABI format buffer, if it comes from the kernel
+ * @ubuf: The UABI format buffer, if it comes from userspace
+ * @pkru: The location to write the PKRU value to
+ *
+ * Converts from the UABI format into the kernel internal hardware
+ * dependent format.
+ *
+ * This function ultimately has three different callers with distinct PKRU
+ * behavior.
+ * 1. When called from sigreturn the PKRU register will be restored from
+ * @fpstate via an XRSTOR. Correctly copying the UABI format buffer to
+ * @fpstate is sufficient to cover this case, but the caller will also
+ * pass a pointer to the thread_struct's pkru field in @pkru and updating
+ * it is harmless.
+ * 2. When called from ptrace the PKRU register will be restored from the
+ * thread_struct's pkru field. A pointer to that is passed in @pkru.
+ * The kernel will restore it manually, so the XRSTOR behavior that resets
+ * the PKRU register to the hardware init value (0) if the corresponding
+ * xfeatures bit is not set is emulated here.
+ * 3. When called from KVM the PKRU register will be restored from the vcpu's
+ * pkru field. A pointer to that is passed in @pkru. KVM hasn't used
+ * XRSTOR and hasn't had the PKRU resetting behavior described above. To
+ * preserve that KVM behavior, it passes NULL for @pkru if the xfeatures
+ * bit is not set.
+ */
+static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
+ const void __user *ubuf, u32 *pkru)
+{
+ struct xregs_state *xsave = &fpstate->regs.xsave;
+ unsigned int offset, size;
+ struct xstate_header hdr;
+ u64 mask;
+ int i;
+
+ offset = offsetof(struct xregs_state, header);
+ if (copy_from_buffer(&hdr, offset, sizeof(hdr), kbuf, ubuf))
+ return -EFAULT;
+
+ if (validate_user_xstate_header(&hdr, fpstate))
+ return -EINVAL;
+
+ /* Validate MXCSR when any of the related features is in use */
+ mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM;
+ if (hdr.xfeatures & mask) {
+ u32 mxcsr[2];
+
+ offset = offsetof(struct fxregs_state, mxcsr);
+ if (copy_from_buffer(mxcsr, offset, sizeof(mxcsr), kbuf, ubuf))
+ return -EFAULT;
+
+ /* Reserved bits in MXCSR must be zero. */
+ if (mxcsr[0] & ~mxcsr_feature_mask)
+ return -EINVAL;
+
+ /* SSE and YMM require MXCSR even when FP is not in use. */
+ if (!(hdr.xfeatures & XFEATURE_MASK_FP)) {
+ xsave->i387.mxcsr = mxcsr[0];
+ xsave->i387.mxcsr_mask = mxcsr[1];
+ }
+ }
+
+ for (i = 0; i < XFEATURE_MAX; i++) {
+ mask = BIT_ULL(i);
+
+ if (hdr.xfeatures & mask) {
+ void *dst = __raw_xsave_addr(xsave, i);
+
+ offset = xstate_offsets[i];
+ size = xstate_sizes[i];
+
+ if (copy_from_buffer(dst, offset, size, kbuf, ubuf))
+ return -EFAULT;
+ }
+ }
+
+ if (hdr.xfeatures & XFEATURE_MASK_PKRU) {
+ struct pkru_state *xpkru;
+
+ xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU);
+ *pkru = xpkru->pkru;
+ } else {
+ /*
+ * KVM may pass NULL here to indicate that it does not need
+ * PKRU updated.
+ */
+ if (pkru)
+ *pkru = 0;
+ }
+
+ /*
+ * The state that came in from userspace was user-state only.
+ * Mask all the user states out of 'xfeatures':
+ */
+ xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL;
+
+ /*
+ * Add back in the features that came in from userspace:
+ */
+ xsave->header.xfeatures |= hdr.xfeatures;
+
+ return 0;
+}
+
+/*
+ * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S]
+ * format and copy to the target thread. Used by ptrace and KVM.
+ */
+int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru)
+{
+ return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru);
+}
+
+/*
+ * Convert from a sigreturn standard-format user-space buffer to kernel
+ * XSAVE[S] format and copy to the target thread. This is called from the
+ * sigreturn() and rt_sigreturn() system calls.
