Merge branch 'x86/fpu' into x86/smap
Reason for merge:
x86/fpu changed the structure of some of the code that x86/smap
changes; mostly fpu-internal.h but also minor changes to the
signal code.
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Resolved Conflicts:
arch/x86/ia32/ia32_signal.c
arch/x86/include/asm/fpu-internal.h
arch/x86/kernel/signal.c
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c97bb7b..d0e910d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -165,10 +165,15 @@
print_cpu_info(&boot_cpu_data);
#endif
check_config();
- check_fpu();
check_hlt();
check_popad();
init_utsname()->machine[1] =
'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
+
+ /*
+ * kernel_fpu_begin/end() in check_fpu() relies on the patched
+ * alternative instructions.
+ */
+ check_fpu();
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7d35d65..44aec5d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1324,7 +1324,6 @@
dbg_restore_debug_regs();
fpu_init();
- xsave_init();
raw_local_save_flags(kernel_eflags);
@@ -1379,6 +1378,5 @@
dbg_restore_debug_regs();
fpu_init();
- xsave_init();
}
#endif
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index f250431..675a050 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -19,24 +19,17 @@
#include <asm/fpu-internal.h>
#include <asm/user.h>
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-#else
-# define save_i387_xstate_ia32 save_i387_xstate
-# define restore_i387_xstate_ia32 restore_i387_xstate
-# define _fpstate_ia32 _fpstate
-# define _xstate_ia32 _xstate
-# define sig_xstate_ia32_size sig_xstate_size
-# define fx_sw_reserved_ia32 fx_sw_reserved
-# define user_i387_ia32_struct user_i387_struct
-# define user32_fxsr_struct user_fxsr_struct
-#endif
-
/*
* Were we in an interrupt that interrupted kernel mode?
*
- * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * For now, with eagerfpu we will return interrupted kernel FPU
+ * state as not-idle. TBD: Ideally we can change the return value
+ * to something like __thread_has_fpu(current). But we need to
+ * be careful of doing __thread_clear_has_fpu() before saving
+ * the FPU etc for supporting nested uses etc. For now, take
+ * the simple route!
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
* pair does nothing at all: the thread must not have fpu (so
* that we don't try to save the FPU state), and TS must
* be set (so that the clts/stts pair does nothing that is
@@ -44,6 +37,9 @@
*/
static inline bool interrupted_kernel_fpu_idle(void)
{
+ if (use_eager_fpu())
+ return 0;
+
return !__thread_has_fpu(current) &&
(read_cr0() & X86_CR0_TS);
}
@@ -77,29 +73,29 @@
}
EXPORT_SYMBOL(irq_fpu_usable);
-void kernel_fpu_begin(void)
+void __kernel_fpu_begin(void)
{
struct task_struct *me = current;
- WARN_ON_ONCE(!irq_fpu_usable());
- preempt_disable();
if (__thread_has_fpu(me)) {
__save_init_fpu(me);
__thread_clear_has_fpu(me);
- /* We do 'stts()' in kernel_fpu_end() */
- } else {
+ /* We do 'stts()' in __kernel_fpu_end() */
+ } else if (!use_eager_fpu()) {
this_cpu_write(fpu_owner_task, NULL);
clts();
}
}
-EXPORT_SYMBOL(kernel_fpu_begin);
+EXPORT_SYMBOL(__kernel_fpu_begin);
-void kernel_fpu_end(void)
+void __kernel_fpu_end(void)
{
- stts();
- preempt_enable();
+ if (use_eager_fpu())
+ math_state_restore();
+ else
+ stts();
}
-EXPORT_SYMBOL(kernel_fpu_end);
+EXPORT_SYMBOL(__kernel_fpu_end);
void unlazy_fpu(struct task_struct *tsk)
{
@@ -113,23 +109,15 @@
}
EXPORT_SYMBOL(unlazy_fpu);
-#ifdef CONFIG_MATH_EMULATION
-# define HAVE_HWFP (boot_cpu_data.hard_math)
-#else
-# define HAVE_HWFP 1
-#endif
-
-static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
unsigned int xstate_size;
EXPORT_SYMBOL_GPL(xstate_size);
-unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
static struct i387_fxsave_struct fx_scratch __cpuinitdata;
static void __cpuinit mxcsr_feature_mask_init(void)
{
unsigned long mask = 0;
- clts();
if (cpu_has_fxsr) {
memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
asm volatile("fxsave %0" : : "m" (fx_scratch));
@@ -138,7 +126,6 @@
mask = 0x0000ffbf;
}
mxcsr_feature_mask &= mask;
- stts();
}
static void __cpuinit init_thread_xstate(void)
@@ -192,9 +179,8 @@
init_thread_xstate();
mxcsr_feature_mask_init();
- /* clean state in init */
- current_thread_info()->status = 0;
- clear_used_math();
+ xsave_init();
+ eager_fpu_init();
}
void fpu_finit(struct fpu *fpu)
@@ -205,12 +191,7 @@
}
if (cpu_has_fxsr) {
- struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
- memset(fx, 0, xstate_size);
- fx->cwd = 0x37f;
- if (cpu_has_xmm)
- fx->mxcsr = MXCSR_DEFAULT;
+ fx_finit(&fpu->state->fxsave);
} else {
struct i387_fsave_struct *fp = &fpu->state->fsave;
memset(fp, 0, xstate_size);
@@ -454,7 +435,7 @@
* FXSR floating point environment conversions.
