Merge branch 'x86-xsave-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-xsave-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, xsave: Make xstate_enable_boot_cpu() __init, protect on CPU 0
  x86, xsave: Add __init attribute to setup_xstate_features()
  x86, xsave: Make init_xstate_buf static
  x86, xsave: Check cpuid level for XSTATE_CPUID (0x0d)
  x86, xsave: Introduce xstate enable functions
  x86, xsave: Separate fpu and xsave initialization
  x86, xsave: Move boot cpu initialization to xsave_init()
  x86, xsave: 32/64 bit boot cpu check unification in initialization
  x86, xsave: Do not include asm/i387.h in asm/xsave.h
  x86, xsave: Use xsaveopt in context-switch path when supported
  x86, xsave: Sync xsave memory layout with its header for user handling
  x86, xsave: Track the offset, size of state in the xsave layout
This commit is contained in:
Linus Torvalds
2010-08-06 16:25:13 -07:00
5 changed files with 222 additions and 42 deletions

View File

@@ -16,11 +16,88 @@
*/
u64 pcntxt_mask;
/*
* Represents init state for the supported extended state.
*/
static 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 unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
/*
* If a processor implementation discern that a processor state component is
* in its initialized state it may modify the corresponding bit in the
* xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory
* layout in the case of xsaveopt. While presenting the xstate information to
* the user, we always ensure that the memory layout of a feature will be in
* the init state if the corresponding header bit is zero. This is to ensure
* that the user doesn't see some stale state in the memory layout during
* signal handling, debugging etc.
*/
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;
if (!fx)
return;
BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU);
xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
/*
* None of the feature bits are in init state. So nothing else
* to do for us, as the memory layout is upto date.
*/
if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
return;
/*
* FP is in init state
*/
if (!(xstate_bv & XSTATE_FP)) {
fx->cwd = 0x37f;
fx->swd = 0;
fx->twd = 0;
fx->fop = 0;
fx->rip = 0;
fx->rdp = 0;
memset(&fx->st_space[0], 0, 128);
}
/*
* SSE is in init state
*/
if (!(xstate_bv & XSTATE_SSE))
memset(&fx->xmm_space[0], 0, 256);
xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2;
/*
* Update all the other memory layouts for which the corresponding
* header bit is in the init state.
*/
while (xstate_bv) {
if (xstate_bv & 0x1) {
int offset = xstate_offsets[feature_bit];
int size = xstate_sizes[feature_bit];
memcpy(((void *) fx) + offset,
((void *) init_xstate_buf) + offset,
size);
}
xstate_bv >>= 1;
feature_bit++;
}
}
/*
* Check for the presence of extended state information in the
* user fpstate pointer in the sigcontext.
@@ -102,6 +179,7 @@ int save_i387_xstate(void __user *buf)
task_thread_info(tsk)->status &= ~TS_USEDFPU;
stts();
} else {
sanitize_i387_state(tsk);
if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
xstate_size))
return -1;
@@ -267,11 +345,6 @@ static void prepare_fx_sw_frame(void)
#endif
}
/*
* Represents init state for the supported extended state.
*/
struct xsave_struct *init_xstate_buf;
#ifdef CONFIG_X86_64
unsigned int sig_xstate_size = sizeof(struct _fpstate);
#endif
@@ -279,37 +352,77 @@ unsigned int sig_xstate_size = sizeof(struct _fpstate);
/*
* Enable the extended processor state save/restore feature
*/
void __cpuinit xsave_init(void)
static inline void xstate_enable(void)
{
if (!cpu_has_xsave)
return;
set_in_cr4(X86_CR4_OSXSAVE);
/*
* Enable all the features that the HW is capable of
* and the Linux kernel is aware of.
*/
xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
}
/*
* Record the offsets and sizes of different state managed by the xsave
* memory layout.
*/
static void __init setup_xstate_features(void)
{
int eax, ebx, ecx, edx, leaf = 0x2;
xstate_features = fls64(pcntxt_mask);
xstate_offsets = alloc_bootmem(xstate_features * sizeof(int));
xstate_sizes = alloc_bootmem(xstate_features * sizeof(int));
do {
cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
if (eax == 0)
break;
xstate_offsets[leaf] = ebx;
xstate_sizes[leaf] = eax;
leaf++;
} while (1);
}
/*
* setup the xstate image representing the init state
*/
static void __init setup_xstate_init(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(xstate_size);
init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
clts();
/*
* Init all the features state with header_bv being 0x0
*/
xrstor_state(init_xstate_buf, -1);
/*
* Dump the init state again. This is to identify the init state
* of any feature which is not represented by all zero's.
*/
xsave_state(init_xstate_buf, -1);
stts();
}
/*
* Enable and initialize the xsave feature.
*/
void __ref xsave_cntxt_init(void)
static void __init xstate_enable_boot_cpu(void)
{
unsigned int eax, ebx, ecx, edx;
cpuid_count(0xd, 0, &eax, &ebx, &ecx, &edx);
if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
WARN(1, KERN_ERR "XSTATE_CPUID missing\n");
return;
}
cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
pcntxt_mask = eax + ((u64)edx << 32);
if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
@@ -322,12 +435,13 @@ void __ref xsave_cntxt_init(void)
* Support only the state known to OS.
*/
pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
xsave_init();
xstate_enable();
/*
* Recompute the context size for enabled features
*/
cpuid_count(0xd, 0, &eax, &ebx, &ecx, &edx);
cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
xstate_size = ebx;
update_regset_xstate_info(xstate_size, pcntxt_mask);
@@ -339,3 +453,23 @@ void __ref xsave_cntxt_init(void)
"cntxt size 0x%x\n",
pcntxt_mask, xstate_size);
}
/*
* For the very first instance, this calls xstate_enable_boot_cpu();
* for all subsequent instances, this calls xstate_enable().
*
* This is somewhat obfuscated due to the lack of powerful enough
* overrides for the section checks.
*/
void __cpuinit xsave_init(void)
{
static __refdata void (*next_func)(void) = xstate_enable_boot_cpu;
void (*this_func)(void);
if (!cpu_has_xsave)
return;
this_func = next_func;
next_func = xstate_enable;
this_func();
}