linux_dsm_epyc7002/arch/x86/include/asm/i387.h

454 lines
11 KiB
C
Raw Normal View History

/*
* Copyright (C) 1994 Linus Torvalds
*
* Pentium III FXSR, SSE support
* General FPU state handling cleanups
* Gareth Hughes <gareth@valinux.com>, May 2000
* x86-64 work by Andi Kleen 2002
*/
#ifndef _ASM_X86_I387_H
#define _ASM_X86_I387_H
#ifndef __ASSEMBLY__
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/regset.h>
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() Wolfgang Walter reported this oops on his via C3 using padlock for AES-encryption: ################################################################## BUG: unable to handle kernel NULL pointer dereference at 000001f0 IP: [<c01028c5>] __switch_to+0x30/0x117 *pde = 00000000 Oops: 0002 [#1] PREEMPT Modules linked in: Pid: 2071, comm: sleep Not tainted (2.6.26 #11) EIP: 0060:[<c01028c5>] EFLAGS: 00010002 CPU: 0 EIP is at __switch_to+0x30/0x117 EAX: 00000000 EBX: c0493300 ECX: dc48dd00 EDX: c0493300 ESI: dc48dd00 EDI: c0493530 EBP: c04cff8c ESP: c04cff7c DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sleep (pid: 2071, ti=c04ce000 task=dc48dd00 task.ti=d2fe6000) Stack: dc48df30 c0493300 00000000 00000000 d2fe7f44 c03b5b43 c04cffc8 00000046 c0131856 0000005a dc472d3c c0493300 c0493470 d983ae00 00002696 00000000 c0239f54 00000000 c04c4000 c04cffd8 c01025fe c04f3740 00049800 c04cffe0 Call Trace: [<c03b5b43>] ? schedule+0x285/0x2ff [<c0131856>] ? pm_qos_requirement+0x3c/0x53 [<c0239f54>] ? acpi_processor_idle+0x0/0x434 [<c01025fe>] ? cpu_idle+0x73/0x7f [<c03a4dcd>] ? rest_init+0x61/0x63 ======================= Wolfgang also found out that adding kernel_fpu_begin() and kernel_fpu_end() around the padlock instructions fix the oops. Suresh wrote: These padlock instructions though don't use/touch SSE registers, but it behaves similar to other SSE instructions. For example, it might cause DNA faults when cr0.ts is set. While this is a spurious DNA trap, it might cause oops with the recent fpu code changes. This is the code sequence that is probably causing this problem: a) new app is getting exec'd and it is somewhere in between start_thread() and flush_old_exec() in the load_xyz_binary() b) At pont "a", task's fpu state (like TS_USEDFPU, used_math() etc) is cleared. c) Now we get an interrupt/softirq which starts using these encrypt/decrypt routines in the network stack. This generates a math fault (as cr0.ts is '1') which sets TS_USEDFPU and restores the math that is in the task's xstate. d) Return to exec code path, which does start_thread() which does free_thread_xstate() and sets xstate pointer to NULL while the TS_USEDFPU is still set. e) At the next context switch from the new exec'd task to another task, we have a scenarios where TS_USEDFPU is set but xstate pointer is null. This can cause an oops during unlazy_fpu() in __switch_to() Now: 1) This should happen with or with out pre-emption. Viro also encountered similar problem with out CONFIG_PREEMPT. 2) kernel_fpu_begin() and kernel_fpu_end() will fix this problem, because kernel_fpu_begin() will manually do a clts() and won't run in to the situation of setting TS_USEDFPU in step "c" above. 3) This was working before the fpu changes, because its a spurious math fault which doesn't corrupt any fpu/sse registers and the task's math state was always in an allocated state. With out the recent lazy fpu allocation changes, while we don't see oops, there is a possible race still present in older kernels(for example, while kernel is using kernel_fpu_begin() in some optimized clear/copy page and an interrupt/softirq happens which uses these padlock instructions generating DNA fault). This is the failing scenario that existed even before the lazy fpu allocation changes: 0. CPU's TS flag is set 1. kernel using FPU in some optimized copy routine and while doing kernel_fpu_begin() takes an interrupt just before doing clts() 2. Takes an interrupt and ipsec uses padlock instruction. And we take a DNA fault as TS flag is still set. 3. We handle the DNA fault and set TS_USEDFPU and clear cr0.ts 4. We complete the padlock routine 5. Go back to step-1, which resumes clts() in kernel_fpu_begin(), finishes the optimized copy routine and does kernel_fpu_end(). At this point, we have cr0.ts again set to '1' but the task's TS_USEFPU is stilll set and not cleared. 6. Now kernel resumes its user operation. And at the next context switch, kernel sees it has do a FP save as TS_USEDFPU is still set and then will do a unlazy_fpu() in __switch_to(). unlazy_fpu() will take a DNA fault, as cr0.ts is '1' and now, because we are in __switch_to(), math_state_restore() will get confused and will restore the next task's FP state and will save it in prev tasks's FP state. Remember, in __switch_to() we are already on the stack of the next task but take a DNA fault for the prev task. This causes the fpu leakage. Fix the padlock instruction usage by calling them inside the context of new routines irq_ts_save/restore(), which clear/restore cr0.ts manually in the interrupt context. This will not generate spurious DNA in the context of the interrupt which will fix the oops encountered and the possible FPU leakage issue. Reported-and-bisected-by: Wolfgang Walter <wolfgang.walter@stwm.de> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2008-08-13 19:02:26 +07:00
#include <linux/hardirq.h>
#include <linux/slab.h>
#include <asm/asm.h>
#include <asm/cpufeature.h>
#include <asm/processor.h>
#include <asm/sigcontext.h>
#include <asm/user.h>
#include <asm/uaccess.h>
#include <asm/xsave.h>
extern unsigned int sig_xstate_size;
extern void fpu_init(void);
extern void mxcsr_feature_mask_init(void);
extern int init_fpu(struct task_struct *child);
extern asmlinkage void math_state_restore(void);
extern void __math_state_restore(void);
extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
extern user_regset_active_fn fpregs_active, xfpregs_active;
extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
xstateregs_get;
extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
xstateregs_set;
/*
* xstateregs_active == fpregs_active. Please refer to the comment
* at the definition of fpregs_active.