*/
-static void
+void
convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
{
struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -491,8 +472,8 @@
memcpy(&to[i], &from[i], sizeof(to[0]));
}
-static void convert_to_fxsr(struct task_struct *tsk,
- const struct user_i387_ia32_struct *env)
+void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env)
{
struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -589,223 +570,6 @@
}
/*
- * Signal frame handlers.
- */
-
-static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
- struct task_struct *tsk = current;
- struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave;
-
- fp->status = fp->swd;
- if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct)))
- return -1;
- return 1;
-}
-
-static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
-{
- struct task_struct *tsk = current;
- struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
- struct user_i387_ia32_struct env;
- int err = 0;
-
- convert_from_fxsr(&env, tsk);
- if (__copy_to_user(buf, &env, sizeof(env)))
- return -1;
-
- err |= __put_user(fx->swd, &buf->status);
- err |= __put_user(X86_FXSR_MAGIC, &buf->magic);
- if (err)
- return -1;
-
- if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size))
- return -1;
- return 1;
-}
-
-static int save_i387_xsave(void __user *buf)
-{
- struct task_struct *tsk = current;
- struct _fpstate_ia32 __user *fx = buf;
- int err = 0;
-
-
- sanitize_i387_state(tsk);
-
- /*
- * 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
- * xstate_bv in the xsave header.
- *
- * xsave aware applications can change the xstate_bv in the xsave
- * header as well as change any contents in the memory layout.
- * xrestore as part of sigreturn will capture all the changes.
- */
- tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
- if (save_i387_fxsave(fx) < 0)
- return -1;
-
- err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32,
- sizeof(struct _fpx_sw_bytes));
- err |= __put_user(FP_XSTATE_MAGIC2,
- (__u32 __user *) (buf + sig_xstate_ia32_size
- - FP_XSTATE_MAGIC2_SIZE));
- if (err)
- return -1;
-
- return 1;
-}
-
-int save_i387_xstate_ia32(void __user *buf)
-{
- struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
- struct task_struct *tsk = current;
-
- if (!used_math())
- return 0;
-
- if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size))
- return -EACCES;
- /*
- * This will cause a "finit" to be triggered by the next
- * attempted FPU operation by the 'current' process.
- */
- clear_used_math();
-
- if (!HAVE_HWFP) {
- return fpregs_soft_get(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, fp) ? -1 : 1;
- }
-
- unlazy_fpu(tsk);
-
- if (cpu_has_xsave)
- return save_i387_xsave(fp);
- if (cpu_has_fxsr)
- return save_i387_fxsave(fp);
- else
- return save_i387_fsave(fp);
-}
-
-static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
- struct task_struct *tsk = current;
-
- return __copy_from_user(&tsk->thread.fpu.state->fsave, buf,
- sizeof(struct i387_fsave_struct));
-}
-
-static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf,
- unsigned int size)
-{
- struct task_struct *tsk = current;
- struct user_i387_ia32_struct env;
- int err;
-
- err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0],
- size);
- /* mxcsr reserved bits must be masked to zero for security reasons */
- tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
- if (err || __copy_from_user(&env, buf, sizeof(env)))
- return 1;
- convert_to_fxsr(tsk, &env);
-
- return 0;
-}
-
-static int restore_i387_xsave(void __user *buf)
-{
- struct _fpx_sw_bytes fx_sw_user;
- struct _fpstate_ia32 __user *fx_user =
- ((struct _fpstate_ia32 __user *) buf);
- struct i387_fxsave_struct __user *fx =
- (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0];
- struct xsave_hdr_struct *xsave_hdr =
- ¤t->thread.fpu.state->xsave.xsave_hdr;
- u64 mask;
- int err;
-
- if (check_for_xstate(fx, buf, &fx_sw_user))
- goto fx_only;
-
- mask = fx_sw_user.xstate_bv;
-
- err = restore_i387_fxsave(buf, fx_sw_user.xstate_size);
-
- xsave_hdr->xstate_bv &= pcntxt_mask;
- /*
- * These bits must be zero.
- */
- xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
-
- /*
- * Init the state that is not present in the memory layout
- * and enabled by the OS.