+ */
+int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
+ const void __user *ubuf)
+{
+ return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
+}
+
+static bool validate_independent_components(u64 mask)
+{
+ u64 xchk;
+
+ if (WARN_ON_FPU(!cpu_feature_enabled(X86_FEATURE_XSAVES)))
+ return false;
+
+ xchk = ~xfeatures_mask_independent();
+
+ if (WARN_ON_ONCE(!mask || mask & xchk))
+ return false;
+
+ return true;
+}
+
+/**
+ * xsaves - Save selected components to a kernel xstate buffer
+ * @xstate: Pointer to the buffer
+ * @mask: Feature mask to select the components to save
+ *
+ * The @xstate buffer must be 64 byte aligned and correctly initialized as
+ * XSAVES does not write the full xstate header. Before first use the
+ * buffer should be zeroed otherwise a consecutive XRSTORS from that buffer
+ * can #GP.
+ *
+ * The feature mask must be a subset of the independent features.
+ */
+void xsaves(struct xregs_state *xstate, u64 mask)
+{
+ int err;
+
+ if (!validate_independent_components(mask))
+ return;
+
+ XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err);
+ WARN_ON_ONCE(err);
+}
+
+/**
+ * xrstors - Restore selected components from a kernel xstate buffer
+ * @xstate: Pointer to the buffer
+ * @mask: Feature mask to select the components to restore
+ *
+ * The @xstate buffer must be 64 byte aligned and correctly initialized
+ * otherwise XRSTORS from that buffer can #GP.
+ *
+ * Proper usage is to restore the state which was saved with
+ * xsaves() into @xstate.
+ *
+ * The feature mask must be a subset of the independent features.
+ */
+void xrstors(struct xregs_state *xstate, u64 mask)
+{
+ int err;
+
+ if (!validate_independent_components(mask))
+ return;
+
+ XSTATE_OP(XRSTORS, xstate, (u32)mask, (u32)(mask >> 32), err);
+ WARN_ON_ONCE(err);
+}
+
+#if IS_ENABLED(CONFIG_KVM)
+void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature)
+{
+ void *addr = get_xsave_addr(&fps->regs.xsave, xfeature);
+
+ if (addr)
+ memset(addr, 0, xstate_sizes[xfeature]);
+}
+EXPORT_SYMBOL_GPL(fpstate_clear_xstate_component);
+#endif
+
+#ifdef CONFIG_X86_64
+
+#ifdef CONFIG_X86_DEBUG_FPU
+/*
+ * Ensure that a subsequent XSAVE* or XRSTOR* instruction with RFBM=@mask
+ * can safely operate on the @fpstate buffer.
+ */
+static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
+{
+ u64 xfd = __this_cpu_read(xfd_state);
+
+ if (fpstate->xfd == xfd)
+ return true;
+
+ /*
+ * The XFD MSR does not match fpstate->xfd. That's invalid when
+ * the passed in fpstate is current's fpstate.
+ */
+ if (fpstate->xfd == current->thread.fpu.fpstate->xfd)
+ return false;
+
+ /*
+ * XRSTOR(S) from init_fpstate are always correct as it will just
+ * bring all components into init state and not read from the
+ * buffer. XSAVE(S) raises #PF after init.
+ */
+ if (fpstate == &init_fpstate)
+ return rstor;
+
+ /*
+ * XSAVE(S): clone(), fpu_swap_kvm_fpu()
+ * XRSTORS(S): fpu_swap_kvm_fpu()
+ */
+
+ /*
+ * No XSAVE/XRSTOR instructions (except XSAVE itself) touch
+ * the buffer area for XFD-disabled state components.
+ */
+ mask &= ~xfd;
+
+ /*
+ * Remove features which are valid in fpstate. They
+ * have space allocated in fpstate.
+ */
+ mask &= ~fpstate->xfeatures;
+
+ /*
+ * Any remaining state components in 'mask' might be written
+ * by XSAVE/XRSTOR. Fail validation it found.