*/
#define xstateregs_active fpregs_active
extern struct _fpx_sw_bytes fx_sw_reserved;
#ifdef CONFIG_IA32_EMULATION
extern unsigned int sig_xstate_ia32_size;
extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
struct _fpstate_ia32;
struct _xstate_ia32;
extern int save_i387_xstate_ia32(void __user *buf);
extern int restore_i387_xstate_ia32(void __user *buf);
#endif
#ifdef CONFIG_MATH_EMULATION
extern void finit_soft_fpu(struct i387_soft_struct *soft);
#else
static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
#endif
#define X87_FSW_ES (1 << 7) /* Exception Summary */
static __always_inline __pure bool use_xsaveopt(void)
{
return static_cpu_has(X86_FEATURE_XSAVEOPT);
}
static __always_inline __pure bool use_xsave(void)
{
return static_cpu_has(X86_FEATURE_XSAVE);
}
static __always_inline __pure bool use_fxsr(void)
{
return static_cpu_has(X86_FEATURE_FXSR);
}
extern void __sanitize_i387_state(struct task_struct *);
static inline void sanitize_i387_state(struct task_struct *tsk)
{
if (!use_xsaveopt())
return;
__sanitize_i387_state(tsk);
}
#ifdef CONFIG_X86_64
static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
{
int err;
/* See comment in fxsave() below. */
#ifdef CONFIG_AS_FXSAVEQ
asm volatile("1: fxrstorq %[fx]\n\t"
"2:\n"
".section .fixup,\"ax\"\n"
"3: movl $-1,%[err]\n"
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err)
: [fx] "m" (*fx), "0" (0));
#else
asm volatile("1: rex64/fxrstor (%[fx])\n\t"
"2:\n"
".section .fixup,\"ax\"\n"
"3: movl $-1,%[err]\n"
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err)
: [fx] "R" (fx), "m" (*fx), "0" (0));
#endif
return err;
}
static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
{
int err;
/*
* Clear the bytes not touched by the fxsave and reserved
* for the SW usage.
*/
err = __clear_user(&fx->sw_reserved,
sizeof(struct _fpx_sw_bytes));
if (unlikely(err))
return -EFAULT;
/* See comment in fxsave() below. */
#ifdef CONFIG_AS_FXSAVEQ
asm volatile("1: fxsaveq %[fx]\n\t"
"2:\n"
".section .fixup,\"ax\"\n"
"3: movl $-1,%[err]\n"
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err), [fx] "=m" (*fx)
: "0" (0));
#else
asm volatile("1: rex64/fxsave (%[fx])\n\t"
"2:\n"
".section .fixup,\"ax\"\n"
"3: movl $-1,%[err]\n"
" jmp 2b\n"
".previous\n"
_ASM_EXTABLE(1b, 3b)
: [err] "=r" (err), "=m" (*fx)
: [fx] "R" (fx), "0" (0));
#endif
if (unlikely(err) &&
__clear_user(fx, sizeof(struct i387_fxsave_struct)))
err = -EFAULT;
/* No need to clear here because the caller clears USED_MATH */
return err;
}
static inline void fpu_fxsave(struct fpu *fpu)
{
/* Using "rex64; fxsave %0" is broken because, if the memory operand
uses any extended registers for addressing, a second REX prefix
will be generated (to the assembler, rex64 followed by semicolon
is a separate instruction), and hence the 64-bitness is lost. */
#ifdef CONFIG_AS_FXSAVEQ
/* Using "fxsaveq %0" would be the ideal choice, but is only supported
starting with gas 2.16. */
__asm__ __volatile__("fxsaveq %0"
: "=m" (fpu->state->fxsave));
#else
/* Using, as a workaround, the properly prefixed form below isn't
accepted by any binutils version so far released, complaining that
the same type of prefix is used twice if an extended register is
needed for addressing (fix submitted to mainline 2005-11-21).
asm volatile("rex64/fxsave %0"
: "=m" (fpu->state->fxsave));
This, however, we can work around by forcing the compiler to select
an addressing mode that doesn't require extended registers. */
asm volatile("rex64/fxsave (%[fx])"
: "=m" (fpu->state->fxsave)
: [fx] "R" (&fpu->state->fxsave));
#endif
}
#else /* CONFIG_X86_32 */
/* perform fxrstor iff the processor has extended states, otherwise frstor */
static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
{
/*
* The "nop" is needed to make the instructions the same
* length.
*/
alternative_input(
"nop ; frstor %1",
"fxrstor %1",
X86_FEATURE_FXSR,
"m" (*fx));
return 0;
}
static inline void fpu_fxsave(struct fpu *fpu)
{
asm volatile("fxsave %[fx]"
: [fx] "=m" (fpu->state->fxsave));
}
#endif /* CONFIG_X86_64 */
/* We need a safe address that is cheap to find and that is already
in L1 during context switch. The best choices are unfortunately
different for UP and SMP */
#ifdef CONFIG_SMP
#define safe_address (__per_cpu_offset[0])
#else
#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
#endif
/*
* These must be called with preempt disabled
*/
static inline void fpu_save_init(struct fpu *fpu)
{
if (use_xsave()) {
fpu_xsave(fpu);
/*
* xsave header may indicate the init state of the FP.