- */
- mask = ~(pcntxt_mask & ~mask);
- xsave_hdr->xstate_bv &= mask;
-
- return err;
-fx_only:
- /*
- * Couldn't find the extended state information in the memory
- * layout. Restore the FP/SSE and init the other extended state
- * enabled by the OS.
- */
- xsave_hdr->xstate_bv = XSTATE_FPSSE;
- return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct));
-}
-
-int restore_i387_xstate_ia32(void __user *buf)
-{
- int err;
- struct task_struct *tsk = current;
- struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
-
- if (HAVE_HWFP)
- clear_fpu(tsk);
-
- if (!buf) {
- if (used_math()) {
- clear_fpu(tsk);
- clear_used_math();
- }
-
- return 0;
- } else
- if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size))
- return -EACCES;
-
- if (!used_math()) {
- err = init_fpu(tsk);
- if (err)
- return err;
- }
-
- if (HAVE_HWFP) {
- if (cpu_has_xsave)
- err = restore_i387_xsave(buf);
- else if (cpu_has_fxsr)
- err = restore_i387_fxsave(fp, sizeof(struct
- i387_fxsave_struct));
- else
- err = restore_i387_fsave(fp);
- } else {
- err = fpregs_soft_set(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, fp) != 0;
- }
- set_used_math();
-
- return err;
-}
-
-/*
* FPU state for core dumps.
* This is only used for a.out dumps now.
* It is declared generically using elf_fpregset_t (which is
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 0bc72e2..d5f15c3 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -150,7 +150,7 @@
return oprom;
}
-void *pci_map_biosrom(struct pci_dev *pdev)
+void __iomem *pci_map_biosrom(struct pci_dev *pdev)
{
struct resource *oprom = find_oprom(pdev);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ef6a845..dc3567e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -66,15 +66,13 @@
{
int ret;
- unlazy_fpu(src);
-
*dst = *src;
if (fpu_allocated(&src->thread.fpu)) {
memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
ret = fpu_alloc(&dst->thread.fpu);
if (ret)
return ret;
- fpu_copy(&dst->thread.fpu, &src->thread.fpu);
+ fpu_copy(dst, src);
}
return 0;
}
@@ -97,16 +95,6 @@
SLAB_PANIC | SLAB_NOTRACK, NULL);
}
-static inline void drop_fpu(struct task_struct *tsk)
-{
- /*
- * Forget coprocessor state..
- */
- tsk->fpu_counter = 0;
- clear_fpu(tsk);
- clear_used_math();
-}
-
/*
* Free current thread data structures etc..
*/
@@ -163,7 +151,13 @@
flush_ptrace_hw_breakpoint(tsk);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
- drop_fpu(tsk);
+ drop_init_fpu(tsk);
+ /*
+ * Free the FPU state for non xsave platforms. They get reallocated
+ * lazily at the first use.
+ */
+ if (!use_eager_fpu())
+ free_thread_xstate(tsk);
}
static void hard_disable_TSC(void)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 516fa18..b9ff83c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -190,10 +190,6 @@
regs->cs = __USER_CS;
regs->ip = new_ip;
regs->sp = new_sp;
- /*
- * Free the old FP and other extended state
- */
- free_thread_xstate(current);
}
EXPORT_SYMBOL_GPL(start_thread);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 0a980c9..8a6d20c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -232,10 +232,6 @@
regs->cs = _cs;
regs->ss = _ss;
regs->flags = X86_EFLAGS_IF;
- /*
- * Free the old FP and other extended state
- */
- free_thread_xstate(current);
}
void
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index c4c6a5c..861a9d1 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1332,9 +1332,6 @@
#define genregs32_get genregs_get
#define genregs32_set genregs_set
-#define user_i387_ia32_struct user_i387_struct
-#define user32_fxsr_struct user_fxsr_struct
-
#endif /* CONFIG_X86_64 */
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 9326128..036bddb 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -118,7 +118,7 @@
get_user_ex(*pax, &sc->ax);
} get_user_catch(err);
- err |= restore_i387_xstate(buf);
+ err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
return err;
}
@@ -207,35 +207,32 @@
void __user **fpstate)
{
/* Default to using normal stack */
+ unsigned long math_size = 0;
unsigned long sp = regs->sp;
+ unsigned long buf_fx = 0;
int onsigstack = on_sig_stack(sp);
-#ifdef CONFIG_X86_64
/* redzone */
- sp -= 128;
-#endif /* CONFIG_X86_64 */
+ if (config_enabled(CONFIG_X86_64))
+ sp -= 128;
if (!onsigstack) {
/* This is the X/Open sanctioned signal stack switching. */
if (ka->sa.sa_flags & SA_ONSTACK) {
if (current->sas_ss_size)
