x86: Address Space Isolation FPU preparations
PATCH v2 1/13 x86/xstate: Remove stale assertions in fpu_x{rstor,save}()
In reply to Alejandro VallejoAfter edb48e76458b("x86/fpu: Combine fpu_ctxt and xsave_area in arch_vcpu"), v->arch.xsave_area is always present and we can just remove these asserts.
---
v2:
* Remove asserts rather than refactor them.
* Trimmed and adjusted commit message
--- xen/arch/x86/i387.c | 2 -- 1 file changed, 2 deletions(-)
xen/arch/x86/i387.c +0 -2
@@ -24,7 +24,6 @@ static inline void fpu_xrstor(struct vcpu *v, uint64_t mask) {bool ok; -ASSERT (v->arch.xsave_area);/* * XCR0 normally represents what guest OS set. In case of Xen itself, * we set the accumulated feature mask before doing save/restore.
@@ -136,7 +135,6 @@ static inline void fpu_xsave(struct vcpu *v)uint64_t mask =vcpu_xsave_mask (v);ASSERT (mask); -ASSERT (v->arch.xsave_area);/* * XCR0 normally represents what guest OS set. In case of Xen itself, * we set the accumulated feature mask before doing save/restore.
Signature · 1 line
2.47.0
PATCH v2 5/13 x86/xstate: Map/unmap xsave area in xstate_set_init() and handle_setbv()
In reply to Alejandro VallejoNo functional change.
---
v2:
* Added comment highlighting fastpath for current
--- xen/arch/x86/xstate.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)
xen/arch/x86/xstate.c +10 -2
@@ -993,7 +993,13 @@ int handle_xsetbv(u32 index, u64 new_bv)clts ();if ( curr->fpu_dirtied ) - asm ("stmxcsr %0" :"=m" (curr->arch.xsave_area->fpu_sse.mxcsr) ); + { +/* has a fastpath for `current`, so there's no actual map */ +struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (curr); + + asm ("stmxcsr %0" :"=m" (xsave_area->fpu_sse.mxcsr) ); +VCPU_UNMAP_XSAVE_AREA (curr, xsave_area); + }else if (xstate_all (curr) ) {/* See the comment in i387.c:vcpu_restore_fpu_eager(). */
@@ -1048,7 +1054,7 @@ void xstate_set_init(uint64_t mask)unsigned long cr0 =read_cr0 ();unsigned long xcr0 =this_cpu (xcr0);struct vcpu *v = idle_vcpu[smp_processor_id ()]; -struct xsave_struct *xstate = v->arch.xsave_area; +struct xsave_struct *xstate;if ( ~xfeature_mask & mask ) {
@@ -1061,8 +1067,10 @@ void xstate_set_init(uint64_t mask)clts (); + xstate =VCPU_MAP_XSAVE_AREA (v);memset (&xstate->xsave_hdr,0 ,sizeof (xstate->xsave_hdr));xrstor (v, mask); +VCPU_UNMAP_XSAVE_AREA (v, xstate);if ( cr0 &X86_CR0_TS )write_cr0 (cr0);
Signature · 1 line
2.47.0
PATCH v2 3/13 x86/hvm: Map/unmap xsave area in hvm_save_cpu_ctxt()
In reply to Alejandro VallejoNo functional change.
---
v2:
* No change
--- xen/arch/x86/hvm/hvm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
xen/arch/x86/hvm/hvm.c +4 -4
@@ -914,11 +914,11 @@ static int cf_check hvm_save_cpu_ctxt(struct vcpu *v, hvm_domain_context_t *h)if ( v->fpu_initialised ) { -BUILD_BUG_ON (sizeof (ctxt.fpu_regs) != -sizeof (v->arch.xsave_area->fpu_sse)); -memcpy (ctxt.fpu_regs, &v->arch.xsave_area->fpu_sse, -sizeof (ctxt.fpu_regs)); +const struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (v); +BUILD_BUG_ON (sizeof (ctxt.fpu_regs) !=sizeof (xsave_area->fpu_sse)); +memcpy (ctxt.fpu_regs, &xsave_area->fpu_sse,sizeof (ctxt.fpu_regs)); +VCPU_UNMAP_XSAVE_AREA (v, xsave_area); ctxt.flags =XEN_X86_FPU_INITIALISED ; }
Signature · 1 line
2.47.0
PATCH v2 8/13 x86/xstate: Map/unmap xsave area in {compress,expand}_xsave_states()
In reply to Alejandro VallejoNo functional change.
---
v2:
* No change
--- xen/arch/x86/xstate.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
xen/arch/x86/xstate.c +6 -2
@@ -177,7 +177,7 @@ static void setup_xstate_comp(uint16_t *comp_offsets,*/ void expand_xsave_states (const struct vcpu *v,void *dest,unsigned int size) { -const struct xsave_struct *xstate = v->arch.xsave_area; +const struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);const void *src;uint16_t comp_offsets[sizeof (xfeature_mask)*8 ];u64 xstate_bv = xstate->xsave_hdr.xstate_bv;
@@ -228,6 +228,8 @@ void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size) valid &= ~feature; } + +VCPU_UNMAP_XSAVE_AREA (v, xstate); }/*
@@ -242,7 +244,7 @@ void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size)*/ void compress_xsave_states (struct vcpu *v,const void *src,unsigned int size) { -struct xsave_struct *xstate = v->arch.xsave_area; +struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);void *dest;uint16_t comp_offsets[sizeof (xfeature_mask)*8 ];u64 xstate_bv, valid;
@@ -294,6 +296,8 @@ void compress_xsave_states(struct vcpu *v, const void *src, unsigned int size) valid &= ~feature; } + +VCPU_UNMAP_XSAVE_AREA (v, xstate); }void xsave (struct vcpu *v,uint64_t mask)
Signature · 1 line
2.47.0
PATCH v2 4/13 x86/fpu: Map/umap xsave area in vcpu_{reset,setup}_fpu()
In reply to Alejandro VallejoNo functional change.