*/
if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
return;
} else if (use_fxsr()) {
fpu_fxsave(fpu);
} else {
x86-32, fpu: Fix FPU exception handling on non-SSE systems On 32bit systems without SSE (that is, they use FSAVE/FRSTOR for FPU context switches), FPU exceptions in user mode cause Oopses, BUGs, recursive faults and other nasty things: fpu exception: 0000 [#1] last sysfs file: /sys/power/state Modules linked in: psmouse evdev pcspkr serio_raw [last unloaded: scsi_wait_scan] Pid: 1638, comm: fxsave-32-excep Not tainted 2.6.35-07798-g58a992b-dirty #633 VP3-596B-DD/VT82C597 EIP: 0060:[<c1003527>] EFLAGS: 00010202 CPU: 0 EIP is at math_error+0x1b4/0x1c8 EAX: 00000003 EBX: cf9be7e0 ECX: 00000000 EDX: cf9c5c00 ESI: cf9d9fb4 EDI: c1372db3 EBP: 00000010 ESP: cf9d9f1c DS: 007b ES: 007b FS: 0000 GS: 00e0 SS: 0068 Process fxsave-32-excep (pid: 1638, ti=cf9d8000 task=cf9be7e0 task.ti=cf9d8000) Stack: 00000000 00000301 00000004 00000000 00000000 cf9d3000 cf9da8f0 00000001 <0> 00000004 cf9b6b60 c1019a6b c1019a79 00000020 00000242 000001b6 cf9c5380 <0> cf806b40 cf791880 00000000 00000282 00000282 c108a213 00000020 cf9c5380 Call Trace: [<c1019a6b>] ? need_resched+0x11/0x1a [<c1019a79>] ? should_resched+0x5/0x1f [<c108a213>] ? do_sys_open+0xbd/0xc7 [<c108a213>] ? do_sys_open+0xbd/0xc7 [<c100353b>] ? do_coprocessor_error+0x0/0x11 [<c12d5965>] ? error_code+0x65/0x70 Code: a8 20 74 30 c7 44 24 0c 06 00 03 00 8d 54 24 04 89 d9 b8 08 00 00 00 e8 9b 6d 02 00 eb 16 8b 93 5c 02 00 00 eb 05 e9 04 ff ff ff <9b> dd 32 9b e9 16 ff ff ff 81 c4 84 00 00 00 5b 5e 5f 5d c3 c6 EIP: [<c1003527>] math_error+0x1b4/0x1c8 SS:ESP 0068:cf9d9f1c This usually continues in slight variations until the system is reset. This bug was introduced by commit 58a992b9cbaf449aeebd3575c3695a9eb5d95b5e: x86-32, fpu: Rewrite fpu_save_init() Signed-off-by: Hans Rosenfeld <hans.rosenfeld@amd.com> Link: http://lkml.kernel.org/r/1302106003-366952-1-git-send-email-hans.rosenfeld@amd.com Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2011-04-06 23:06:43 +07:00
asm volatile("fnsave %[fx]; fwait"
: [fx] "=m" (fpu->state->fsave));
return;
}
if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
asm volatile("fnclex");
/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
is pending. Clear the x87 state here by setting it to fixed
values. safe_address is a random variable that should be in L1 */
alternative_input(
ASM_NOP8 ASM_NOP2,
"emms\n\t" /* clear stack tags */
"fildl %P[addr]", /* set F?P to defined value */
X86_FEATURE_FXSAVE_LEAK,
[addr] "m" (safe_address));
}
static inline void __save_init_fpu(struct task_struct *tsk)
{
fpu_save_init(&tsk->thread.fpu);
task_thread_info(tsk)->status &= ~TS_USEDFPU;
}
static inline int fpu_fxrstor_checking(struct fpu *fpu)
{
return fxrstor_checking(&fpu->state->fxsave);
}
static inline int fpu_restore_checking(struct fpu *fpu)
{
if (use_xsave())
return fpu_xrstor_checking(fpu);
else
return fpu_fxrstor_checking(fpu);
}
static inline int restore_fpu_checking(struct task_struct *tsk)
{
return fpu_restore_checking(&tsk->thread.fpu);
}
/*
* Signal frame handlers...
*/
extern int save_i387_xstate(void __user *buf);
extern int restore_i387_xstate(void __user *buf);
static inline void __unlazy_fpu(struct task_struct *tsk)
{
if (task_thread_info(tsk)->status & TS_USEDFPU) {
__save_init_fpu(tsk);
stts();
} else
tsk->fpu_counter = 0;
}
static inline void __clear_fpu(struct task_struct *tsk)
{
if (task_thread_info(tsk)->status & TS_USEDFPU) {
/* Ignore delayed exceptions from user space */
asm volatile("1: fwait\n"
"2:\n"
_ASM_EXTABLE(1b, 2b));
task_thread_info(tsk)->status &= ~TS_USEDFPU;
stts();
}
}
static inline void kernel_fpu_begin(void)
{
struct thread_info *me = current_thread_info();
preempt_disable();
if (me->status & TS_USEDFPU)
__save_init_fpu(me->task);
else
clts();
}
static inline void kernel_fpu_end(void)
{
stts();
preempt_enable();
}
static inline bool irq_fpu_usable(void)
{
struct pt_regs *regs;
return !in_interrupt() || !(regs = get_irq_regs()) || \
user_mode(regs) || (read_cr0() & X86_CR0_TS);
}
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() Wolfgang Walter reported this oops on his via C3 using padlock for AES-encryption: ################################################################## BUG: unable to handle kernel NULL pointer dereference at 000001f0 IP: [<c01028c5>] __switch_to+0x30/0x117 *pde = 00000000 Oops: 0002 [#1] PREEMPT Modules linked in: Pid: 2071, comm: sleep Not tainted (2.6.26 #11) EIP: 0060:[<c01028c5>] EFLAGS: 00010002 CPU: 0 EIP is at __switch_to+0x30/0x117 EAX: 00000000 EBX: c0493300 ECX: dc48dd00 EDX: c0493300 ESI: dc48dd00 EDI: c0493530 EBP: c04cff8c ESP: c04cff7c DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sleep (pid: 2071, ti=c04ce000 task=dc48dd00 task.ti=d2fe6000) Stack: dc48df30 c0493300 00000000 00000000 d2fe7f44 c03b5b43 c04cffc8 00000046 c0131856 0000005a dc472d3c c0493300 c0493470 d983ae00 00002696 00000000 c0239f54 00000000 c04c4000 c04cffd8 c01025fe c04f3740 00049800 c04cffe0 Call Trace: [<c03b5b43>] ? schedule+0x285/0x2ff [<c0131856>] ? pm_qos_requirement+0x3c/0x53 [<c0239f54>] ? acpi_processor_idle+0x0/0x434 [<c01025fe>] ? cpu_idle+0x73/0x7f [<c03a4dcd>] ? rest_init+0x61/0x63 ======================= Wolfgang also found out that adding kernel_fpu_begin() and kernel_fpu_end() around the padlock instructions fix the oops. Suresh wrote: These padlock instructions though don't use/touch SSE