sp = current->sas_ss_sp + current->sas_ss_size;
- } else {
-#ifdef CONFIG_X86_32
- /* This is the legacy signal stack switching. */
- if ((regs->ss & 0xffff) != __USER_DS &&
- !(ka->sa.sa_flags & SA_RESTORER) &&
- ka->sa.sa_restorer)
+ } else if (config_enabled(CONFIG_X86_32) &&
+ (regs->ss & 0xffff) != __USER_DS &&
+ !(ka->sa.sa_flags & SA_RESTORER) &&
+ ka->sa.sa_restorer) {
+ /* This is the legacy signal stack switching. */
sp = (unsigned long) ka->sa.sa_restorer;
-#endif /* CONFIG_X86_32 */
}
}
if (used_math()) {
- sp -= sig_xstate_size;
-#ifdef CONFIG_X86_64
- sp = round_down(sp, 64);
-#endif /* CONFIG_X86_64 */
+ sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+ &buf_fx, &math_size);
*fpstate = (void __user *)sp;
}
@@ -248,8 +245,9 @@
if (onsigstack && !likely(on_sig_stack(sp)))
return (void __user *)-1L;
- /* save i387 state */
- if (used_math() && save_i387_xstate(*fpstate) < 0)
+ /* save i387 and extended state */
+ if (used_math() &&
+ save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
return (void __user *)-1L;
return (void __user *)sp;
@@ -385,7 +383,7 @@
*/
put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
} put_user_catch(err);
-
+
err |= copy_siginfo_to_user(&frame->info, info);
err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
regs, set->sig[0]);
@@ -477,6 +475,75 @@
}
#endif /* CONFIG_X86_32 */
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+ siginfo_t *info, compat_sigset_t *set,
+ struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_X32_ABI
+ struct rt_sigframe_x32 __user *frame;
+ void __user *restorer;
+ int err = 0;
+ void __user *fpstate = NULL;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ return -EFAULT;
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ if (copy_siginfo_to_user32(&frame->info, info))
+ return -EFAULT;
+ }
+
+ put_user_try {
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ put_user_ex(0, &frame->uc.uc__pad0);
+
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ restorer = ka->sa.sa_restorer;
+ } else {
+ /* could use a vstub here */
+ restorer = NULL;
+ err |= -EFAULT;
+ }
+ put_user_ex(restorer, &frame->pretcode);
+ } put_user_catch(err);
+
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+ if (err)
+ return -EFAULT;
+
+ /* Set up registers for signal handler */
+ regs->sp = (unsigned long) frame;
+ regs->ip = (unsigned long) ka->sa.sa_handler;
+
+ /* We use the x32 calling convention here... */
+ regs->di = sig;
+ regs->si = (unsigned long) &frame->info;
+ regs->dx = (unsigned long) &frame->uc;
+
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+
+ regs->cs = __USER_CS;
+ regs->ss = __USER_DS;
+#endif /* CONFIG_X86_X32_ABI */
+
+ return 0;
+}
+
#ifdef CONFIG_X86_32
/*
* Atomically swap in the new signal mask, and wait for a signal.
@@ -615,55 +682,22 @@
return sig;
}
-#ifdef CONFIG_X86_32
-
-#define is_ia32 1
-#define ia32_setup_frame __setup_frame
-#define ia32_setup_rt_frame __setup_rt_frame
-
-#else /* !CONFIG_X86_32 */
-
-#ifdef CONFIG_IA32_EMULATION
-#define is_ia32 test_thread_flag(TIF_IA32)
-#else /* !CONFIG_IA32_EMULATION */
-#define is_ia32 0
-#endif /* CONFIG_IA32_EMULATION */
-
-#ifdef CONFIG_X86_X32_ABI
-#define is_x32 test_thread_flag(TIF_X32)
-
-static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
- siginfo_t *info, compat_sigset_t *set,
- struct pt_regs *regs);
-#else /* !CONFIG_X86_X32_ABI */
-#define is_x32 0
-#endif /* CONFIG_X86_X32_ABI */
-
-int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
- sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct k_sigaction *ka,
- sigset_t *set, struct pt_regs *regs);
-
-#endif /* CONFIG_X86_32 */
-
static int
setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
struct pt_regs *regs)
{
int usig = signr_convert(sig);
sigset_t *set = sigmask_to_save();
+ compat_sigset_t *cset = (compat_sigset_t *) set;
/* Set up the stack frame */
- if (is_ia32) {
+ if (is_ia32_frame()) {
if (ka->sa.sa_flags & SA_SIGINFO)
- return ia32_setup_rt_frame(usig, ka, info, set, regs);
+ return ia32_setup_rt_frame(usig, ka, info, cset, regs);
else
- return ia32_setup_frame(usig, ka, set, regs);
-#ifdef CONFIG_X86_X32_ABI
- } else if (is_x32) {
- return x32_setup_rt_frame(usig, ka, info,
- (compat_sigset_t *)set, regs);
-#endif
+ return ia32_setup_frame(usig, ka, cset, regs);
+ } else if (is_x32_frame()) {