---
v2:
* No change
--- xen/arch/x86/i387.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)
xen/arch/x86/i387.c +10 -2
@@ -304,8 +304,10 @@ int vcpu_init_fpu(struct vcpu *v)void vcpu_reset_fpu (struct vcpu *v) { +struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (v); + v->fpu_initialised = false; - *v->arch.xsave_area = (struct xsave_struct ) { + *xsave_area = (struct xsave_struct ) { .fpu_sse = { .mxcsr =MXCSR_DEFAULT , .fcw =FCW_RESET ,
@@ -313,15 +315,21 @@ void vcpu_reset_fpu(struct vcpu *v) }, .xsave_hdr.xstate_bv = X86_XCR0_X87, }; + +VCPU_UNMAP_XSAVE_AREA (v, xsave_area); }void vcpu_setup_fpu (struct vcpu *v,const void *data) { +struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (v); + v->fpu_initialised = true; - *v->arch.xsave_area = (struct xsave_struct ) { + *xsave_area = (struct xsave_struct ) { .fpu_sse = *(const fpusse_t *)data, .xsave_hdr.xstate_bv =XSTATE_FP_SSE , }; + +VCPU_UNMAP_XSAVE_AREA (v, xsave_area); }/* Free FPU's context save area */
Signature · 1 line
2.47.0
v2 cover x86: Address Space Isolation FPU preparations
See original cover letter in v1
v1: https://lore.kernel.org/xen-devel/[email protected]/v1->v2:
* Turned v1/patch1 into an assert removal
* Dropped v1/patch11: "x86/mpx: Adjust read_bndcfgu() to clean after itself"
* Other minor changes out of feedback. Explained in each patch.
Alejandro Vallejo (13):
x86/xstate: Remove stale assertions in fpu_x{rstor,save}() x86/xstate: Create map/unmap primitives for xsave areas x86/hvm: Map/unmap xsave area in hvm_save_cpu_ctxt() x86/fpu: Map/umap xsave area in vcpu_{reset,setup}_fpu() x86/xstate: Map/unmap xsave area in xstate_set_init() and
handle_setbv()
x86/hvm: Map/unmap xsave area in hvmemul_{get,put}_fpu() x86/domctl: Map/unmap xsave area in arch_get_info_guest() x86/xstate: Map/unmap xsave area in {compress,expand}_xsave_states() x86/emulator: Refactor FXSAVE_AREA to use wrappers x86/mpx: Map/unmap xsave area in in read_bndcfgu() x86/fpu: Pass explicit xsave areas to fpu_(f)xsave() x86/fpu: Pass explicit xsave areas to fpu_(f)xrstor() x86/xstate: Make xstate_all() and vcpu_xsave_mask() take explicit
xstate
xen/arch/x86/domctl.c | 9 +++-- xen/arch/x86/hvm/emulate.c | 12 +++++- xen/arch/x86/hvm/hvm.c | 8 ++-- xen/arch/x86/i387.c | 65 +++++++++++++++++++------------ xen/arch/x86/include/asm/xstate.h | 51 ++++++++++++++++++++++-- xen/arch/x86/x86_emulate/blk.c | 11 +++++- xen/arch/x86/xstate.c | 47 +++++++++++++++------- 7 files changed, 150 insertions(+), 53 deletions(-)
Signature · 1 line
2.47.0
PATCH v2 2/13 x86/xstate: Create map/unmap primitives for xsave areas
Add infrastructure to simplify ASI handling. With ASI in the picture we'll have several different means of accessing the XSAVE area of a given vCPU, depending on whether a domain is covered by ASI or not and whether the vCPU is question is scheduled on the current pCPU or not.
Having these complexities exposed at the call sites becomes unwieldy very fast. These wrappers are intended to be used in a similar way to map_domain_page() and unmap_domain_page(); The map operation will dispatch the appropriate pointer for each case in a future patch, while unmap will remain a no-op where no unmap is required (e.g: when there's no ASI) and remove the transient maping if one was required.
Follow-up patches replace all uses of raw v->arch.xsave_area by this mechanism in preparation to add the beforementioned dispatch logic to be added at a later time.
---
v2:
* Comment macros more heavily to show their performance characteristics.
* Addressed various nits in the macro comments.
* Macro names to uppercase.
--- xen/arch/x86/include/asm/xstate.h | 42 +++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+)
xen/arch/x86/include/asm/xstate.h +42 -0
@@ -143,4 +143,46 @@ static inline bool xstate_all(const struct vcpu *v) (v->arch.xcr0_accum & XSTATE_LAZY & ~XSTATE_FP_SSE); } +/* +* Fetch a pointer to a vCPU's XSAVE area +* +* TL;DR: If v == current, the mapping is guaranteed to already exist. +* +* Despite the name, this macro might not actually map anything. The only case +* in which a mutation of page tables is strictly required is when ASI==on && +* v!=current. For everything else the mapping already exists and needs not +* be created nor destroyed. +* +* +-----------------+--------------+ +* | v == current | v != current | +* +--------------+-----------------+--------------+ +* | ASI enabled | per-vCPU fixmap | actual map | +* +--------------+-----------------+--------------+ +* | ASI disabled | directmap | +* +--------------+--------------------------------+ +* +* There MUST NOT be outstanding maps of XSAVE areas of the non-current vCPU +* at the point of context switch. Otherwise, the unmap operation will +* misbehave. +* +* TODO: Expand the macro to the ASI cases after infra to do so is in place. +* +* @param v Owner of the XSAVE area +*/ +#define VCPU_MAP_XSAVE_AREA (v) ((v)->arch.xsave_area) + +/* +* Drops the mapping of a vCPU's XSAVE area and nullifies its pointer on exit +* +* See VCPU_MAP_XSAVE_AREA() for additional information on the persistence of +* these mappings. This macro only tears down the mappings in the ASI=on && +* v!=current case. +* +* TODO: Expand the macro to the ASI cases after infra to do so is in place. +* +* @param v Owner of the XSAVE area +* @param x XSAVE blob of v +*/ +#define VCPU_UNMAP_XSAVE_AREA (v, x) ({ (x) = NULL; }) +#endif /* __ASM_XSTATE_H */
Signature · 1 line
2.47.0
PATCH v2 11/13 x86/fpu: Pass explicit xsave areas to fpu_(f)xsave()
In reply to Alejandro VallejoNo functional change.