+ */
+ return !mask;
+}
+
+void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor)
+{
+ WARN_ON_ONCE(!xstate_op_valid(fpstate, mask, rstor));
+}
+#endif /* CONFIG_X86_DEBUG_FPU */
+
+static int __init xfd_update_static_branch(void)
+{
+ /*
+ * If init_fpstate.xfd has bits set then dynamic features are
+ * available and the dynamic sizing must be enabled.
+ */
+ if (init_fpstate.xfd)
+ static_branch_enable(&__fpu_state_size_dynamic);
+ return 0;
+}
+arch_initcall(xfd_update_static_branch)
+
+void fpstate_free(struct fpu *fpu)
+{
+ if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate)
+ vfree(fpu->fpstate);
+}
+
+/**
+ * fpstate_realloc - Reallocate struct fpstate for the requested new features
+ *
+ * @xfeatures: A bitmap of xstate features which extend the enabled features
+ * of that task
+ * @ksize: The required size for the kernel buffer
+ * @usize: The required size for user space buffers
+ * @guest_fpu: Pointer to a guest FPU container. NULL for host allocations
+ *
+ * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer
+ * terminates quickly, vfree()-induced IPIs may be a concern, but tasks
+ * with large states are likely to live longer.
+ *
+ * Returns: 0 on success, -ENOMEM on allocation error.
+ */
+static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
+ unsigned int usize, struct fpu_guest *guest_fpu)
+{
+ struct fpu *fpu = &current->thread.fpu;
+ struct fpstate *curfps, *newfps = NULL;
+ unsigned int fpsize;
+ bool in_use;
+
+ fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64);
+
+ newfps = vzalloc(fpsize);
+ if (!newfps)
+ return -ENOMEM;
+ newfps->size = ksize;
+ newfps->user_size = usize;
+ newfps->is_valloc = true;
+
+ /*
+ * When a guest FPU is supplied, use @guest_fpu->fpstate
+ * as reference independent whether it is in use or not.
+ */
+ curfps = guest_fpu ? guest_fpu->fpstate : fpu->fpstate;
+
+ /* Determine whether @curfps is the active fpstate */
+ in_use = fpu->fpstate == curfps;
+
+ if (guest_fpu) {
+ newfps->is_guest = true;
+ newfps->is_confidential = curfps->is_confidential;
+ newfps->in_use = curfps->in_use;
+ guest_fpu->xfeatures |= xfeatures;
+ guest_fpu->uabi_size = usize;
+ }
+
+ fpregs_lock();
+ /*
+ * If @curfps is in use, ensure that the current state is in the
+ * registers before swapping fpstate as that might invalidate it
+ * due to layout changes.
+ */
+ if (in_use && test_thread_flag(TIF_NEED_FPU_LOAD))
+ fpregs_restore_userregs();
+
+ newfps->xfeatures = curfps->xfeatures | xfeatures;
+ newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+ newfps->xfd = curfps->xfd & ~xfeatures;
+
+ /* Do the final updates within the locked region */
+ xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures);
+
+ if (guest_fpu) {
+ guest_fpu->fpstate = newfps;
+ /* If curfps is active, update the FPU fpstate pointer */
+ if (in_use)
+ fpu->fpstate = newfps;
+ } else {
+ fpu->fpstate = newfps;
+ }
+
+ if (in_use)
+ xfd_update_state(fpu->fpstate);
+ fpregs_unlock();
+
+ /* Only free valloc'ed state */
+ if (curfps && curfps->is_valloc)
+ vfree(curfps);
+
+ return 0;
+}
+
+static int validate_sigaltstack(unsigned int usize)
+{
+ struct task_struct *thread, *leader = current->group_leader;
+ unsigned long framesize = get_sigframe_size();
+
+ lockdep_assert_held(&current->sighand->siglock);
+
+ /* get_sigframe_size() is based on fpu_user_cfg.max_size */
+ framesize -= fpu_user_cfg.max_size;
+ framesize += usize;
+ for_each_thread(leader, thread) {
+ if (thread->sas_ss_size && thread->sas_ss_size < framesize)
+ return -ENOSPC;
+ }
+ return 0;
+}
+
+static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
+{
+ /*
+ * This deliberately does not exclude !XSAVES as we still might
+ * decide to optionally context switch XCR0 or talk the silicon
+ * vendors into extending XFD for the pre AMX states, especially
+ * AVX512.