+ return x32_setup_rt_frame(usig, ka, info, cset, regs);
} else {
return __setup_rt_frame(sig, ka, info, set, regs);
}
@@ -827,73 +861,6 @@
}
#ifdef CONFIG_X86_X32_ABI
-static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
- siginfo_t *info, compat_sigset_t *set,
- struct pt_regs *regs)
-{
- struct rt_sigframe_x32 __user *frame;
- void __user *restorer;
- int err = 0;
- void __user *fpstate = NULL;
-
- frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
-
- if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
- return -EFAULT;
-
- if (ka->sa.sa_flags & SA_SIGINFO) {
- if (copy_siginfo_to_user32(&frame->info, info))
- return -EFAULT;
- }
-
- put_user_try {
- /* Create the ucontext. */
- if (cpu_has_xsave)
- put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- put_user_ex(0, &frame->uc.uc_flags);
- put_user_ex(0, &frame->uc.uc_link);
- put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- put_user_ex(sas_ss_flags(regs->sp),
- &frame->uc.uc_stack.ss_flags);
- put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- put_user_ex(0, &frame->uc.uc__pad0);
-
- if (ka->sa.sa_flags & SA_RESTORER) {
- restorer = ka->sa.sa_restorer;
- } else {
- /* could use a vstub here */
- restorer = NULL;
- err |= -EFAULT;
- }
- put_user_ex(restorer, &frame->pretcode);
- } put_user_catch(err);
-
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
- if (err)
- return -EFAULT;
-
- /* Set up registers for signal handler */
- regs->sp = (unsigned long) frame;
- regs->ip = (unsigned long) ka->sa.sa_handler;
-
- /* We use the x32 calling convention here... */
- regs->di = sig;
- regs->si = (unsigned long) &frame->info;
- regs->dx = (unsigned long) &frame->uc;
-
- loadsegment(ds, __USER_DS);
- loadsegment(es, __USER_DS);
-
- regs->cs = __USER_CS;
- regs->ss = __USER_DS;
-
- return 0;
-}
-
asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
{
struct rt_sigframe_x32 __user *frame;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b481341..4f4aba0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -613,11 +613,12 @@
}
__thread_fpu_begin(tsk);
+
/*
* Paranoid restore. send a SIGSEGV if we fail to restore the state.
*/
if (unlikely(restore_fpu_checking(tsk))) {
- __thread_fpu_end(tsk);
+ drop_init_fpu(tsk);
force_sig(SIGSEGV, tsk);
return;
}
@@ -629,6 +630,8 @@
dotraplinkage void __kprobes
do_device_not_available(struct pt_regs *regs, long error_code)
{
+ BUG_ON(use_eager_fpu());
+
#ifdef CONFIG_MATH_EMULATION
if (read_cr0() & X86_CR0_EM) {
struct math_emu_info info = { };
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 3d3e207..4e89b3d 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -10,9 +10,7 @@
#include <linux/compat.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
-#ifdef CONFIG_IA32_EMULATION
-#include <asm/sigcontext32.h>
-#endif
+#include <asm/sigframe.h>
#include <asm/xcr.h>
/*
@@ -23,13 +21,9 @@
/*
* Represents init state for the supported extended state.
*/
-static struct xsave_struct *init_xstate_buf;
+struct xsave_struct *init_xstate_buf;
-struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-struct _fpx_sw_bytes fx_sw_reserved_ia32;
-#endif
-
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
/*
@@ -44,9 +38,9 @@
*/
void __sanitize_i387_state(struct task_struct *tsk)
{
- u64 xstate_bv;
- int feature_bit = 0x2;
struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
+ int feature_bit = 0x2;
+ u64 xstate_bv;
if (!fx)
return;
@@ -104,213 +98,326 @@
* Check for the presence of extended state information in the
* user fpstate pointer in the sigcontext.
*/
-int check_for_xstate(struct i387_fxsave_struct __user *buf,
- void __user *fpstate,
- struct _fpx_sw_bytes *fx_sw_user)
+static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
+ void __user *fpstate,
+ struct _fpx_sw_bytes *fx_sw)
{
int min_xstate_size = sizeof(struct i387_fxsave_struct) +
sizeof(struct xsave_hdr_struct);
unsigned int magic2;
- int err;
- err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0],
- sizeof(struct _fpx_sw_bytes));
- if (err)
- return -EFAULT;
+ if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+ return -1;
- /*
- * First Magic check failed.
- */
- if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1)
- return -EINVAL;
+ /* 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 > xstate_size ||
+ fx_sw->xstate_size > fx_sw->extended_size)
+ return -1;
/*
- * Check for error scenarios.