---
v2:
* const-ified v
--- xen/arch/x86/i387.c | 16 ++++++++++------ xen/arch/x86/include/asm/xstate.h | 2 +- xen/arch/x86/xstate.c | 3 +-- 3 files changed, 12 insertions(+), 9 deletions(-)
xen/arch/x86/i387.c +10 -6
@@ -129,7 +129,7 @@ static inline uint64_t vcpu_xsave_mask(const struct vcpu *v) }/* Save x87 extended state */ -static inline void fpu_xsave (struct vcpu *v) +static inline void fpu_xsave (const struct vcpu *v,struct xsave_struct *xsave_area) {bool ok;uint64_t mask =vcpu_xsave_mask (v);
@@ -141,15 +141,14 @@ static inline void fpu_xsave(struct vcpu *v)*/ ok =set_xcr0 (v->arch.xcr0_accum |XSTATE_FP_SSE );ASSERT (ok); -xsave (v, mask); +xsave (v, xsave_area, mask); ok =set_xcr0 (v->arch.xcr0 ?:XSTATE_FP_SSE );ASSERT (ok); }/* Save x87 FPU, MMX, SSE and SSE2 state */ -static inline void fpu_fxsave (struct vcpu *v) +static inline void fpu_fxsave (struct vcpu *v,fpusse_t *fpu_ctxt) { -fpusse_t *fpu_ctxt = &v->arch.xsave_area->fpu_sse;unsigned int fip_width = v->domain->arch.x87_fip_width;if ( fip_width !=4 )
@@ -264,6 +263,8 @@ void vcpu_restore_fpu_lazy(struct vcpu *v)*/ static bool _vcpu_save_fpu (struct vcpu *v) { +struct xsave_struct *xsave_area; +if ( !v->fpu_dirtied && !v->arch.nonlazy_xstate_used )return false;
@@ -272,11 +273,14 @@ static bool _vcpu_save_fpu(struct vcpu *v)/* This can happen, if a paravirtualised guest OS has set its CR0.TS. */ clts (); + xsave_area =VCPU_MAP_XSAVE_AREA (v); +if ( cpu_has_xsave ) -fpu_xsave (v); +fpu_xsave (v, xsave_area);else -fpu_fxsave (v); +fpu_fxsave (v, &xsave_area->fpu_sse); +VCPU_UNMAP_XSAVE_AREA (v, xsave_area); v->fpu_dirtied =0 ;return true;
xen/arch/x86/include/asm/xstate.h +1 -1
@@ -97,7 +97,7 @@ uint64_t get_xcr0(void);void set_msr_xss (u64 xss);uint64_t get_msr_xss (void );uint64_t read_bndcfgu (void ); -void xsave (struct vcpu *v,uint64_t mask); +void xsave (const struct vcpu *v,struct xsave_struct *ptr,uint64_t mask);void xrstor (struct vcpu *v,uint64_t mask);void xstate_set_init (uint64_t mask);bool xsave_enabled (const struct vcpu *v);
xen/arch/x86/xstate.c +1 -2
@@ -300,9 +300,8 @@ void compress_xsave_states(struct vcpu *v, const void *src, unsigned int size)VCPU_UNMAP_XSAVE_AREA (v, xstate); } -void xsave (struct vcpu *v,uint64_t mask) +void xsave (const struct vcpu *v,struct xsave_struct *ptr,uint64_t mask) { -struct xsave_struct *ptr = v->arch.xsave_area;uint32_t hmask = mask >>32 ;uint32_t lmask = mask;unsigned int fip_width = v->domain->arch.x87_fip_width;
Signature · 1 line
2.47.0
PATCH v2 6/13 x86/hvm: Map/unmap xsave area in hvmemul_{get,put}_fpu()
In reply to Alejandro VallejoNo functional change.
---
v2:
* Added comments highlighting fastpath for current
--- xen/arch/x86/hvm/emulate.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)
xen/arch/x86/hvm/emulate.c +10 -2
@@ -2371,7 +2371,9 @@ static int cf_check hvmemul_get_fpu(alternative_vcall (hvm_funcs.fpu_dirty_intercept); else if ( type == X86EMUL_FPU_fpu ) { -const fpusse_t *fpu_ctxt = &curr->arch.xsave_area->fpu_sse; +/* has a fastpath for `current`, so there's no actual map */ +const struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (curr); +const fpusse_t *fpu_ctxt = &xsave_area->fpu_sse;/* * Latch current register state so that we can back out changes
@@ -2397,6 +2399,8 @@ static int cf_check hvmemul_get_fpu(else ASSERT (fcw == fpu_ctxt->fcw); } + +VCPU_UNMAP_XSAVE_AREA (curr, xsave_area); }return X86EMUL_OKAY ;
@@ -2411,7 +2415,9 @@ static void cf_check hvmemul_put_fpu(if ( aux ) { -fpusse_t *fpu_ctxt = &curr->arch.xsave_area->fpu_sse; +/* has a fastpath for `current`, so there's no actual map */ +struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (curr); +fpusse_t *fpu_ctxt = &xsave_area->fpu_sse;bool dval = aux->dval;int mode =hvm_guest_x86_mode (curr);
@@ -2465,6 +2471,8 @@ static void cf_check hvmemul_put_fpu( fpu_ctxt->fop = aux->op; +VCPU_UNMAP_XSAVE_AREA (curr, xsave_area); +/* Re-use backout code below. */ backout = X86EMUL_FPU_fpu; }
Signature · 1 line
2.47.0
PATCH v2 7/13 x86/domctl: Map/unmap xsave area in arch_get_info_guest()
In reply to Alejandro VallejoNo functional change.