registers, but it behaves similar to other SSE instructions. For example, it might cause DNA faults when cr0.ts is set. While this is a spurious DNA trap, it might cause oops with the recent fpu code changes. This is the code sequence that is probably causing this problem: a) new app is getting exec'd and it is somewhere in between start_thread() and flush_old_exec() in the load_xyz_binary() b) At pont "a", task's fpu state (like TS_USEDFPU, used_math() etc) is cleared. c) Now we get an interrupt/softirq which starts using these encrypt/decrypt routines in the network stack. This generates a math fault (as cr0.ts is '1') which sets TS_USEDFPU and restores the math that is in the task's xstate. d) Return to exec code path, which does start_thread() which does free_thread_xstate() and sets xstate pointer to NULL while the TS_USEDFPU is still set. e) At the next context switch from the new exec'd task to another task, we have a scenarios where TS_USEDFPU is set but xstate pointer is null. This can cause an oops during unlazy_fpu() in __switch_to() Now: 1) This should happen with or with out pre-emption. Viro also encountered similar problem with out CONFIG_PREEMPT. 2) kernel_fpu_begin() and kernel_fpu_end() will fix this problem, because kernel_fpu_begin() will manually do a clts() and won't run in to the situation of setting TS_USEDFPU in step "c" above. 3) This was working before the fpu changes, because its a spurious math fault which doesn't corrupt any fpu/sse registers and the task's math state was always in an allocated state. With out the recent lazy fpu allocation changes, while we don't see oops, there is a possible race still present in older kernels(for example, while kernel is using kernel_fpu_begin() in some optimized clear/copy page and an interrupt/softirq happens which uses these padlock instructions generating DNA fault). This is the failing scenario that existed even before the lazy fpu allocation changes: 0. CPU's TS flag is set 1. kernel using FPU in some optimized copy routine and while doing kernel_fpu_begin() takes an interrupt just before doing clts() 2. Takes an interrupt and ipsec uses padlock instruction. And we take a DNA fault as TS flag is still set. 3. We handle the DNA fault and set TS_USEDFPU and clear cr0.ts 4. We complete the padlock routine 5. Go back to step-1, which resumes clts() in kernel_fpu_begin(), finishes the optimized copy routine and does kernel_fpu_end(). At this point, we have cr0.ts again set to '1' but the task's TS_USEFPU is stilll set and not cleared. 6. Now kernel resumes its user operation. And at the next context switch, kernel sees it has do a FP save as TS_USEDFPU is still set and then will do a unlazy_fpu() in __switch_to(). unlazy_fpu() will take a DNA fault, as cr0.ts is '1' and now, because we are in __switch_to(), math_state_restore() will get confused and will restore the next task's FP state and will save it in prev tasks's FP state. Remember, in __switch_to() we are already on the stack of the next task but take a DNA fault for the prev task. This causes the fpu leakage. Fix the padlock instruction usage by calling them inside the context of new routines irq_ts_save/restore(), which clear/restore cr0.ts manually in the interrupt context. This will not generate spurious DNA in the context of the interrupt which will fix the oops encountered and the possible FPU leakage issue. Reported-and-bisected-by: Wolfgang Walter <wolfgang.walter@stwm.de> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2008-08-13 19:02:26 +07:00
/*
* Some instructions like VIA's padlock instructions generate a spurious
* DNA fault but don't modify SSE registers. And these instructions
x86: Clear TS in irq_ts_save() when in an atomic section The dynamic FPU context allocation changes caused the padlock driver to generate the below warning. Fix it by masking TS when doing padlock encryption operations in an atomic section. This solves: BUG: sleeping function called from invalid context at mm/slub.c:1602 in_atomic(): 1, irqs_disabled(): 0, pid: 82, name: cryptomgr_test Pid: 82, comm: cryptomgr_test Not tainted 2.6.29.4-168.test7.fc11.x86_64 #1 Call Trace: [<ffffffff8103ff16>] __might_sleep+0x10b/0x110 [<ffffffff810cd3b2>] kmem_cache_alloc+0x37/0xf1 [<ffffffff81018505>] init_fpu+0x49/0x8a [<ffffffff81012a83>] math_state_restore+0x3e/0xbc [<ffffffff813ac6d0>] do_device_not_available+0x9/0xb [<ffffffff810123ab>] device_not_available+0x1b/0x20 [<ffffffffa001c066>] ? aes_crypt+0x66/0x74 [padlock_aes] [<ffffffff8119a51a>] ? blkcipher_walk_next+0x257/0x2e0 [<ffffffff8119a731>] ? blkcipher_walk_first+0x18e/0x19d [<ffffffffa001c1fe>] aes_encrypt+0x9d/0xe5 [padlock_aes] [<ffffffffa0027253>] crypt+0x6b/0x114 [xts] [<ffffffffa001c161>] ? aes_encrypt+0x0/0xe5 [padlock_aes] [<ffffffffa001c161>] ? aes_encrypt+0x0/0xe5 [padlock_aes] [<ffffffffa0027390>] encrypt+0x49/0x4b [xts] [<ffffffff81199acc>] async_encrypt+0x3c/0x3e [<ffffffff8119dafc>] test_skcipher+0x1da/0x658 [<ffffffff811979c3>] ? crypto_spawn_tfm+0x8e/0xb1 [<ffffffff8119672d>] ? __crypto_alloc_tfm+0x11b/0x15f [<ffffffff811979c3>] ? crypto_spawn_tfm+0x8e/0xb1 [<ffffffff81199dbe>] ? skcipher_geniv_init+0x2b/0x47 [<ffffffff8119a905>] ? async_chainiv_init+0x5c/0x61 [<ffffffff8119dfdd>] alg_test_skcipher+0x63/0x9b [<ffffffff8119e1bc>] alg_test+0x12d/0x175 [<ffffffff8119c488>] cryptomgr_test+0x38/0x54 [<ffffffff8119c450>] ? cryptomgr_test+0x0/0x54 [<ffffffff8105c6c9>] kthread+0x4d/0x78 [<ffffffff8101264a>] child_rip+0xa/0x20 [<ffffffff81011f67>] ? restore_args+0x0/0x30 [<ffffffff8105c67c>] ? kthread+0x0/0x78 [<ffffffff81012640>] ? child_rip+0x0/0x20 Signed-off-by: Chuck Ebbert <cebbert@redhat.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> LKML-Reference: <20090609104050.50158cfe@dhcp-100-2-144.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-09 21:40:50 +07:00