+ */
+ bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
+ struct fpu *fpu = &current->group_leader->thread.fpu;
+ struct fpu_state_perm *perm;
+ unsigned int ksize, usize;
+ u64 mask;
+ int ret = 0;
+
+ /* Check whether fully enabled */
+ if ((permitted & requested) == requested)
+ return 0;
+
+ /* Calculate the resulting kernel state size */
+ mask = permitted | requested;
+ /* Take supervisor states into account on the host */
+ if (!guest)
+ mask |= xfeatures_mask_supervisor();
+ ksize = xstate_calculate_size(mask, compacted);
+
+ /* Calculate the resulting user state size */
+ mask &= XFEATURE_MASK_USER_SUPPORTED;
+ usize = xstate_calculate_size(mask, false);
+
+ if (!guest) {
+ ret = validate_sigaltstack(usize);
+ if (ret)
+ return ret;
+ }
+
+ perm = guest ? &fpu->guest_perm : &fpu->perm;
+ /* Pairs with the READ_ONCE() in xstate_get_group_perm() */
+ WRITE_ONCE(perm->__state_perm, mask);
+ /* Protected by sighand lock */
+ perm->__state_size = ksize;
+ perm->__user_state_size = usize;
+ return ret;
+}
+
+/*
+ * Permissions array to map facilities with more than one component
+ */
+static const u64 xstate_prctl_req[XFEATURE_MAX] = {
+ [XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA,
+};
+
+static int xstate_request_perm(unsigned long idx, bool guest)
+{
+ u64 permitted, requested;
+ int ret;
+
+ if (idx >= XFEATURE_MAX)
+ return -EINVAL;
+
+ /*
+ * Look up the facility mask which can require more than
+ * one xstate component.
+ */
+ idx = array_index_nospec(idx, ARRAY_SIZE(xstate_prctl_req));
+ requested = xstate_prctl_req[idx];
+ if (!requested)
+ return -EOPNOTSUPP;
+
+ if ((fpu_user_cfg.max_features & requested) != requested)
+ return -EOPNOTSUPP;
+
+ /* Lockless quick check */
+ permitted = xstate_get_group_perm(guest);
+ if ((permitted & requested) == requested)
+ return 0;
+
+ /* Protect against concurrent modifications */
+ spin_lock_irq(&current->sighand->siglock);
+ permitted = xstate_get_group_perm(guest);
+
+ /* First vCPU allocation locks the permissions. */
+ if (guest && (permitted & FPU_GUEST_PERM_LOCKED))
+ ret = -EBUSY;
+ else
+ ret = __xstate_request_perm(permitted, requested, guest);
+ spin_unlock_irq(&current->sighand->siglock);
+ return ret;
+}
+
+int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu)
+{
+ u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC;
+ struct fpu_state_perm *perm;
+ unsigned int ksize, usize;
+ struct fpu *fpu;
+
+ if (!xfd_event) {
+ if (!guest_fpu)
+ pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err);
+ return 0;
+ }
+
+ /* Protect against concurrent modifications */
+ spin_lock_irq(&current->sighand->siglock);
+
+ /* If not permitted let it die */
+ if ((xstate_get_group_perm(!!guest_fpu) & xfd_event) != xfd_event) {
+ spin_unlock_irq(&current->sighand->siglock);
+ return -EPERM;
+ }
+
+ fpu = &current->group_leader->thread.fpu;
+ perm = guest_fpu ? &fpu->guest_perm : &fpu->perm;
+ ksize = perm->__state_size;
+ usize = perm->__user_state_size;
+
+ /*
+ * The feature is permitted. State size is sufficient. Dropping
+ * the lock is safe here even if more features are added from
+ * another task, the retrieved buffer sizes are valid for the
+ * currently requested feature(s).