---
v2:
* No change
--- xen/arch/x86/domctl.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
xen/arch/x86/domctl.c +5 -4
@@ -1377,16 +1377,17 @@ void arch_get_info_guest(struct vcpu *v, vcpu_guest_context_u c)unsigned int i;const struct domain *d = v->domain;bool compat =is_pv_32bit_domain (d); +const struct xsave_struct *xsave_area;#ifdef CONFIG_COMPAT #define c (fld) (!compat ? (c.nat->fld) : (c.cmp->fld))#else #define c (fld) (c.nat->fld)#endif -BUILD_BUG_ON (sizeof (c.nat->fpu_ctxt) != -sizeof (v->arch.xsave_area->fpu_sse)); -memcpy (&c.nat->fpu_ctxt, &v->arch.xsave_area->fpu_sse, -sizeof (c.nat->fpu_ctxt)); + xsave_area =VCPU_MAP_XSAVE_AREA (v); +BUILD_BUG_ON (sizeof (c.nat->fpu_ctxt) !=sizeof (xsave_area->fpu_sse)); +memcpy (&c.nat->fpu_ctxt, &xsave_area->fpu_sse,sizeof (c.nat->fpu_ctxt)); +VCPU_UNMAP_XSAVE_AREA (v, xsave_area);if (is_pv_domain (d) )c (flags = v->arch.pv.vgc_flags & ~(VGCF_i387_valid|VGCF_in_kernel));
Signature · 1 line
2.47.0
PATCH v2 12/13 x86/fpu: Pass explicit xsave areas to fpu_(f)xrstor()
In reply to Alejandro VallejoNo functional change.
---
v2:
* const-ified v in fpu_xrstor()
--- xen/arch/x86/i387.c | 26 ++++++++++++++++---------- xen/arch/x86/include/asm/xstate.h | 2 +- xen/arch/x86/xstate.c | 10 ++++++---- 3 files changed, 23 insertions(+), 15 deletions(-)
xen/arch/x86/i387.c +16 -10
@@ -20,7 +20,8 @@/* FPU Restore Functions */ /*******************************/ /* Restore x87 extended state */ -static inline void fpu_xrstor (struct vcpu *v,uint64_t mask) +static inline void fpu_xrstor (struct vcpu *v,struct xsave_struct *xsave_area, +uint64_t mask) {bool ok;
@@ -30,16 +31,14 @@ static inline void fpu_xrstor(struct vcpu *v, uint64_t mask)*/ ok =set_xcr0 (v->arch.xcr0_accum |XSTATE_FP_SSE );ASSERT (ok); -xrstor (v, mask); +xrstor (v, xsave_area, mask); ok =set_xcr0 (v->arch.xcr0 ?:XSTATE_FP_SSE );ASSERT (ok); }/* Restore x87 FPU, MMX, SSE and SSE2 state */ -static inline void fpu_fxrstor (struct vcpu *v) +static inline void fpu_fxrstor (struct vcpu *v,const fpusse_t *fpu_ctxt) { -const fpusse_t *fpu_ctxt = &v->arch.xsave_area->fpu_sse; -/* * Some CPUs don't save/restore FDP/FIP/FOP unless an exception * is pending. Clear the x87 state here by setting it to fixed
@@ -195,6 +194,8 @@ static inline void fpu_fxsave(struct vcpu *v, fpusse_t *fpu_ctxt)/* Restore FPU state whenever VCPU is schduled in. */ void vcpu_restore_fpu_nonlazy (struct vcpu *v,bool need_stts) { +struct xsave_struct *xsave_area; +/* Restore nonlazy extended state (i.e. parts not tracked by CR0.TS). */ if ( !v->arch.fully_eager_fpu && !v->arch.nonlazy_xstate_used ) goto maybe_stts;
@@ -209,12 +210,13 @@ void vcpu_restore_fpu_nonlazy(struct vcpu *v, bool need_stts)* above) we also need to restore full state, to prevent subsequently * saving state belonging to another vCPU. */ + xsave_area =VCPU_MAP_XSAVE_AREA (v);if ( v->arch.fully_eager_fpu ||xstate_all (v) ) {if ( cpu_has_xsave ) -fpu_xrstor (v,XSTATE_ALL ); +fpu_xrstor (v, xsave_area,XSTATE_ALL );else -fpu_fxrstor (v); +fpu_fxrstor (v, &xsave_area->fpu_sse); v->fpu_initialised =1 ; v->fpu_dirtied =1 ;
@@ -224,9 +226,10 @@ void vcpu_restore_fpu_nonlazy(struct vcpu *v, bool need_stts) }else { -fpu_xrstor (v,XSTATE_NONLAZY ); +fpu_xrstor (v, xsave_area,XSTATE_NONLAZY ); need_stts = true; } +VCPU_UNMAP_XSAVE_AREA (v, xsave_area); maybe_stts:if ( need_stts )