* get used from interrupt context as well. To prevent these kernel instructions
* in interrupt context interacting wrongly with other user/kernel fpu usage, we
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() Wolfgang Walter reported this oops on his via C3 using padlock for AES-encryption: ################################################################## BUG: unable to handle kernel NULL pointer dereference at 000001f0 IP: [<c01028c5>] __switch_to+0x30/0x117 *pde = 00000000 Oops: 0002 [#1] PREEMPT Modules linked in: Pid: 2071, comm: sleep Not tainted (2.6.26 #11) EIP: 0060:[<c01028c5>] EFLAGS: 00010002 CPU: 0 EIP is at __switch_to+0x30/0x117 EAX: 00000000 EBX: c0493300 ECX: dc48dd00 EDX: c0493300 ESI: dc48dd00 EDI: c0493530 EBP: c04cff8c ESP: c04cff7c DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sleep (pid: 2071, ti=c04ce000 task=dc48dd00 task.ti=d2fe6000) Stack: dc48df30 c0493300 00000000 00000000 d2fe7f44 c03b5b43 c04cffc8 00000046 c0131856 0000005a dc472d3c c0493300 c0493470 d983ae00 00002696 00000000 c0239f54 00000000 c04c4000 c04cffd8 c01025fe c04f3740 00049800 c04cffe0 Call Trace: [<c03b5b43>] ? schedule+0x285/0x2ff [<c0131856>] ? pm_qos_requirement+0x3c/0x53 [<c0239f54>] ? acpi_processor_idle+0x0/0x434 [<c01025fe>] ? cpu_idle+0x73/0x7f [<c03a4dcd>] ? rest_init+0x61/0x63 ======================= Wolfgang also found out that adding kernel_fpu_begin() and kernel_fpu_end() around the padlock instructions fix the oops. Suresh wrote: These padlock instructions though don't use/touch SSE registers, but it behaves similar to other SSE instructions. For example, it might cause DNA faults when cr0.ts is set. While this is a spurious DNA trap, it might cause oops with the recent fpu code changes. This is the code sequence that is probably causing this problem: a) new app is getting exec'd and it is somewhere in between start_thread() and flush_old_exec() in the load_xyz_binary() b) At pont "a", task's fpu state (like TS_USEDFPU, used_math() etc) is cleared. c) Now we get an interrupt/softirq which starts using these encrypt/decrypt routines in the network stack. This generates a math fault (as cr0.ts is '1') which sets TS_USEDFPU and restores the math that is in the task's xstate. d) Return to exec code path, which does start_thread() which does free_thread_xstate() and sets xstate pointer to NULL while the TS_USEDFPU is still set. e) At the next context switch from the new exec'd task to another task, we have a scenarios where TS_USEDFPU is set but xstate pointer is null. This can cause an oops during unlazy_fpu() in __switch_to() Now: 1) This should happen with or with out pre-emption. Viro also encountered similar problem with out CONFIG_PREEMPT. 2) kernel_fpu_begin() and kernel_fpu_end() will fix this problem, because kernel_fpu_begin() will manually do a clts() and won't run in to the situation of setting TS_USEDFPU in step "c" above. 3) This was working before the fpu changes, because its a spurious math fault which doesn't corrupt any fpu/sse registers and the task's math state was always in an allocated state. With out the recent lazy fpu allocation changes, while we don't see oops, there is a possible race still present in older kernels(for example, while kernel is using kernel_fpu_begin() in some optimized clear/copy page and an interrupt/softirq happens which uses these padlock instructions generating DNA fault). This is the failing scenario that existed even before the lazy fpu allocation changes: 0. CPU's TS flag is set 1. kernel using FPU in some optimized copy routine and while doing kernel_fpu_begin() takes an interrupt just before doing clts() 2. Takes an interrupt and ipsec uses padlock instruction. And we take a DNA fault as TS flag is still set. 3. We handle the DNA fault and set TS_USEDFPU and clear cr0.ts 4. We complete the padlock routine 5. Go back to step-1, which resumes clts() in kernel_fpu_begin(), finishes the optimized copy routine and does kernel_fpu_end(). At this point, we have cr0.ts again set to '1' but the task's TS_USEFPU is stilll set and not cleared. 6. Now kernel resumes its user operation. And at the next context switch, kernel sees it has do a FP save as TS_USEDFPU is still set and then will do a unlazy_fpu() in __switch_to(). unlazy_fpu() will take a DNA fault, as cr0.ts is '1' and now, because we are in __switch_to(), math_state_restore() will get confused and will restore the next task's FP state and will save it in prev tasks's FP state. Remember, in __switch_to() we are already on the stack of the next task but take a DNA fault for the prev task. This causes the fpu leakage. Fix the padlock instruction usage by calling them inside the context of new routines irq_ts_save/restore(), which clear/restore cr0.ts manually in the interrupt context. This will not generate spurious DNA in the context of the interrupt which will fix the oops encountered and the possible FPU leakage issue. Reported-and-bisected-by: Wolfgang Walter <wolfgang.walter@stwm.de> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2008-08-13 19:02:26 +07:00
