[PATCH 1/3] x86: Get rid of ->hard_math and all the FPU asm fu
From: Borislav Petkov
Date: Mon Apr 29 2013 - 10:04:52 EST
From: "H. Peter Anvin" <hpa@xxxxxxxxx>
Reimplement FPU detection code in C and drop old, not-so-recommended
detection method in asm. Move all the relevant stuff into i387.c where
it conceptually belongs. Finally drop cpuinfo_x86.hard_math.
[ hpa: huge thanks to Borislav for taking my original concept patch
and productizing it ]
[ Boris, note to self: do not use static_cpu_has before alternatives! ]
Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxx>
Link: http://lkml.kernel.org/r/1365436666-9837-2-git-send-email-bp@xxxxxxxxx
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxx>
---
arch/x86/include/asm/fpu-internal.h | 2 --
arch/x86/include/asm/processor.h | 3 +-
arch/x86/kernel/asm-offsets_32.c | 1 -
arch/x86/kernel/cpu/bugs.c | 21 ++-----------
arch/x86/kernel/cpu/common.c | 3 +-
arch/x86/kernel/cpu/cyrix.c | 2 +-
arch/x86/kernel/cpu/proc.c | 4 +--
arch/x86/kernel/head_32.S | 21 -------------
arch/x86/kernel/i387.c | 59 ++++++++++++++++++++++++++++++-------
arch/x86/kernel/xsave.c | 5 ++--
arch/x86/lguest/boot.c | 2 +-
arch/x86/xen/enlighten.c | 2 +-
12 files changed, 60 insertions(+), 65 deletions(-)
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index e25cc33ec54d..fb808d71cd70 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -62,10 +62,8 @@ extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
#define xstateregs_active fpregs_active
#ifdef CONFIG_MATH_EMULATION
-# define HAVE_HWFP (boot_cpu_data.hard_math)
extern void finit_soft_fpu(struct i387_soft_struct *soft);
#else
-# define HAVE_HWFP 1
static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
#endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 22224b3b43bb..578f8b1d6910 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -89,9 +89,9 @@ struct cpuinfo_x86 {
char wp_works_ok; /* It doesn't on 386's */
/* Problems on some 486Dx4's and old 386's: */
- char hard_math;
char rfu;
char pad0;
+ char pad1;
#else
/* Number of 4K pages in DTLB/ITLB combined(in pages): */
int x86_tlbsize;
@@ -164,6 +164,7 @@ extern const struct seq_operations cpuinfo_op;
#define cache_line_size() (boot_cpu_data.x86_cache_alignment)
extern void cpu_detect(struct cpuinfo_x86 *c);
+extern void __cpuinit fpu_detect(struct cpuinfo_x86 *c);
extern void early_cpu_init(void);
extern void identify_boot_cpu(void);
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 85d98ab15cdc..a8ff7f936649 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -28,7 +28,6 @@ void foo(void)
OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask);
- OFFSET(CPUINFO_hard_math, cpuinfo_x86, hard_math);
OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level);
OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability);
OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4112be9a4659..03445346ee0a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -17,15 +17,6 @@
#include <asm/paravirt.h>
#include <asm/alternative.h>
-static int __init no_387(char *s)
-{
- boot_cpu_data.hard_math = 0;
- write_cr0(X86_CR0_TS | X86_CR0_EM | X86_CR0_MP | read_cr0());
- return 1;
-}
-
-__setup("no387", no_387);
-
static double __initdata x = 4195835.0;
static double __initdata y = 3145727.0;
@@ -44,15 +35,6 @@ static void __init check_fpu(void)
{
s32 fdiv_bug;
- if (!boot_cpu_data.hard_math) {
-#ifndef CONFIG_MATH_EMULATION
- pr_emerg("No coprocessor found and no math emulation present\n");
- pr_emerg("Giving up\n");
- for (;;) ;
-#endif
- return;
- }
-
kernel_fpu_begin();
/*
@@ -107,5 +89,6 @@ void __init check_bugs(void)
* kernel_fpu_begin/end() in check_fpu() relies on the patched
* alternative instructions.
*/
- check_fpu();
+ if (cpu_has_fpu)
+ check_fpu();
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 22018f70a671..d4dd99350e9d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -711,10 +711,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
return;
cpu_detect(c);
-
get_cpu_vendor(c);
-
get_cpu_cap(c);
+ fpu_detect(c);
if (this_cpu->c_early_init)
this_cpu->c_early_init(c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index d048d5ca43c1..7582f475b163 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -333,7 +333,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
switch (dir0_lsn) {
case 0xd: /* either a 486SLC or DLC w/o DEVID */
dir0_msn = 0;
- p = Cx486_name[(c->hard_math) ? 1 : 0];
+ p = Cx486_name[(cpu_has_fpu ? 1 : 0)];
break;
case 0xe: /* a 486S A step */
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 37a198bd48c8..aee6317b902f 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -37,8 +37,8 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
- c->hard_math ? "yes" : "no",
- c->hard_math ? "yes" : "no",
+ static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+ static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
c->cpuid_level,
c->wp_works_ok ? "yes" : "no");
}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 73afd11799ca..e65ddc62e113 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -444,7 +444,6 @@ is486:
orl %ecx,%eax
movl %eax,%cr0
- call check_x87
lgdt early_gdt_descr
lidt idt_descr
ljmp $(__KERNEL_CS),$1f
@@ -467,26 +466,6 @@ is486:
pushl $0 # fake return address for unwinder
jmp *(initial_code)
-/*
- * We depend on ET to be correct. This checks for 287/387.