@@ -238,6 +241,7 @@ void vcpu_restore_fpu_nonlazy(struct vcpu *v, bool need_stts)*/ void vcpu_restore_fpu_lazy (struct vcpu *v) { +struct xsave_struct *xsave_area;ASSERT (!is_idle_vcpu (v));/* Avoid recursion. */
@@ -248,10 +252,12 @@ void vcpu_restore_fpu_lazy(struct vcpu *v)ASSERT (!v->arch.fully_eager_fpu); + xsave_area =VCPU_MAP_XSAVE_AREA (v);if ( cpu_has_xsave ) -fpu_xrstor (v,XSTATE_LAZY ); +fpu_xrstor (v, xsave_area,XSTATE_LAZY );else -fpu_fxrstor (v); +fpu_fxrstor (v, &xsave_area->fpu_sse); +VCPU_UNMAP_XSAVE_AREA (v, xsave_area); v->fpu_initialised =1 ; v->fpu_dirtied =1 ;
xen/arch/x86/include/asm/xstate.h +1 -1
@@ -98,7 +98,7 @@ void set_msr_xss(u64 xss);uint64_t get_msr_xss (void );uint64_t read_bndcfgu (void );void xsave (const struct vcpu *v,struct xsave_struct *ptr,uint64_t mask); -void xrstor (struct vcpu *v,uint64_t mask); +void xrstor (const struct vcpu *v,struct xsave_struct *ptr,uint64_t mask);void xstate_set_init (uint64_t mask);bool xsave_enabled (const struct vcpu *v); int __must_check validate_xstate(const struct domain *d,
xen/arch/x86/xstate.c +6 -4
@@ -374,11 +374,10 @@ void xsave(const struct vcpu *v, struct xsave_struct *ptr, uint64_t mask) ptr->fpu_sse.x[FPU_WORD_SIZE_OFFSET ] = fip_width; } -void xrstor (struct vcpu *v,uint64_t mask) +void xrstor (const struct vcpu *v,struct xsave_struct *ptr,uint64_t mask) {uint32_t hmask = mask >>32 ;uint32_t lmask = mask; -struct xsave_struct *ptr = v->arch.xsave_area;unsigned int faults, prev_faults;/*
@@ -992,6 +991,7 @@ int handle_xsetbv(u32 index, u64 new_bv) mask &= curr->fpu_dirtied ? ~XSTATE_FP_SSE :XSTATE_NONLAZY ;if ( mask ) { +struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (curr);unsigned long cr0 =read_cr0 ();clts ();
@@ -1011,7 +1011,9 @@ int handle_xsetbv(u32 index, u64 new_bv) curr->fpu_dirtied =1 ; cr0 &= ~X86_CR0_TS ; } -xrstor (curr, mask); +xrstor (curr, xsave_area, mask); +VCPU_UNMAP_XSAVE_AREA (curr, xsave_area); +if ( cr0 &X86_CR0_TS )write_cr0 (cr0); }
@@ -1078,7 +1080,7 @@ void xstate_set_init(uint64_t mask) xstate =VCPU_MAP_XSAVE_AREA (v);memset (&xstate->xsave_hdr,0 ,sizeof (xstate->xsave_hdr)); -xrstor (v, mask); +xrstor (v, xstate, mask);VCPU_UNMAP_XSAVE_AREA (v, xstate);if ( cr0 &X86_CR0_TS )
Signature · 1 line
2.47.0
PATCH v2 9/13 x86/emulator: Refactor FXSAVE_AREA to use wrappers
In reply to Alejandro VallejoAdds an UNMAP primitive to make use of vcpu_unmap_xsave_area() when linked into xen. unmap is a no-op during tests.
---
v2:
* Added comments highlighting fastpath on current
--- xen/arch/x86/x86_emulate/blk.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)
xen/arch/x86/x86_emulate/blk.c +10 -1
@@ -11,9 +11,12 @@ !defined(X86EMUL_NO_SIMD)# ifdef __XEN__# include <asm/xstate.h> -# define FXSAVE_AREA ((void *)¤t->arch.xsave_area->fpu_sse) +/* has a fastpath for `current`, so there's no actual map */ +# define FXSAVE_AREA ((void *)VCPU_MAP_XSAVE_AREA(current)) +# define UNMAP_FXSAVE_AREA (x) VCPU_UNMAP_XSAVE_AREA(currt ent, x)# else # define FXSAVE_AREA get_fpu_save_area() +# define UNMAP_FXSAVE_AREA (x) ((void)x)# endif #endif
@@ -292,6 +295,9 @@ int x86_emul_blk( }else asmvolatile ("fxrstor %0" ::"m" (*fxsr) ); + +UNMAP_FXSAVE_AREA (fxsr); +break ; }
@@ -320,6 +326,9 @@ int x86_emul_blk(if ( fxsr != ptr )/* i.e. s->op_bytes < sizeof(*fxsr) */ memcpy (ptr, fxsr, s->op_bytes); + +UNMAP_FXSAVE_AREA (fxsr); +break ; }
Signature · 1 line
2.47.0
PATCH v2 10/13 x86/mpx: Map/unmap xsave area in in read_bndcfgu()
In reply to Alejandro VallejoNo functional change.