- */
- if (fx_sw_user->xstate_size < min_xstate_size ||
- fx_sw_user->xstate_size > xstate_size ||
- fx_sw_user->xstate_size > fx_sw_user->extended_size)
- return -EINVAL;
-
- err = __get_user(magic2, (__u32 *) (((void *)fpstate) +
- fx_sw_user->extended_size -
- FP_XSTATE_MAGIC2_SIZE));
- if (err)
- return err;
- /*
* 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 (magic2 != FP_XSTATE_MAGIC2)
- return -EFAULT;
+ if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+ || magic2 != FP_XSTATE_MAGIC2)
+ return -1;
return 0;
}
-#ifdef CONFIG_X86_64
/*
* Signal frame handlers.
*/
-
-int save_i387_xstate(void __user *buf)
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
{
- struct task_struct *tsk = current;
- int err = 0;
+ if (use_fxsr()) {
+ struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct user_i387_ia32_struct env;
+ struct _fpstate_ia32 __user *fp = buf;
- if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size))
- return -EACCES;
+ convert_from_fxsr(&env, tsk);
- BUG_ON(sig_xstate_size < xstate_size);
-
- if ((unsigned long)buf % 64)
- pr_err("%s: bad fpstate %p\n", __func__, buf);
-
- if (!used_math())
- return 0;
-
- if (user_has_fpu()) {
- if (use_xsave())
- err = xsave_user(buf);
- else
- err = fxsave_user(buf);
-
- if (err)
- return err;
- user_fpu_end();
+ if (__copy_to_user(buf, &env, sizeof(env)) ||
+ __put_user(xsave->i387.swd, &fp->status) ||
+ __put_user(X86_FXSR_MAGIC, &fp->magic))
+ return -1;
} else {
- sanitize_i387_state(tsk);
- if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
- xstate_size))
+ struct i387_fsave_struct __user *fp = buf;
+ u32 swd;
+ if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
return -1;
}
- clear_used_math(); /* trigger finit */
-
- if (use_xsave()) {
- struct _fpstate __user *fx = buf;
- struct _xstate __user *x = buf;
- u64 xstate_bv;
-
- err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
- sizeof(struct _fpx_sw_bytes));
-
- err |= __put_user(FP_XSTATE_MAGIC2,
- (__u32 __user *) (buf + sig_xstate_size
- - FP_XSTATE_MAGIC2_SIZE));
-
- /*
- * Read the xstate_bv which we copied (directly from the cpu or
- * from the state in task struct) to the user buffers and
- * set the FP/SSE bits.
- */
- err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv);
-
- /*
- * 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
- * xstate_bv in the xsave header.
- *
- * xsave aware apps can change the xstate_bv in the xsave
- * header as well as change any contents in the memory layout.
- * xrestore as part of sigreturn will capture all the changes.
- */
- xstate_bv |= XSTATE_FPSSE;
-
- err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv);
-
- if (err)
- return err;
- }
-
- return 1;
+ return 0;
}
-/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE
- * state.
- */
-static int restore_user_xstate(void __user *buf)
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
{
- struct _fpx_sw_bytes fx_sw_user;
- u64 mask;
+ struct xsave_struct __user *x = buf;
+ struct _fpx_sw_bytes *sw_bytes;
+ u32 xstate_bv;
int err;
- if (((unsigned long)buf % 64) ||
- check_for_xstate(buf, buf, &fx_sw_user))
- goto fx_only;
+ /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+ sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+ err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
- mask = fx_sw_user.xstate_bv;
-
- /*
- * restore the state passed by the user.
- */
- err = xrestore_user(buf, mask);
- if (err)
+ if (!use_xsave())
return err;
- /*
- * init the state skipped by the user.
- */
- mask = pcntxt_mask & ~mask;
- if (unlikely(mask))
- xrstor_state(init_xstate_buf, mask);
+ err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
- return 0;
-
-fx_only:
/*
- * couldn't find the extended state information in the
- * memory layout. Restore just the FP/SSE and init all
- * the other extended state.
+ * Read the xstate_bv which we copied (directly from the cpu or
+ * from the state in task struct) to the user buffers.
*/
- xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE);
- return fxrstor_checking((__force struct i387_fxsave_struct *)buf);
+ err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
+
+ /*
+ * 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
+ * xstate_bv in the xsave header.
+ *
+ * xsave aware apps can change the xstate_bv in the xsave
+ * header as well as change any contents in the memory layout.
+ * xrestore as part of sigreturn will capture all the changes.
+ */
+ xstate_bv |= XSTATE_FPSSE;
+
+ err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
+
+ return err;
+}
+
+static inline int save_user_xstate(struct xsave_struct __user *buf)
+{
+ int err;
+
+ if (use_xsave())
+ err = xsave_user(buf);
+ else if (use_fxsr())
+ err = fxsave_user((struct i387_fxsave_struct __user *) buf);
+ else
+ err = fsave_user((struct i387_fsave_struct __user *) buf);
+
+ if (unlikely(err) && __clear_user(buf, xstate_size))
+ err = -EFAULT;
+ return err;
}
/*
- * This restores directly out of user space. Exceptions are handled.