- */
-check_x87:
- movb $0,X86_HARD_MATH
- clts
- fninit
- fstsw %ax
- cmpb $0,%al
- je 1f
- movl %cr0,%eax /* no coprocessor: have to set bits */
- xorl $4,%eax /* set EM */
- movl %eax,%cr0
- ret
- ALIGN
-1: movb $1,X86_HARD_MATH
- .byte 0xDB,0xE4 /* fsetpm for 287, ignored by 387 */
- ret
-
-
#include "verify_cpu.S"
/*
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 245a71db401a..5d8b07c9db63 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -135,7 +135,7 @@ static void __cpuinit init_thread_xstate(void)
* xsave_init().
*/
- if (!HAVE_HWFP) {
+ if (!cpu_has_fpu) {
/*
* Disable xsave as we do not support it if i387
* emulation is enabled.
@@ -162,6 +162,14 @@ void __cpuinit fpu_init(void)
unsigned long cr0;
unsigned long cr4_mask = 0;
+#ifndef CONFIG_MATH_EMULATION
+ if (!cpu_has_fpu) {
+ pr_emerg("No FPU found and no math emulation present\n");
+ pr_emerg("Giving up\n");
+ for (;;)
+ asm volatile("hlt");
+ }
+#endif
if (cpu_has_fxsr)
cr4_mask |= X86_CR4_OSFXSR;
if (cpu_has_xmm)
@@ -171,7 +179,7 @@ void __cpuinit fpu_init(void)
cr0 = read_cr0();
cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
- if (!HAVE_HWFP)
+ if (!cpu_has_fpu)
cr0 |= X86_CR0_EM;
write_cr0(cr0);
@@ -189,7 +197,7 @@ void __cpuinit fpu_init(void)
void fpu_finit(struct fpu *fpu)
{
- if (!HAVE_HWFP) {
+ if (!cpu_has_fpu) {
finit_soft_fpu(&fpu->state->soft);
return;
}
@@ -218,7 +226,7 @@ int init_fpu(struct task_struct *tsk)
int ret;
if (tsk_used_math(tsk)) {
- if (HAVE_HWFP && tsk == current)
+ if (cpu_has_fpu && tsk == current)
unlazy_fpu(tsk);
tsk->thread.fpu.last_cpu = ~0;
return 0;
@@ -515,14 +523,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
if (ret)
return ret;
- if (!HAVE_HWFP)
+ if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
- if (!cpu_has_fxsr) {
+ if (!cpu_has_fxsr)
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
&target->thread.fpu.state->fsave, 0,
-1);
- }
sanitize_i387_state(target);
@@ -549,13 +556,13 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
sanitize_i387_state(target);
- if (!HAVE_HWFP)
+ if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
- if (!cpu_has_fxsr) {
+ if (!cpu_has_fxsr)
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.state->fsave, 0, -1);
- }
+ &target->thread.fpu.state->fsave, 0,
+ -1);
if (pos > 0 || count < sizeof(env))
convert_from_fxsr(&env, target);
@@ -596,3 +603,33 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu)
EXPORT_SYMBOL(dump_fpu);
#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
+
+static int __init no_387(char *s)
+{
+ setup_clear_cpu_cap(X86_FEATURE_FPU);
+ return 1;
+}
+
+__setup("no387", no_387);
+
+void __cpuinit fpu_detect(struct cpuinfo_x86 *c)
+{
+ 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));
+
+ if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+ set_cpu_cap(c, X86_FEATURE_FPU);
+ else
+ clear_cpu_cap(c, X86_FEATURE_FPU);
+
+ /* The final cr0 value is set in fpu_init() */
+}
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index ada87a329edc..d6c28acdf99c 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -243,7 +243,7 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
if (!access_ok(VERIFY_WRITE, buf, size))
return -EACCES;
- if (!HAVE_HWFP)
+ if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_get(current, NULL, 0,
sizeof(struct user_i387_ia32_struct), NULL,
(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
@@ -350,11 +350,10 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
if (!used_math() && init_fpu(tsk))
return -1;
- if (!HAVE_HWFP) {
+ if (!static_cpu_has(X86_FEATURE_FPU))
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;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 7114c63f047d..d482bcaf61c1 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1410,7 +1410,7 @@ __init void lguest_init(void)
new_cpu_data.x86_capability[0] = cpuid_edx(1);
/* Math is always hard! */
- new_cpu_data.hard_math = 1;
+ set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
/* We don't have features. We have puppies! Puppies! */
#ifdef CONFIG_X86_MCE
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ddab5390d548..2e3223a27746 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1462,7 +1462,7 @@ asmlinkage void __init xen_start_kernel(void)
#ifdef CONFIG_X86_32
/* set up basic CPUID stuff */
cpu_detect(&new_cpu_data);
- new_cpu_data.hard_math = 1;
+ set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
new_cpu_data.wp_works_ok = 1;
new_cpu_data.x86_capability[0] = cpuid_edx(1);
#endif
--
1.8.3.rc0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/