+ */
+ spin_unlock_irq(&current->sighand->siglock);
+
+ /*
+ * Try to allocate a new fpstate. If that fails there is no way
+ * out.
+ */
+ if (fpstate_realloc(xfd_event, ksize, usize, guest_fpu))
+ return -EFAULT;
+ return 0;
+}
+
+int xfd_enable_feature(u64 xfd_err)
+{
+ return __xfd_enable_feature(xfd_err, NULL);
+}
+
+#else /* CONFIG_X86_64 */
+static inline int xstate_request_perm(unsigned long idx, bool guest)
+{
+ return -EPERM;
+}
+#endif /* !CONFIG_X86_64 */
+
+u64 xstate_get_guest_group_perm(void)
+{
+ return xstate_get_group_perm(true);
+}
+EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm);
+
+/**
+ * fpu_xstate_prctl - xstate permission operations
+ * @tsk: Redundant pointer to current
+ * @option: A subfunction of arch_prctl()
+ * @arg2: option argument
+ * Return: 0 if successful; otherwise, an error code
+ *
+ * Option arguments:
+ *
+ * ARCH_GET_XCOMP_SUPP: Pointer to user space u64 to store the info
+ * ARCH_GET_XCOMP_PERM: Pointer to user space u64 to store the info
+ * ARCH_REQ_XCOMP_PERM: Facility number requested
+ *
+ * For facilities which require more than one XSTATE component, the request
+ * must be the highest state component number related to that facility,
+ * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and
+ * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18).
+ */
+long fpu_xstate_prctl(int option, unsigned long arg2)
+{
+ u64 __user *uptr = (u64 __user *)arg2;
+ u64 permitted, supported;
+ unsigned long idx = arg2;
+ bool guest = false;
+
+ switch (option) {
+ case ARCH_GET_XCOMP_SUPP:
+ supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features;
+ return put_user(supported, uptr);
+
+ case ARCH_GET_XCOMP_PERM:
+ /*
+ * Lockless snapshot as it can also change right after the
+ * dropping the lock.
+ */
+ permitted = xstate_get_host_group_perm();
+ permitted &= XFEATURE_MASK_USER_SUPPORTED;
+ return put_user(permitted, uptr);
+
+ case ARCH_GET_XCOMP_GUEST_PERM:
+ permitted = xstate_get_guest_group_perm();
+ permitted &= XFEATURE_MASK_USER_SUPPORTED;
+ return put_user(permitted, uptr);
+
+ case ARCH_REQ_XCOMP_GUEST_PERM:
+ guest = true;
+ fallthrough;
+
+ case ARCH_REQ_XCOMP_PERM:
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return -EOPNOTSUPP;
+
+ return xstate_request_perm(idx, guest);
+
+ default:
+ return -EINVAL;
+ }
+}
+
+#ifdef CONFIG_PROC_PID_ARCH_STATUS
+/*
+ * Report the amount of time elapsed in millisecond since last AVX512
+ * use in the task.