+ * 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.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * 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.
*/
-int restore_i387_xstate(void __user *buf)
+int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
{
+ struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave;
struct task_struct *tsk = current;
- int err = 0;
+ int ia32_fxstate = (buf != buf_fx);
+
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
+
+ if (!access_ok(VERIFY_WRITE, buf, size))
+ return -EACCES;
+
+ if (!HAVE_HWFP)
+ return fpregs_soft_get(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct), NULL,
+ (struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+ if (user_has_fpu()) {
+ /* Save the live register state to the user directly. */
+ if (save_user_xstate(buf_fx))
+ return -1;
+ /* Update the thread's fxstate to save the fsave header. */
+ if (ia32_fxstate)
+ fpu_fxsave(&tsk->thread.fpu);
+ } else {
+ sanitize_i387_state(tsk);
+ if (__copy_to_user(buf_fx, xsave, xstate_size))
+ return -1;
+ }
+
+ /* Save the fsave header for the 32-bit frames. */
+ if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+ return -1;
+
+ if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+ return -1;
+
+ drop_init_fpu(tsk); /* trigger finit */
+
+ return 0;
+}
+
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+ struct user_i387_ia32_struct *ia32_env,
+ u64 xstate_bv, int fx_only)
+{
+ struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
+
+ if (use_xsave()) {
+ /* These bits must be zero. */
+ xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+
+ /*
+ * Init the state that is not present in the memory
+ * layout and not enabled by the OS.
+ */
+ if (fx_only)
+ xsave_hdr->xstate_bv = XSTATE_FPSSE;
+ else
+ xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
+ }
+
+ if (use_fxsr()) {
+ /*
+ * mscsr reserved bits must be masked to zero for security
+ * reasons.
+ */
+ xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+ convert_to_fxsr(tsk, ia32_env);
+ }
+}
+
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
+ */
+static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
+{
+ if (use_xsave()) {
+ if ((unsigned long)buf % 64 || fx_only) {
+ u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
+ xrstor_state(init_xstate_buf, init_bv);
+ return fxrstor_checking((__force void *) buf);
+ } else {
+ u64 init_bv = pcntxt_mask & ~xbv;
+ if (unlikely(init_bv))
+ xrstor_state(init_xstate_buf, init_bv);
+ return xrestore_user(buf, xbv);
+ }
+ } else if (use_fxsr()) {
+ return fxrstor_checking((__force void *) buf);
+ } else
+ return frstor_checking((__force void *) buf);
+}
+
+int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
+{
+ int ia32_fxstate = (buf != buf_fx);
+ struct task_struct *tsk = current;
+ int state_size = xstate_size;
+ u64 xstate_bv = 0;
+ int fx_only = 0;
+
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
if (!buf) {
- if (used_math())
- goto clear;
+ drop_init_fpu(tsk);
return 0;
- } else
- if (!access_ok(VERIFY_READ, buf, sig_xstate_size))
- return -EACCES;
-
- if (!used_math()) {
- err = init_fpu(tsk);
- if (err)
- return err;
}
- user_fpu_begin();
- if (use_xsave())
- err = restore_user_xstate(buf);
- else
- err = fxrstor_checking((__force struct i387_fxsave_struct *)
- buf);
- if (unlikely(err)) {
+ if (!access_ok(VERIFY_READ, buf, size))
+ return -EACCES;
+
+ if (!used_math() && init_fpu(tsk))
+ return -1;
+
+ if (!HAVE_HWFP) {
+ return fpregs_soft_set(current, NULL,
+ 0, sizeof(struct user_i387_ia32_struct),
+ NULL, buf) != 0;
+ }
+
+ if (use_xsave()) {
+ struct _fpx_sw_bytes fx_sw_user;
+ if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+ /*
+ * Couldn't find the extended state information in the
+ * memory layout. Restore just the FP/SSE and init all
+ * the other extended state.
+ */
+ state_size = sizeof(struct i387_fxsave_struct);
+ fx_only = 1;
+ } else {
+ state_size = fx_sw_user.xstate_size;
+ xstate_bv = fx_sw_user.xstate_bv;
+ }
+ }
+
+ if (ia32_fxstate) {
/*
- * Encountered an error while doing the restore from the
- * user buffer, clear the fpu state.
+ * For 32-bit frames with fxstate, copy the user state to the
+ * thread's fpu state, reconstruct fxstate from the fsave
+ * header. Sanitize the copied state etc.
*/
-clear:
- clear_fpu(tsk);
- clear_used_math();
+ struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct user_i387_ia32_struct env;
+ int err = 0;
+
+ /*
+ * Drop the current fpu which clears used_math(). This ensures
+ * that any context-switch during the copy of the new state,
+ * avoids the intermediate state from getting restored/saved.
+ * Thus avoiding the new restored state from getting corrupted.