---
v2:
* s/ret/bndcfgu
--- xen/arch/x86/xstate.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)
xen/arch/x86/xstate.c +9 -3
@@ -1022,9 +1022,10 @@ int handle_xsetbv(u32 index, u64 new_bv)uint64_t read_bndcfgu (void ) { +uint64_t bndcfgu =0 ;unsigned long cr0 =read_cr0 (); -struct xsave_struct *xstate - = idle_vcpu[smp_processor_id ()]->arch.xsave_area; +struct vcpu *v = idle_vcpu[smp_processor_id ()]; +struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);const struct xstate_bndcsr *bndcsr;ASSERT (cpu_has_mpx);
@@ -1050,7 +1051,12 @@ uint64_t read_bndcfgu(void)if ( cr0 &X86_CR0_TS )write_cr0 (cr0); -return xstate->xsave_hdr.xstate_bv &X86_XCR0_BNDCSR ? bndcsr->bndcfgu :0 ; +if ( xstate->xsave_hdr.xstate_bv &X86_XCR0_BNDCSR ) + bndcfgu = bndcsr->bndcfgu; + +VCPU_UNMAP_XSAVE_AREA (v, xstate); + +return bndcfgu; }void xstate_set_init (uint64_t mask)
Signature · 1 line
2.47.0
PATCH v2 13/13 x86/xstate: Make xstate_all() and vcpu_xsave_mask() take explicit xstate
In reply to Alejandro VallejoNo functional change.
--- xen/arch/x86/i387.c | 9 +++++---- xen/arch/x86/include/asm/xstate.h | 5 +++-- xen/arch/x86/xstate.c | 2 +- 3 files changed, 9 insertions(+), 7 deletions(-)
xen/arch/x86/i387.c +5 -4
@@ -107,7 +107,8 @@ static inline void fpu_fxrstor(struct vcpu *v, const fpusse_t *fpu_ctxt)/* FPU Save Functions */ /*******************************/ -static inline uint64_t vcpu_xsave_mask (const struct vcpu *v) +static inline uint64_t vcpu_xsave_mask (const struct vcpu *v, +const struct xsave_struct *xsave_area) {if ( v->fpu_dirtied )return v->arch.nonlazy_xstate_used ?XSTATE_ALL :XSTATE_LAZY ;
@@ -124,14 +125,14 @@ static inline uint64_t vcpu_xsave_mask(const struct vcpu *v)* XSTATE_FP_SSE), vcpu_xsave_mask will return XSTATE_ALL. Otherwise * return XSTATE_NONLAZY. */ -return xstate_all (v) ?XSTATE_ALL :XSTATE_NONLAZY ; +return xstate_all (v, xsave_area) ?XSTATE_ALL :XSTATE_NONLAZY ; }/* Save x87 extended state */ static inline void fpu_xsave (const struct vcpu *v,struct xsave_struct *xsave_area) {bool ok; -uint64_t mask =vcpu_xsave_mask (v); +uint64_t mask =vcpu_xsave_mask (v, xsave_area);ASSERT (mask);/*
@@ -211,7 +212,7 @@ void vcpu_restore_fpu_nonlazy(struct vcpu *v, bool need_stts)* saving state belonging to another vCPU. */ xsave_area =VCPU_MAP_XSAVE_AREA (v); -if ( v->arch.fully_eager_fpu ||xstate_all (v) ) +if ( v->arch.fully_eager_fpu ||xstate_all (v, xsave_area) ) {if ( cpu_has_xsave )fpu_xrstor (v, xsave_area,XSTATE_ALL );
xen/arch/x86/include/asm/xstate.h +3 -2
@@ -132,14 +132,15 @@ xsave_area_compressed(const struct xsave_struct *xsave_area)return xsave_area->xsave_hdr.xcomp_bv &XSTATE_COMPACTION_ENABLED ; } -static inline bool xstate_all (const struct vcpu *v) +static inline bool xstate_all (const struct vcpu *v, +const struct xsave_struct *xsave_area) {/* * XSTATE_FP_SSE may be excluded, because the offsets of XSTATE_FP_SSE * (in the legacy region of xsave area) are fixed, so saving * XSTATE_FP_SSE will not cause overwriting problem with XSAVES/XSAVEC. */ -return xsave_area_compressed (v->arch.xsave_area) && +return xsave_area_compressed (xsave_area) && (v->arch.xcr0_accum &XSTATE_LAZY & ~XSTATE_FP_SSE ); }
xen/arch/x86/xstate.c +1 -1
@@ -1003,7 +1003,7 @@ int handle_xsetbv(u32 index, u64 new_bv) asm ("stmxcsr %0" :"=m" (xsave_area->fpu_sse.mxcsr) );VCPU_UNMAP_XSAVE_AREA (curr, xsave_area); } -else if (xstate_all (curr) ) +else if (xstate_all (curr, xsave_area) ) {/* See the comment in i387.c:vcpu_restore_fpu_eager(). */ mask |=XSTATE_LAZY ;
Signature · 1 line
2.47.0
Re: [PATCH v2 01/13] x86/xstate: Remove stale assertions in fpu_x{rstor,save}()
In reply to Alejandro VallejoQuoted 5 lines · Alejandro Vallejo
After
edb48e76458b("x86/fpu: Combine fpu_ctxt and xsave_area in arch_vcpu"),v->arch.xsave_areais always present and we can just remove these asserts.Fixes edb48e76458b("x86/fpu: Combine fpu_ctxt and xsave_area in arch_vcpu")Signed-off-by Alejandro Vallejo <[email protected]>
Re: [PATCH v2 02/13] x86/xstate: Create map/unmap primitives for xsave areas
In reply to Alejandro VallejoQuoted 23 lines · Alejandro Vallejo
xen/arch/x86/include/asm/xstate.h +17
-0@@ -143,4 +143,46 @@ static inline bool xstate_all(const struct vcpu *v) (v->arch.xcr0_accum &XSTATE_LAZY & ~XSTATE_FP_SSE ); } +/* +* Fetch a pointer to a vCPU's XSAVE area +* +* TL;DR: If v == current, the mapping is guaranteed to already exist. +* +* Despite the name, this macro might not actually map anything. The only case +* in which a mutation of page tables is strictly required is when ASI==on && +* v!=current. For everything else the mapping already exists and needs not +* be created nor destroyed. +* +* +-----------------+--------------+ +* | v == current | v != current | +* +--------------+-----------------+--------------+ +* | ASI enabled | per-vCPU fixmap | actual map | +* +--------------+-----------------+--------------+ +* | ASI disabled | directmap | +* +--------------+--------------------------------+
xen/arch/x86/include/asm/xstate.h static inline bool xstate_all(const struct vcpu *v) · line 172
Quoted 10 lines
xen/arch/x86/include/asm/xstate.h +10
-0+* +* There MUST NOT be outstanding maps of XSAVE areas of the non-current vCPU +* at the point of context switch. Otherwise, the unmap operation will +* misbehave. +* +* TODO: Expand the macro to the ASI cases after infra to do so is in place. +* +* @param v Owner of the XSAVE area +*/ +#define VCPU_MAP_XSAVE_AREA (v) ((v)->arch.xsave_area)
When this is fleshed out, I expect (hope) type safety (type of "return value") will remain to be there. I think it would be nice ...