* should use them only in the context of irq_ts_save/restore()
*/
static inline int irq_ts_save(void)
{
/*
x86: Clear TS in irq_ts_save() when in an atomic section The dynamic FPU context allocation changes caused the padlock driver to generate the below warning. Fix it by masking TS when doing padlock encryption operations in an atomic section. This solves: BUG: sleeping function called from invalid context at mm/slub.c:1602 in_atomic(): 1, irqs_disabled(): 0, pid: 82, name: cryptomgr_test Pid: 82, comm: cryptomgr_test Not tainted 2.6.29.4-168.test7.fc11.x86_64 #1 Call Trace: [<ffffffff8103ff16>] __might_sleep+0x10b/0x110 [<ffffffff810cd3b2>] kmem_cache_alloc+0x37/0xf1 [<ffffffff81018505>] init_fpu+0x49/0x8a [<ffffffff81012a83>] math_state_restore+0x3e/0xbc [<ffffffff813ac6d0>] do_device_not_available+0x9/0xb [<ffffffff810123ab>] device_not_available+0x1b/0x20 [<ffffffffa001c066>] ? aes_crypt+0x66/0x74 [padlock_aes] [<ffffffff8119a51a>] ? blkcipher_walk_next+0x257/0x2e0 [<ffffffff8119a731>] ? blkcipher_walk_first+0x18e/0x19d [<ffffffffa001c1fe>] aes_encrypt+0x9d/0xe5 [padlock_aes] [<ffffffffa0027253>] crypt+0x6b/0x114 [xts] [<ffffffffa001c161>] ? aes_encrypt+0x0/0xe5 [padlock_aes] [<ffffffffa001c161>] ? aes_encrypt+0x0/0xe5 [padlock_aes] [<ffffffffa0027390>] encrypt+0x49/0x4b [xts] [<ffffffff81199acc>] async_encrypt+0x3c/0x3e [<ffffffff8119dafc>] test_skcipher+0x1da/0x658 [<ffffffff811979c3>] ? crypto_spawn_tfm+0x8e/0xb1 [<ffffffff8119672d>] ? __crypto_alloc_tfm+0x11b/0x15f [<ffffffff811979c3>] ? crypto_spawn_tfm+0x8e/0xb1 [<ffffffff81199dbe>] ? skcipher_geniv_init+0x2b/0x47 [<ffffffff8119a905>] ? async_chainiv_init+0x5c/0x61 [<ffffffff8119dfdd>] alg_test_skcipher+0x63/0x9b [<ffffffff8119e1bc>] alg_test+0x12d/0x175 [<ffffffff8119c488>] cryptomgr_test+0x38/0x54 [<ffffffff8119c450>] ? cryptomgr_test+0x0/0x54 [<ffffffff8105c6c9>] kthread+0x4d/0x78 [<ffffffff8101264a>] child_rip+0xa/0x20 [<ffffffff81011f67>] ? restore_args+0x0/0x30 [<ffffffff8105c67c>] ? kthread+0x0/0x78 [<ffffffff81012640>] ? child_rip+0x0/0x20 Signed-off-by: Chuck Ebbert <cebbert@redhat.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> LKML-Reference: <20090609104050.50158cfe@dhcp-100-2-144.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-09 21:40:50 +07:00
* If in process context and not atomic, we can take a spurious DNA fault.
* Otherwise, doing clts() in process context requires disabling preemption
* or some heavy lifting like kernel_fpu_begin()
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() Wolfgang Walter reported this oops on his via C3 using padlock for AES-encryption: ################################################################## BUG: unable to handle kernel NULL pointer dereference at 000001f0 IP: [<c01028c5>] __switch_to+0x30/0x117 *pde = 00000000 Oops: 0002 [#1] PREEMPT Modules linked in: Pid: 2071, comm: sleep Not tainted (2.6.26 #11) EIP: 0060:[<c01028c5>] EFLAGS: 00010002 CPU: 0 EIP is at __switch_to+0x30/0x117 EAX: 00000000 EBX: c0493300 ECX: dc48dd00 EDX: c0493300 ESI: dc48dd00 EDI: c0493530 EBP: c04cff8c ESP: c04cff7c DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sleep (pid: 2071, ti=c04ce000 task=dc48dd00 task.ti=d2fe6000) Stack: dc48df30 c0493300 00000000 00000000 d2fe7f44 c03b5b43 c04cffc8 00000046 c0131856 0000005a dc472d3c c0493300 c0493470 d983ae00 00002696 00000000 c0239f54 00000000 c04c4000 c04cffd8 c01025fe c04f3740 00049800 c04cffe0 Call Trace: [<c03b5b43>] ? schedule+0x285/0x2ff [<c0131856>] ? pm_qos_requirement+0x3c/0x53 [<c0239f54>] ? acpi_processor_idle+0x0/0x434 [<c01025fe>] ? cpu_idle+0x73/0x7f [<c03a4dcd>] ? rest_init+0x61/0x63 ======================= Wolfgang also found out that adding kernel_fpu_begin() and kernel_fpu_end() around the padlock instructions fix the oops. Suresh wrote: These padlock instructions though don't use/touch SSE registers, but it behaves similar to other SSE instructions. For example, it might cause DNA faults when cr0.ts is set. While this is a spurious DNA trap, it might cause oops with the recent fpu code changes. This is the code sequence that is probably causing this problem: a) new app is getting exec'd and it is somewhere in between start_thread() and flush_old_exec() in the load_xyz_binary() b) At pont "a", task's fpu state (like TS_USEDFPU, used_math() etc) is cleared. c) Now we get an interrupt/softirq which starts using these encrypt/decrypt routines in the network stack. This generates a math fault (as cr0.ts is '1') which sets TS_USEDFPU and restores the math that is in the task's xstate. d) Return to exec code path, which does start_thread() which does free_thread_xstate() and sets xstate pointer to NULL while the TS_USEDFPU is still set. e) At the next context switch from the new exec'd task to another task, we have a scenarios where TS_USEDFPU is set but xstate pointer is null. This can cause an oops during unlazy_fpu() in __switch_to() Now: 1) This should happen with or with out pre-emption. Viro also encountered similar problem with out CONFIG_PREEMPT. 2) kernel_fpu_begin() and kernel_fpu_end() will fix this problem, because kernel_fpu_begin() will manually do a clts() and won't run in to the situation of setting TS_USEDFPU in step "c" above. 