+ * We will be ready to restore/save the state only after
+ * set_used_math() is again set.
+ */
+ drop_fpu(tsk);
+
+ if (__copy_from_user(xsave, buf_fx, state_size) ||
+ __copy_from_user(&env, buf, sizeof(env))) {
+ err = -1;
+ } else {
+ sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
+ set_used_math();
+ }
+
+ if (use_eager_fpu())
+ math_state_restore();
+
+ return err;
+ } else {
+ /*
+ * For 64-bit frames and 32-bit fsave frames, restore the user
+ * state to the registers directly (with exceptions handled).
+ */
+ user_fpu_begin();
+ if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
+ drop_init_fpu(tsk);
+ return -1;
+ }
}
- return err;
+
+ return 0;
}
-#endif
/*
* Prepare the SW reserved portion of the fxsave memory layout, indicating
@@ -321,31 +428,22 @@
*/
static void prepare_fx_sw_frame(void)
{
- int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) +
- FP_XSTATE_MAGIC2_SIZE;
+ int fsave_header_size = sizeof(struct i387_fsave_struct);
+ int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
- sig_xstate_size = sizeof(struct _fpstate) + size_extended;
-
-#ifdef CONFIG_IA32_EMULATION
- sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended;
-#endif
-
- memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved));
+ if (config_enabled(CONFIG_X86_32))
+ size += fsave_header_size;
fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
- fx_sw_reserved.extended_size = sig_xstate_size;
+ fx_sw_reserved.extended_size = size;
fx_sw_reserved.xstate_bv = pcntxt_mask;
fx_sw_reserved.xstate_size = xstate_size;
-#ifdef CONFIG_IA32_EMULATION
- memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved,
- sizeof(struct _fpx_sw_bytes));
- fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size;
-#endif
-}
-#ifdef CONFIG_X86_64
-unsigned int sig_xstate_size = sizeof(struct _fpstate);
-#endif
+ if (config_enabled(CONFIG_IA32_EMULATION)) {
+ fx_sw_reserved_ia32 = fx_sw_reserved;
+ fx_sw_reserved_ia32.extended_size += fsave_header_size;
+ }
+}
/*
* Enable the extended processor state save/restore feature
@@ -384,19 +482,21 @@
/*
* setup the xstate image representing the init state
*/
-static void __init setup_xstate_init(void)
+static void __init setup_init_fpu_buf(void)
{
- setup_xstate_features();
-
/*
* Setup init_xstate_buf to represent the init state of
* all the features managed by the xsave
*/
init_xstate_buf = alloc_bootmem_align(xstate_size,
__alignof__(struct xsave_struct));
- init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
+ fx_finit(&init_xstate_buf->i387);
- clts();
+ if (!cpu_has_xsave)
+ return;
+
+ setup_xstate_features();
+
/*
* Init all the features state with header_bv being 0x0
*/
@@ -406,9 +506,21 @@
* of any feature which is not represented by all zero's.
*/
xsave_state(init_xstate_buf, -1);
- stts();
}
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static int __init eager_fpu_setup(char *s)
+{
+ if (!strcmp(s, "on"))
+ eagerfpu = ENABLE;
+ else if (!strcmp(s, "off"))
+ eagerfpu = DISABLE;
+ else if (!strcmp(s, "auto"))
+ eagerfpu = AUTO;
+ return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
/*
* Enable and initialize the xsave feature.
*/
@@ -445,8 +557,11 @@
update_regset_xstate_info(xstate_size, pcntxt_mask);
prepare_fx_sw_frame();
+ setup_init_fpu_buf();
- setup_xstate_init();
+ /* Auto enable eagerfpu for xsaveopt */
+ if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+ eagerfpu = ENABLE;
pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n",
pcntxt_mask, xstate_size);
@@ -471,3 +586,43 @@
next_func = xstate_enable;
this_func();
}
+
+static inline void __init eager_fpu_init_bp(void)
+{
+ current->thread.fpu.state =
+ alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct));
+ if (!init_xstate_buf)
+ setup_init_fpu_buf();
+}
+
+void __cpuinit eager_fpu_init(void)
+{
+ static __refdata void (*boot_func)(void) = eager_fpu_init_bp;
+
+ clear_used_math();
+ current_thread_info()->status = 0;
+
+ if (eagerfpu == ENABLE)
+ setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+ if (!cpu_has_eager_fpu) {
+ stts();
+ return;
+ }
+
+ if (boot_func) {
+ boot_func();
+ boot_func = NULL;
+ }
+
+ /*
+ * This is same as math_state_restore(). But use_xsave() is
+ * not yet patched to use math_state_restore().
+ */
+ init_fpu(current);
+ __thread_fpu_begin(current);
+ if (cpu_has_xsave)
+ xrstor_state(init_xstate_buf, -1);
+ else
+ fxrstor_checking(&init_xstate_buf->i387);
+}