xen/arch/x86/include/asm/xstate.h static inline bool xstate_all(const struct vcpu *v) · line 186
Quoted 13 lines
xen/arch/x86/include/asm/xstate.h +13
-0+/* +* Drops the mapping of a vCPU's XSAVE area and nullifies its pointer on exit +* +* See VCPU_MAP_XSAVE_AREA() for additional information on the persistence of +* these mappings. This macro only tears down the mappings in the ASI=on && +* v!=current case. +* +* TODO: Expand the macro to the ASI cases after infra to do so is in place. +* +* @param v Owner of the XSAVE area +* @param x XSAVE blob of v +*/ +#define VCPU_UNMAP_XSAVE_AREA (v, x) ({ (x) = NULL; })
... if this was typesafe (at least on x) from the very beginning as well. Thoughts?
Jan
Re: [PATCH v2 03/13] x86/hvm: Map/unmap xsave area in hvm_save_cpu_ctxt()
In reply to Alejandro VallejoQuoted 3 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>
Re: [PATCH v2 04/13] x86/fpu: Map/umap xsave area in vcpu_{reset,setup}_fpu()
In reply to Alejandro VallejoQuoted 3 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>
Re: [PATCH v2 05/13] x86/xstate: Map/unmap xsave area in xstate_set_init() and handle_setbv()
In reply to Alejandro VallejoQuoted 3 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>
with ...
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 998
Quoted 10 lines
xen/arch/x86/xstate.c +3
-1@@ -993,7 +993,13 @@ int handle_xsetbv(u32 index, u64 new_bv)clts ();if ( curr->fpu_dirtied ) - asm ("stmxcsr %0" :"=m" (curr->arch.xsave_area->fpu_sse.mxcsr) ); + { +/* has a fastpath for `current`, so there's no actual map */ +struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (curr);
... comment style adhered to (capital 'H').
Jan
Re: [PATCH v2 06/13] x86/hvm: Map/unmap xsave area in hvmemul_{get,put}_fpu()
In reply to Alejandro VallejoQuoted 3 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>
Again with comment style adjusted:
Jan
Re: [PATCH v2 07/13] x86/domctl: Map/unmap xsave area in arch_get_info_guest()
In reply to Alejandro VallejoQuoted 3 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>
Re: [PATCH v2 08/13] x86/xstate: Map/unmap xsave area in {compress,expand}_xsave_states()
In reply to Alejandro VallejoQuoted 24 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>---
v2:
* No change--- xen/arch/x86/xstate.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)xen/arch/x86/xstate.c +1
-1@@ -177,7 +177,7 @@ static void setup_xstate_comp(uint16_t *comp_offsets,*/ void expand_xsave_states (const struct vcpu *v,void *dest,unsigned int size) { -const struct xsave_struct *xstate = v->arch.xsave_area; +const struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);const void *src;uint16_t comp_offsets[sizeof (xfeature_mask)*8 ];u64 xstate_bv = xstate->xsave_hdr.xstate_bv;
xen/arch/x86/xstate.c void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size) · line 233
Quoted 6 lines
xen/arch/x86/xstate.c +2
-0@@ -228,6 +228,8 @@ void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size) valid &= ~feature; } + +VCPU_UNMAP_XSAVE_AREA (v, xstate); }
In the middle of these two hunks there's an early return.
Quoted 10 lines
xen/arch/x86/xstate.c +1
-1@@ -242,7 +244,7 @@ void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size)*/ void compress_xsave_states (struct vcpu *v,const void *src,unsigned int size) { -struct xsave_struct *xstate = v->arch.xsave_area; +struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);void *dest;uint16_t comp_offsets[sizeof (xfeature_mask)*8 ];u64 xstate_bv, valid;
xen/arch/x86/xstate.c void compress_xsave_states(struct vcpu *v, const void *src, unsigned int size) · line 301
Quoted 6 lines
xen/arch/x86/xstate.c +2
-0@@ -294,6 +296,8 @@ void compress_xsave_states(struct vcpu *v, const void *src, unsigned int size) valid &= ~feature; } + +VCPU_UNMAP_XSAVE_AREA (v, xstate); }
Same here.
Jan
Re: [PATCH v2 09/13] x86/emulator: Refactor FXSAVE_AREA to use wrappers
In reply to Alejandro Vallejoxen/arch/x86/x86_emulate/blk.c line 16
Quoted 10 lines · Alejandro Vallejo
xen/arch/x86/x86_emulate/blk.c +3
-1@@ -11,9 +11,12 @@ !defined(X86EMUL_NO_SIMD)# ifdef __XEN__# include <asm/xstate.h> -# define FXSAVE_AREA ((void *)¤t->arch.xsave_area->fpu_sse) +/* has a fastpath for `current`, so there's no actual map */ +# define FXSAVE_AREA ((void *)VCPU_MAP_XSAVE_AREA(current)) +# define UNMAP_FXSAVE_AREA (x) VCPU_UNMAP_XSAVE_AREA(currt ent, x)
The typo of the first argument strongly suggests that the macro should already now evaluate its parameters, also pleasing Misra.
xen/arch/x86/x86_emulate/blk.c line 19
Quoted 3 lines
xen/arch/x86/x86_emulate/blk.c +1
-0# else # define FXSAVE_AREA get_fpu_save_area() +# define UNMAP_FXSAVE_AREA (x) ((void)x)
If only for consistency and to avoid setting bad precedents - parentheses please around x.