+ */
+static void avx512_status(struct seq_file *m, struct task_struct *task)
+{
+ unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+ long delta;
+
+ if (!timestamp) {
+ /*
+ * Report -1 if no AVX512 usage
+ */
+ delta = -1;
+ } else {
+ delta = (long)(jiffies - timestamp);
+ /*
+ * Cap to LONG_MAX if time difference > LONG_MAX
+ */
+ if (delta < 0)
+ delta = LONG_MAX;
+ delta = jiffies_to_msecs(delta);
+ }
+
+ seq_put_decimal_ll(m, "AVX512_elapsed_ms:\t", delta);
+ seq_putc(m, '\n');
+}
+
+/*
+ * Report architecture specific information
+ */
+int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
+{
+ /*
+ * Report AVX512 state if the processor and build option supported.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_AVX512F))
+ avx512_status(m, task);
+
+ return 0;
+}
+#endif /* CONFIG_PROC_PID_ARCH_STATUS */
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
new file mode 100644
index 000000000..3518fb26d
--- /dev/null
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -0,0 +1,327 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_KERNEL_FPU_XSTATE_H
+#define __X86_KERNEL_FPU_XSTATE_H
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/xstate.h>
+#include <asm/fpu/xcr.h>
+
+#ifdef CONFIG_X86_64
+DECLARE_PER_CPU(u64, xfd_state);
+#endif
+
+static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask)
+{
+ /*
+ * XRSTORS requires these bits set in xcomp_bv, or it will
+ * trigger #GP:
+ */
+ if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED))
+ xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT;
+}
+
+static inline u64 xstate_get_group_perm(bool guest)
+{
+ struct fpu *fpu = &current->group_leader->thread.fpu;
+ struct fpu_state_perm *perm;
+
+ /* Pairs with WRITE_ONCE() in xstate_request_perm() */
+ perm = guest ? &fpu->guest_perm : &fpu->perm;
+ return READ_ONCE(perm->__state_perm);
+}
+
+static inline u64 xstate_get_host_group_perm(void)
+{
+ return xstate_get_group_perm(false);
+}
+
+enum xstate_copy_mode {
+ XSTATE_COPY_FP,
+ XSTATE_COPY_FX,
+ XSTATE_COPY_XSAVE,
+};
+
+struct membuf;
+extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
+ u64 xfeatures, u32 pkru_val,
+ enum xstate_copy_mode copy_mode);
+extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
+ enum xstate_copy_mode mode);
+extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
+extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf);
+
+
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system_xstate(unsigned int legacy_size);
+
+extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+
+static inline u64 xfeatures_mask_supervisor(void)
+{
+ return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
+}
+
+static inline u64 xfeatures_mask_independent(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR))
+ return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR;
+
+ return XFEATURE_MASK_INDEPENDENT;
+}
+
+/* XSAVE/XRSTOR wrapper functions */
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX "0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVEC ".byte " REX_PREFIX "0x0f,0xc7,0x27"
+#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/*
+ * After this @err contains 0 on success or the trap number when the
+ * operation raises an exception.
+ */
+#define XSTATE_OP(op, st, lmask, hmask, err) \
+ asm volatile("1:" op "\n\t" \
+ "xor %[err], %[err]\n" \
+ "2:\n\t" \
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \
+ : [err] "=a" (err) \
+ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
+ : "memory")
+
+/*
+ * If XSAVES is enabled, it replaces XSAVEC because it supports supervisor
+ * states in addition to XSAVEC.
+ *
+ * Otherwise if XSAVEC is enabled, it replaces XSAVEOPT because it supports
+ * compacted storage format in addition to XSAVEOPT.
+ *
+ * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
+ * supports modified optimization which is not supported by XSAVE.
+ *
+ * We use XSAVE as a fallback.
+ *
+ * The 661 label is defined in the ALTERNATIVE* macros as the address of the
+ * original instruction which gets replaced. We need to use it here as the
+ * address of the instruction where we might get an exception at.
+ */
+#define XSTATE_XSAVE(st, lmask, hmask, err) \
+ asm volatile(ALTERNATIVE_3(XSAVE, \
+ XSAVEOPT, X86_FEATURE_XSAVEOPT, \
+ XSAVEC, X86_FEATURE_XSAVEC, \
+ XSAVES, X86_FEATURE_XSAVES) \
+ "\n" \
+ "xor %[err], %[err]\n" \
+ "3:\n" \
+ _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
+ : [err] "=r" (err) \
+ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
+ : "memory")
+
+/*
+ * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
+ * XSAVE area format.
+ */
+#define XSTATE_XRESTORE(st, lmask, hmask) \
+ asm volatile(ALTERNATIVE(XRSTOR, \
+ XRSTORS, X86_FEATURE_XSAVES) \
+ "\n" \
+ "3:\n" \
+ _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE) \
+ : \
+ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
+ : "memory")
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU)
+extern void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor);
+#else
+static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { }
+#endif
+
+#ifdef CONFIG_X86_64
+static inline void xfd_update_state(struct fpstate *fpstate)
+{
+ if (fpu_state_size_dynamic()) {
+ u64 xfd = fpstate->xfd;
+
+ if (__this_cpu_read(xfd_state) != xfd) {
+ wrmsrl(MSR_IA32_XFD, xfd);
+ __this_cpu_write(xfd_state, xfd);
+ }
+ }
+}
+
+extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu);
+#else
+static inline void xfd_update_state(struct fpstate *fpstate) { }
+
+static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) {
+ return -EPERM;
+}
+#endif
+
+/*
+ * Save processor xstate to xsave area.