3) This was working before the fpu changes, because its a spurious math fault which doesn't corrupt any fpu/sse registers and the task's math state was always in an allocated state. With out the recent lazy fpu allocation changes, while we don't see oops, there is a possible race still present in older kernels(for example, while kernel is using kernel_fpu_begin() in some optimized clear/copy page and an interrupt/softirq happens which uses these padlock instructions generating DNA fault). This is the failing scenario that existed even before the lazy fpu allocation changes: 0. CPU's TS flag is set 1. kernel using FPU in some optimized copy routine and while doing kernel_fpu_begin() takes an interrupt just before doing clts() 2. Takes an interrupt and ipsec uses padlock instruction. And we take a DNA fault as TS flag is still set. 3. We handle the DNA fault and set TS_USEDFPU and clear cr0.ts 4. We complete the padlock routine 5. Go back to step-1, which resumes clts() in kernel_fpu_begin(), finishes the optimized copy routine and does kernel_fpu_end(). At this point, we have cr0.ts again set to '1' but the task's TS_USEFPU is stilll set and not cleared. 6. Now kernel resumes its user operation. And at the next context switch, kernel sees it has do a FP save as TS_USEDFPU is still set and then will do a unlazy_fpu() in __switch_to(). unlazy_fpu() will take a DNA fault, as cr0.ts is '1' and now, because we are in __switch_to(), math_state_restore() will get confused and will restore the next task's FP state and will save it in prev tasks's FP state. Remember, in __switch_to() we are already on the stack of the next task but take a DNA fault for the prev task. This causes the fpu leakage. Fix the padlock instruction usage by calling them inside the context of new routines irq_ts_save/restore(), which clear/restore cr0.ts manually in the interrupt context. This will not generate spurious DNA in the context of the interrupt which will fix the oops encountered and the possible FPU leakage issue. Reported-and-bisected-by: Wolfgang Walter <wolfgang.walter@stwm.de> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2008-08-13 19:02:26 +07:00
*/
x86: Clear TS in irq_ts_save() when in an atomic section The dynamic FPU context allocation changes caused the padlock driver to generate the below warning. Fix it by masking TS when doing padlock encryption operations in an atomic section. This solves: BUG: sleeping function called from invalid context at mm/slub.c:1602 in_atomic(): 1, irqs_disabled(): 0, pid: 82, name: cryptomgr_test Pid: 82, comm: cryptomgr_test Not tainted 2.6.29.4-168.test7.fc11.x86_64 #1 Call Trace: [<ffffffff8103ff16>] __might_sleep+0x10b/0x110 [<ffffffff810cd3b2>] kmem_cache_alloc+0x37/0xf1 [<ffffffff81018505>] init_fpu+0x49/0x8a [<ffffffff81012a83>] math_state_restore+0x3e/0xbc [<ffffffff813ac6d0>] do_device_not_available+0x9/0xb [<ffffffff810123ab>] device_not_available+0x1b/0x20 [<ffffffffa001c066>] ? aes_crypt+0x66/0x74 [padlock_aes] [<ffffffff8119a51a>] ? blkcipher_walk_next+0x257/0x2e0 [<ffffffff8119a731>] ? blkcipher_walk_first+0x18e/0x19d [<ffffffffa001c1fe>] aes_encrypt+0x9d/0xe5 [padlock_aes] [<ffffffffa0027253>] crypt+0x6b/0x114 [xts] [<ffffffffa001c161>] ? aes_encrypt+0x0/0xe5 [padlock_aes] [<ffffffffa001c161>] ? aes_encrypt+0x0/0xe5 [padlock_aes] [<ffffffffa0027390>] encrypt+0x49/0x4b [xts] [<ffffffff81199acc>] async_encrypt+0x3c/0x3e [<ffffffff8119dafc>] test_skcipher+0x1da/0x658 [<ffffffff811979c3>] ? crypto_spawn_tfm+0x8e/0xb1 [<ffffffff8119672d>] ? __crypto_alloc_tfm+0x11b/0x15f [<ffffffff811979c3>] ? crypto_spawn_tfm+0x8e/0xb1 [<ffffffff81199dbe>] ? skcipher_geniv_init+0x2b/0x47 [<ffffffff8119a905>] ? async_chainiv_init+0x5c/0x61 [<ffffffff8119dfdd>] alg_test_skcipher+0x63/0x9b [<ffffffff8119e1bc>] alg_test+0x12d/0x175 [<ffffffff8119c488>] cryptomgr_test+0x38/0x54 [<ffffffff8119c450>] ? cryptomgr_test+0x0/0x54 [<ffffffff8105c6c9>] kthread+0x4d/0x78 [<ffffffff8101264a>] child_rip+0xa/0x20 [<ffffffff81011f67>] ? restore_args+0x0/0x30 [<ffffffff8105c67c>] ? kthread+0x0/0x78 [<ffffffff81012640>] ? child_rip+0x0/0x20 Signed-off-by: Chuck Ebbert <cebbert@redhat.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> LKML-Reference: <20090609104050.50158cfe@dhcp-100-2-144.bos.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-09 21:40:50 +07:00
if (!in_atomic())
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() Wolfgang Walter reported this oops on his via C3 using padlock for AES-encryption: ################################################################## BUG: unable to handle kernel NULL pointer dereference at 000001f0 IP: [<c01028c5>] __switch_to+0x30/0x117 *pde = 00000000 Oops: 0002 [#1] PREEMPT Modules linked in: Pid: 2071, comm: sleep Not tainted (2.6.26 #11) EIP: 0060:[<c01028c5>] EFLAGS: 00010002 CPU: 0 EIP is at __switch_to+0x30/0x117 EAX: 00000000 EBX: c0493300 ECX: dc48dd00 EDX: c0493300 ESI: dc48dd00 EDI: c0493530 EBP: c04cff8c ESP: c04cff7c DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sleep (pid: 2071, ti=c04ce000 task=dc48dd00 task.ti=d2fe6000) Stack: dc48df30 c0493300 00000000 00000000 d2fe7f44 c03b5b43 c04cffc8 00000046 c0131856 0000005a dc472d3c c0493300 c0493470 d983ae00 00002696 00000000 c0239f54 00000000 c04c4000 c04cffd8 c01025fe c04f3740 00049800 c04cffe0 Call Trace: [<c03b5b43>] ? schedule+0x285/0x2ff [<c0131856>] ? pm_qos_requirement+0x3c/0x53 [<c0239f54>] ? acpi_processor_idle+0x0/0x434 [<c01025fe>] ? cpu_idle+0x73/0x7f [<c03a4dcd>] ? rest_init+0x61/0x63 ======================= Wolfgang also found out that adding kernel_fpu_begin() and kernel_fpu_end() around the