Files
linux/arch/x86/kernel/fpu/xstate.h
Linus Torvalds 70f43ea3a3 Merge tag 'x86-mm-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 memory management updates from Thomas Gleixner:

 - Make LAM enablement safe vs. kernel threads using a process mm
   temporarily as switching back to the process would not update CR3 and
   therefore not enable LAM causing faults in user space when using
   tagged pointers. Cure it by synchronizing LAM enablement via IPIs to
   all CPUs which use the related mm.

 - Cure a LAM harmless inconsistency between CR3 and the state during
   context switch. It's both confusing and prone to lead to real bugs

 - Handle alt stack handling for threads which run with a non-zero
   protection key. The non-zero key prevents the kernel to access the
   alternate stack. Cure it by temporarily enabling all protection keys
   for the alternate stack setup/restore operations.

 - Provide a EFI config table identity mapping for kexec kernel to
   prevent kexec fails because the new kernel cannot access the config
   table array

 - Use GB pages only when a full GB is mapped in the identity map as
   otherwise the CPU can speculate into reserved areas after the end of
   memory which causes malfunction on UV systems.

 - Remove the noisy and pointless SRAT table dump during boot

 - Use is_ioremap_addr() for iounmap() address range checks instead of
   high_memory. is_ioremap_addr() is more precise.

* tag 'x86-mm-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ioremap: Improve iounmap() address range checks
  x86/mm: Remove duplicate check from build_cr3()
  x86/mm: Remove unused NX related declarations
  x86/mm: Remove unused CR3_HW_ASID_BITS
  x86/mm: Don't print out SRAT table information
  x86/mm/ident_map: Use gbpages only where full GB page should be mapped.
  x86/kexec: Add EFI config table identity mapping for kexec kernel
  selftests/mm: Add new testcases for pkeys
  x86/pkeys: Restore altstack access in sigreturn()
  x86/pkeys: Update PKRU to enable all pkeys before XSAVE
  x86/pkeys: Add helper functions to update PKRU on the sigframe
  x86/pkeys: Add PKRU as a parameter in signal handling functions
  x86/mm: Cleanup prctl_enable_tagged_addr() nr_bits error checking
  x86/mm: Fix LAM inconsistency during context switch
  x86/mm: Use IPIs to synchronize LAM enablement
2024-09-17 15:03:01 +02:00