+ *
+ * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features
+ * and command line options. The choice is permanent until the next reboot.
+ */
+static inline void os_xsave(struct fpstate *fpstate)
+{
+ u64 mask = fpstate->xfeatures;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ WARN_ON_FPU(!alternatives_patched);
+ xfd_validate_state(fpstate, mask, false);
+
+ XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err);
+
+ /* We should never fault when copying to a kernel buffer: */
+ WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ *
+ * Uses XRSTORS when XSAVES is used, XRSTOR otherwise.
+ */
+static inline void os_xrstor(struct fpstate *fpstate, u64 mask)
+{
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+
+ xfd_validate_state(fpstate, mask, true);
+ XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask);
+}
+
+/* Restore of supervisor state. Does not require XFD */
+static inline void os_xrstor_supervisor(struct fpstate *fpstate)
+{
+ u64 mask = xfeatures_mask_supervisor();
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+
+ XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask);
+}
+
+/*
+ * XSAVE itself always writes all requested xfeatures. Removing features
+ * from the request bitmap reduces the features which are written.
+ * Generate a mask of features which must be written to a sigframe. The
+ * unset features can be optimized away and not written.
+ *
+ * This optimization is user-visible. Only use for states where
+ * uninitialized sigframe contents are tolerable, like dynamic features.
+ *
+ * Users of buffers produced with this optimization must check XSTATE_BV
+ * to determine which features have been optimized out.
+ */
+static inline u64 xfeatures_need_sigframe_write(void)
+{
+ u64 xfeaures_to_write;
+
+ /* In-use features must be written: */
+ xfeaures_to_write = xfeatures_in_use();
+
+ /* Also write all non-optimizable sigframe features: */
+ xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED &
+ ~XFEATURE_MASK_SIGFRAME_INITOPT;
+
+ return xfeaures_to_write;
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for backward compatibility for
+ * old applications which don't understand the compacted format of the
+ * xsave area.
+ *
+ * The caller has to zero buf::header before calling this because XSAVE*
+ * does not touch the reserved fields in the header.
+ */
+static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
+{
+ /*
+ * Include the features which are not xsaved/rstored by the kernel
+ * internally, e.g. PKRU. That's user space ABI and also required
+ * to allow the signal handler to modify PKRU.
+ */
+ struct fpstate *fpstate = current->thread.fpu.fpstate;
+ u64 mask = fpstate->user_xfeatures;
+ u32 lmask;
+ u32 hmask;
+ int err;
+
+ /* Optimize away writing unnecessary xfeatures: */
+ if (fpu_state_size_dynamic())
+ mask &= xfeatures_need_sigframe_write();
+
+ lmask = mask;
+ hmask = mask >> 32;
+ xfd_validate_state(fpstate, mask, false);
+
+ stac();
+ XSTATE_OP(XSAVE, buf, lmask, hmask, err);
+ clac();
+
+ return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask)
+{
+ struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ xfd_validate_state(current->thread.fpu.fpstate, mask, true);
+
+ stac();
+ XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+ clac();
+
+ return err;
+}
+
+/*
+ * Restore xstate from kernel space xsave area, return an error code instead of
+ * an exception.
+ */
+static inline int os_xrstor_safe(struct fpstate *fpstate, u64 mask)
+{
+ struct xregs_state *xstate = &fpstate->regs.xsave;
+ u32 lmask = mask;
+ u32 hmask = mask >> 32;
+ int err;
+
+ /* Ensure that XFD is up to date */
+ xfd_update_state(fpstate);
+
+ if (cpu_feature_enabled(X86_FEATURE_XSAVES))
+ XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+ else
+ XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
+
+ return err;
+}
+
+
+#endif