padlock instructions fix the oops. Suresh wrote: These padlock instructions though don't use/touch SSE registers, but it behaves similar to other SSE instructions. For example, it might cause DNA faults when cr0.ts is set. While this is a spurious DNA trap, it might cause oops with the recent fpu code changes. This is the code sequence that is probably causing this problem: a) new app is getting exec'd and it is somewhere in between start_thread() and flush_old_exec() in the load_xyz_binary() b) At pont "a", task's fpu state (like TS_USEDFPU, used_math() etc) is cleared. c) Now we get an interrupt/softirq which starts using these encrypt/decrypt routines in the network stack. This generates a math fault (as cr0.ts is '1') which sets TS_USEDFPU and restores the math that is in the task's xstate. d) Return to exec code path, which does start_thread() which does free_thread_xstate() and sets xstate pointer to NULL while the TS_USEDFPU is still set. e) At the next context switch from the new exec'd task to another task, we have a scenarios where TS_USEDFPU is set but xstate pointer is null. This can cause an oops during unlazy_fpu() in __switch_to() Now: 1) This should happen with or with out pre-emption. Viro also encountered similar problem with out CONFIG_PREEMPT. 2) kernel_fpu_begin() and kernel_fpu_end() will fix this problem, because kernel_fpu_begin() will manually do a clts() and won't run in to the situation of setting TS_USEDFPU in step "c" above. 3) This was working before the fpu changes, because its a spurious math fault which doesn't corrupt any fpu/sse registers and the task's math state was always in an allocated state. With out the recent lazy fpu allocation changes, while we don't see oops, there is a possible race still present in older kernels(for example, while kernel is using kernel_fpu_begin() in some optimized clear/copy page and an interrupt/softirq happens which uses these padlock instructions generating DNA fault). This is the failing scenario that existed even before the lazy fpu allocation changes: 0. CPU's TS flag is set 1. kernel using FPU in some optimized copy routine and while doing kernel_fpu_begin() takes an interrupt just before doing clts() 2. Takes an interrupt and ipsec uses padlock instruction. And we take a DNA fault as TS flag is still set. 3. We handle the DNA fault and set TS_USEDFPU and clear cr0.ts 4. We complete the padlock routine 5. Go back to step-1, which resumes clts() in kernel_fpu_begin(), finishes the optimized copy routine and does kernel_fpu_end(). At this point, we have cr0.ts again set to '1' but the task's TS_USEFPU is stilll set and not cleared. 6. Now kernel resumes its user operation. And at the next context switch, kernel sees it has do a FP save as TS_USEDFPU is still set and then will do a unlazy_fpu() in __switch_to(). unlazy_fpu() will take a DNA fault, as cr0.ts is '1' and now, because we are in __switch_to(), math_state_restore() will get confused and will restore the next task's FP state and will save it in prev tasks's FP state. Remember, in __switch_to() we are already on the stack of the next task but take a DNA fault for the prev task. This causes the fpu leakage. Fix the padlock instruction usage by calling them inside the context of new routines irq_ts_save/restore(), which clear/restore cr0.ts manually in the interrupt context. This will not generate spurious DNA in the context of the interrupt which will fix the oops encountered and the possible FPU leakage issue. Reported-and-bisected-by: Wolfgang Walter <wolfgang.walter@stwm.de> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2008-08-13 19:02:26 +07:00
return 0;
if (read_cr0() & X86_CR0_TS) {
clts();
return 1;
}
return 0;
}
static inline void irq_ts_restore(int TS_state)
{
if (TS_state)
stts();
}
/*
* These disable preemption on their own and are safe
*/
static inline void save_init_fpu(struct task_struct *tsk)
{
preempt_disable();
__save_init_fpu(tsk);
stts();
preempt_enable();
}
static inline void unlazy_fpu(struct task_struct *tsk)
{
preempt_disable();
__unlazy_fpu(tsk);
preempt_enable();
}
static inline void clear_fpu(struct task_struct *tsk)
{
preempt_disable();
__clear_fpu(tsk);
preempt_enable();
}
/*
* i387 state interaction
*/
static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
{
if (cpu_has_fxsr) {
return tsk->thread.fpu.state->fxsave.cwd;
} else {
return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
}
}
static inline unsigned short get_fpu_swd(struct task_struct *tsk)
{
if (cpu_has_fxsr) {
return tsk->thread.fpu.state->fxsave.swd;
} else {
return (unsigned short)tsk->thread.fpu.state->fsave.swd;
}
}
static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
{
if (cpu_has_xmm) {
return tsk->thread.fpu.state->fxsave.mxcsr;
} else {
return MXCSR_DEFAULT;
}
}
static bool fpu_allocated(struct fpu *fpu)
{
return fpu->state != NULL;
}
static inline int fpu_alloc(struct fpu *fpu)
{
if (fpu_allocated(fpu))
return 0;
fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
if (!fpu->state)
return -ENOMEM;
WARN_ON((unsigned long)fpu->state & 15);
return 0;
}
static inline void fpu_free(struct fpu *fpu)
{
if (fpu->state) {
kmem_cache_free(task_xstate_cachep, fpu->state);
fpu->state = NULL;
}
}
static inline void fpu_copy(struct fpu *dst, struct fpu *src)
{
memcpy(dst->state, src->state, xstate_size);
}
extern void fpu_finit(struct fpu *fpu);
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_I387_H */