diff options
author | Maxime Ripard <maxime@cerno.tech> | 2020-08-18 14:14:25 +0200 |
---|---|---|
committer | Maxime Ripard <maxime@cerno.tech> | 2020-08-18 14:14:25 +0200 |
commit | d85ddd1318e66c0c2665dbfcbc21a8b66c9152aa (patch) | |
tree | e49e401abd2468b398d4bc84c7e05c2c2c3b0966 /arch/x86/include/asm/fpu | |
parent | MAINTAINERS: Change maintainer for hisilicon DRM driver (diff) | |
parent | Linux 5.9-rc1 (diff) | |
download | linux-dev-d85ddd1318e66c0c2665dbfcbc21a8b66c9152aa.tar.xz linux-dev-d85ddd1318e66c0c2665dbfcbc21a8b66c9152aa.zip |
Merge v5.9-rc1 into drm-misc-next
Sam needs 5.9-rc1 to have dev_err_probe in to merge some patches.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Diffstat (limited to 'arch/x86/include/asm/fpu')
-rw-r--r-- | arch/x86/include/asm/fpu/internal.h | 48 | ||||
-rw-r--r-- | arch/x86/include/asm/fpu/regset.h | 4 | ||||
-rw-r--r-- | arch/x86/include/asm/fpu/types.h | 27 | ||||
-rw-r--r-- | arch/x86/include/asm/fpu/xstate.h | 40 |
4 files changed, 74 insertions, 45 deletions
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 845e7481ab77..0a460f2a3f90 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -34,7 +34,6 @@ extern int fpu__copy(struct task_struct *dst, struct task_struct *src); extern void fpu__clear_user_states(struct fpu *fpu); extern void fpu__clear_all(struct fpu *fpu); extern int fpu__exception_code(struct fpu *fpu, int trap_nr); -extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate); /* * Boot time FPU initialization functions: @@ -274,7 +273,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) */ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) { - u64 mask = -1; + u64 mask = xfeatures_mask_all; u32 lmask = mask; u32 hmask = mask >> 32; int err; @@ -320,7 +319,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) */ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) { - u64 mask = -1; + u64 mask = xfeatures_mask_all; u32 lmask = mask; u32 hmask = mask >> 32; int err; @@ -356,6 +355,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) */ static inline int copy_xregs_to_user(struct xregs_state __user *buf) { + u64 mask = xfeatures_mask_user(); + u32 lmask = mask; + u32 hmask = mask >> 32; int err; /* @@ -367,7 +369,7 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf) return -EFAULT; stac(); - XSTATE_OP(XSAVE, buf, -1, -1, err); + XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); return err; @@ -408,43 +410,7 @@ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask) return err; } -/* - * These must be called with preempt disabled. Returns - * 'true' if the FPU state is still intact and we can - * keep registers active. - * - * The legacy FNSAVE instruction cleared all FPU state - * unconditionally, so registers are essentially destroyed. - * Modern FPU state can be kept in registers, if there are - * no pending FP exceptions. - */ -static inline int copy_fpregs_to_fpstate(struct fpu *fpu) -{ - if (likely(use_xsave())) { - copy_xregs_to_kernel(&fpu->state.xsave); - - /* - * AVX512 state is tracked here because its use is - * known to slow the max clock speed of the core. - */ - if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) - fpu->avx512_timestamp = jiffies; - return 1; - } - - if (likely(use_fxsr())) { - copy_fxregs_to_kernel(fpu); - return 1; - } - - /* - * Legacy FPU register saving, FNSAVE always clears FPU registers, - * so we have to mark them inactive: - */ - asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); - - return 0; -} +extern int copy_fpregs_to_fpstate(struct fpu *fpu); static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h index d5bdffb9d27f..4f928d6a367b 100644 --- a/arch/x86/include/asm/fpu/regset.h +++ b/arch/x86/include/asm/fpu/regset.h @@ -8,8 +8,8 @@ #include <linux/regset.h> extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active; -extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, - xstateregs_get; +extern user_regset_get2_fn fpregs_get, xfpregs_get, fpregs_soft_get, + xstateregs_get; extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, xstateregs_set; diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index f098f6cab94b..c87364ea6446 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -114,6 +114,12 @@ enum xfeature { XFEATURE_Hi16_ZMM, XFEATURE_PT_UNIMPLEMENTED_SO_FAR, XFEATURE_PKRU, + XFEATURE_RSRVD_COMP_10, + XFEATURE_RSRVD_COMP_11, + XFEATURE_RSRVD_COMP_12, + XFEATURE_RSRVD_COMP_13, + XFEATURE_RSRVD_COMP_14, + XFEATURE_LBR, XFEATURE_MAX, }; @@ -128,6 +134,7 @@ enum xfeature { #define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM) #define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR) #define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU) +#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR) #define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE) #define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \ @@ -229,6 +236,26 @@ struct pkru_state { u32 pad; } __packed; +/* + * State component 15: Architectural LBR configuration state. + * The size of Arch LBR state depends on the number of LBRs (lbr_depth). + */ + +struct lbr_entry { + u64 from; + u64 to; + u64 info; +}; + +struct arch_lbr_state { + u64 lbr_ctl; + u64 lbr_depth; + u64 ler_from; + u64 ler_to; + u64 ler_info; + struct lbr_entry entries[]; +} __packed; + struct xstate_header { u64 xfeatures; u64 xcomp_bv; diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 422d8369012a..14ab815132d4 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -21,6 +21,8 @@ #define XSAVE_YMM_SIZE 256 #define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) +#define XSAVE_ALIGNMENT 64 + /* All currently supported user features */ #define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ @@ -36,6 +38,27 @@ #define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0) /* + * A supervisor state component may not always contain valuable information, + * and its size may be huge. Saving/restoring such supervisor state components + * at each context switch can cause high CPU and space overhead, which should + * be avoided. Such supervisor state components should only be saved/restored + * on demand. The on-demand dynamic supervisor features are set in this mask. + * + * Unlike the existing supported supervisor features, a dynamic supervisor + * feature does not allocate a buffer in task->fpu, and the corresponding + * supervisor state component cannot be saved/restored at each context switch. + * + * To support a dynamic supervisor feature, a developer should follow the + * dos and don'ts as below: + * - Do dynamically allocate a buffer for the supervisor state component. + * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the + * state component to/from the buffer. + * - Don't set the bit corresponding to the dynamic supervisor feature in + * IA32_XSS at run time, since it has been set at boot time. + */ +#define XFEATURE_MASK_DYNAMIC (XFEATURE_MASK_LBR) + +/* * Unsupported supervisor features. When a supervisor feature in this mask is * supported in the future, move it to the supported supervisor feature mask. */ @@ -43,6 +66,7 @@ /* All supervisor states including supported and unsupported states. */ #define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \ + XFEATURE_MASK_DYNAMIC | \ XFEATURE_MASK_SUPERVISOR_UNSUPPORTED) #ifdef CONFIG_X86_64 @@ -63,6 +87,14 @@ static inline u64 xfeatures_mask_user(void) return xfeatures_mask_all & XFEATURE_MASK_USER_SUPPORTED; } +static inline u64 xfeatures_mask_dynamic(void) +{ + if (!boot_cpu_has(X86_FEATURE_ARCH_LBR)) + return XFEATURE_MASK_DYNAMIC & ~XFEATURE_MASK_LBR; + + return XFEATURE_MASK_DYNAMIC; +} + extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; extern void __init update_regset_xstate_info(unsigned int size, @@ -71,11 +103,15 @@ extern void __init update_regset_xstate_info(unsigned int size, void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); const void *get_xsave_field_ptr(int xfeature_nr); int using_compacted_format(void); -int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); -int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int xfeature_size(int xfeature_nr); +struct membuf; +void copy_xstate_to_kernel(struct membuf to, struct xregs_state *xsave); int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); void copy_supervisor_to_kernel(struct xregs_state *xsave); +void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask); +void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask); + /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ int validate_user_xstate_header(const struct xstate_header *hdr); |