330 lines
9.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __X86_KERNEL_FPU_XSTATE_H
#define __X86_KERNEL_FPU_XSTATE_H
#include <asm/cpufeature.h>
#include <asm/fpu/xstate.h>
#include <asm/fpu/xcr.h>
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(u64, xfd_state);
#endif
static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask)
{
/*
* XRSTORS requires these bits set in xcomp_bv, or it will
* trigger #GP:
*/
if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED))
xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT;
}
static inline u64 xstate_get_group_perm(bool guest)
{
struct fpu *fpu = &current->group_leader->thread.fpu;
struct fpu_state_perm *perm;
/* Pairs with WRITE_ONCE() in xstate_request_perm() */
perm = guest ? &fpu->guest_perm : &fpu->perm;
return READ_ONCE(perm->__state_perm);
}
static inline u64 xstate_get_host_group_perm(void)
{
return xstate_get_group_perm(false);
}
enum xstate_copy_mode {
XSTATE_COPY_FP,
XSTATE_COPY_FX,
XSTATE_COPY_XSAVE,
};
struct membuf;
extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
u64 xfeatures, u32 pkru_val,
enum xstate_copy_mode copy_mode);
extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode mode);
extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf);
extern void fpu__init_cpu_xstate(void);
extern void fpu__init_system_xstate(unsigned int legacy_size);
extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr);
static inline u64 xfeatures_mask_supervisor(void)
{
return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
}
static inline u64 xfeatures_mask_independent(void)
{
if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR))
return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR;
return fpu_kernel_cfg.independent_features;
}
/* XSAVE/XRSTOR wrapper functions */
#ifdef CONFIG_X86_64
#define REX_PREFIX "0x48, "
#else
#define REX_PREFIX
#endif
/* These macros all use (%edi)/(%rdi) as the single memory argument. */
#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
#define XSAVEC ".byte " REX_PREFIX "0x0f,0xc7,0x27"
#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f"
#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
/*
* After this @err contains 0 on success or the trap number when the
* operation raises an exception.
*/
#define XSTATE_OP(op, st, lmask, hmask, err) \
asm volatile("1:" op "\n\t" \
"xor %[err], %[err]\n" \
"2:\n\t" \
_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \
: [err] "=a" (err) \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
/*
* If XSAVES is enabled, it replaces XSAVEC because it supports supervisor
* states in addition to XSAVEC.
*
* Otherwise if XSAVEC is enabled, it replaces XSAVEOPT because it supports
* compacted storage format in addition to XSAVEOPT.
*
* Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
* supports modified optimization which is not supported by XSAVE.
*
* Use XSAVE as a fallback.
*/
#define XSTATE_XSAVE(st, lmask, hmask, err) \
asm volatile("1: " ALTERNATIVE_3(XSAVE, \
XSAVEOPT, X86_FEATURE_XSAVEOPT, \
XSAVEC, X86_FEATURE_XSAVEC, \
XSAVES, X86_FEATURE_XSAVES) \
"\n" \
"xor %[err], %[err]\n" \
"3:\n" \
_ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
: [err] "=r" (err) \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
/*
* Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
* XSAVE area format.
*/
#define XSTATE_XRESTORE(st, lmask, hmask) \
asm volatile("1: " ALTERNATIVE(XRSTOR, \
XRSTORS, X86_FEATURE_XSAVES) \
"\n" \
"3:\n" \
_ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \
: \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
#if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU)
extern void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor);
#else
static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { }
#endif
#ifdef CONFIG_X86_64
static inline void xfd_set_state(u64 xfd)
{
wrmsrl(MSR_IA32_XFD, xfd);
__this_cpu_write(xfd_state, xfd);
}
static inline void xfd_update_state(struct fpstate *fpstate)
{
if (fpu_state_size_dynamic()) {
u64 xfd = fpstate->xfd;
if (__this_cpu_read(xfd_state) != xfd)
xfd_set_state(xfd);
}
}
extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu);
#else
static inline void xfd_set_state(u64 xfd) { }
static inline void xfd_update_state(struct fpstate *fpstate) { }
static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) {
return -EPERM;
}
#endif
/*
* Save processor xstate to xsave area.
*
* Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features
* and command line options. The choice is permanent until the next reboot.
*/
static inline void os_xsave(struct fpstate *fpstate)
{
u64 mask = fpstate->xfeatures;
u32 lmask = mask;
u32 hmask = mask >> 32;
int err;
WARN_ON_FPU(!alternatives_patched);
xfd_validate_state(fpstate, mask, false);
XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err);
/* We should never fault when copying to a kernel buffer: */
WARN_ON_FPU(err);
}
/*
* Restore processor xstate from xsave area.
*
* Uses XRSTORS when XSAVES is used, XRSTOR otherwise.
*/
static inline void os_xrstor(struct fpstate *fpstate, u64 mask)
{
u32 lmask = mask;
u32 hmask = mask >> 32;
xfd_validate_state(fpstate, mask, true);
XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask);
}
/* Restore of supervisor state. Does not require XFD */
static inline void os_xrstor_supervisor(struct fpstate *fpstate)
{
u64 mask = xfeatures_mask_supervisor();
u32 lmask = mask;
u32 hmask = mask >> 32;
XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask);
}
/*
* XSAVE itself always writes all requested xfeatures. Removing features
* from the request bitmap reduces the features which are written.
* Generate a mask of features which must be written to a sigframe. The
* unset features can be optimized away and not written.
*
* This optimization is user-visible. Only use for states where
* uninitialized sigframe contents are tolerable, like dynamic features.
*
* Users of buffers produced with this optimization must check XSTATE_BV
* to determine which features have been optimized out.
*/
static inline u64 xfeatures_need_sigframe_write(void)
{
u64 xfeaures_to_write;
/* In-use features must be written: */
xfeaures_to_write = xfeatures_in_use();
/* Also write all non-optimizable sigframe features: */
xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED &
~XFEATURE_MASK_SIGFRAME_INITOPT;
return xfeaures_to_write;
}
/*
* Save xstate to user space xsave area.
*
* We don't use modified optimization because xrstor/xrstors might track
* a different application.
*
* We don't use compacted format xsave area for backward compatibility for
* old applications which don't understand the compacted format of the
* xsave area.
*
* The caller has to zero buf::header before calling this because XSAVE*
* does not touch the reserved fields in the header.
*/
static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
{
/*
* Include the features which are not xsaved/rstored by the kernel
* internally, e.g. PKRU. That's user space ABI and also required
* to allow the signal handler to modify PKRU.
*/
struct fpstate *fpstate = current->thread.fpu.fpstate;
u64 mask = fpstate->user_xfeatures;
u32 lmask;
u32 hmask;
int err;
/* Optimize away writing unnecessary xfeatures: */
if (fpu_state_size_dynamic())
mask &= xfeatures_need_sigframe_write();
lmask = mask;
hmask = mask >> 32;
xfd_validate_state(fpstate, mask, false);
stac();
XSTATE_OP(XSAVE, buf, lmask, hmask, err);
clac();
return err;
}
/*
* Restore xstate from user space xsave area.
*/
static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask)
{
struct xregs_state *xstate = ((__force struct xregs_state *)buf);
u32 lmask = mask;
u32 hmask = mask >> 32;
int err;
xfd_validate_state(current->thread.fpu.fpstate, mask, true);
stac();
XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
clac();
return err;
}
/*
* Restore xstate from kernel space xsave area, return an error code instead of
* an exception.
*/
static inline int os_xrstor_safe(struct fpstate *fpstate, u64 mask)
{
struct xregs_state *xstate = &fpstate->regs.xsave;
u32 lmask = mask;
u32 hmask = mask >> 32;
int err;
/* Ensure that XFD is up to date */
xfd_update_state(fpstate);
if (cpu_feature_enabled(X86_FEATURE_XSAVES))
XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
else
XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
return err;
}
#endif