Quoted 11 lines
xen/arch/x86/x86_emulate/blk.c +3
-0@@ -292,6 +295,9 @@ int x86_emul_blk( }else asmvolatile ("fxrstor %0" ::"m" (*fxsr) ); + +UNMAP_FXSAVE_AREA (fxsr); +break ; }
xen/arch/x86/x86_emulate/blk.c int x86_emul_blk( · line 333
Quoted 8 lines
xen/arch/x86/x86_emulate/blk.c +3
-0@@ -320,6 +326,9 @@ int x86_emul_blk(if ( fxsr != ptr )/* i.e. s->op_bytes < sizeof(*fxsr) */ memcpy (ptr, fxsr, s->op_bytes); + +UNMAP_FXSAVE_AREA (fxsr); +break ; }
So for now the emulator only supports FXSAVE / FXRSTOR. That'll need to change sooner or later. Is it really appropriate in that light to name the new macro after FXSAVE, when the underlying machinery uses all XSAVE?
Jan
Re: [PATCH v2 10/13] x86/mpx: Map/unmap xsave area in in read_bndcfgu()
In reply to Alejandro Vallejoxen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1027
Quoted 11 lines · Alejandro Vallejo
xen/arch/x86/xstate.c +2
-2@@ -1022,9 +1022,10 @@ int handle_xsetbv(u32 index, u64 new_bv)uint64_t read_bndcfgu (void ) { +uint64_t bndcfgu =0 ;unsigned long cr0 =read_cr0 (); -struct xsave_struct *xstate - = idle_vcpu[smp_processor_id ()]->arch.xsave_area; +struct vcpu *v = idle_vcpu[smp_processor_id ()];
Can this be pointer-to-const? Certainly right now, so the question is rather meant to be forward looking.
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1028
Quoted 1 line
xen/arch/x86/xstate.c +1
-0+struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);
This certainly can be pointer-to-const, just like ...
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1029
Quoted 1 line
xen/arch/x86/xstate.c +0
-0const struct xstate_bndcsr *bndcsr;
... this is.
Jan
Re: [PATCH v2 11/13] x86/fpu: Pass explicit xsave areas to fpu_(f)xsave()
In reply to Alejandro VallejoQuoted 6 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>---
v2:
* const-ified v
Hmm, yes, you did ...
xen/arch/x86/i387.c static inline uint64_t vcpu_xsave_mask(const struct vcpu *v) · line 132
Quoted 8 lines
xen/arch/x86/i387.c +1
-1@@ -129,7 +129,7 @@ static inline uint64_t vcpu_xsave_mask(const struct vcpu *v) }/* Save x87 extended state */ -static inline void fpu_xsave (struct vcpu *v) +static inline void fpu_xsave (const struct vcpu *v,struct xsave_struct *xsave_area)
... here.
xen/arch/x86/i387.c static inline void fpu_xsave(struct vcpu *v) · line 150
Quoted 13 lines
xen/arch/x86/i387.c +2
-2@@ -141,15 +141,14 @@ static inline void fpu_xsave(struct vcpu *v)*/ ok =set_xcr0 (v->arch.xcr0_accum |XSTATE_FP_SSE );ASSERT (ok); -xsave (v, mask); +xsave (v, xsave_area, mask); ok =set_xcr0 (v->arch.xcr0 ?:XSTATE_FP_SSE );ASSERT (ok); }/* Save x87 FPU, MMX, SSE and SSE2 state */ -static inline void fpu_fxsave (struct vcpu *v) +static inline void fpu_fxsave (struct vcpu *v,fpusse_t *fpu_ctxt)
But then not here.
Jan
Re: [PATCH v2 12/13] x86/fpu: Pass explicit xsave areas to fpu_(f)xrstor()
In reply to Alejandro VallejoQuoted 6 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>---
v2:
* const-ified v infpu_xrstor()
Yet what about fpu_fxrstor()?
Jan
Re: [PATCH v2 13/13] x86/xstate: Make xstate_all() and vcpu_xsave_mask() take explicit xstate
In reply to Alejandro VallejoQuoted 3 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>
Re: [PATCH v2 02/13] x86/xstate: Create map/unmap primitives for xsave areas
In reply to Jan BeulichQuoted 29 lines · Jan Beulich
Quoted 28 lines · Alejandro Vallejo
xen/arch/x86/include/asm/xstate.h +22
-0@@ -143,4 +143,46 @@ static inline bool xstate_all(const struct vcpu *v) (v->arch.xcr0_accum &XSTATE_LAZY & ~XSTATE_FP_SSE ); } +/* +* Fetch a pointer to a vCPU's XSAVE area +* +* TL;DR: If v == current, the mapping is guaranteed to already exist. +* +* Despite the name, this macro might not actually map anything. The only case +* in which a mutation of page tables is strictly required is when ASI==on && +* v!=current. For everything else the mapping already exists and needs not +* be created nor destroyed. +* +* +-----------------+--------------+ +* | v == current | v != current | +* +--------------+-----------------+--------------+ +* | ASI enabled | per-vCPU fixmap | actual map | +* +--------------+-----------------+--------------+ +* | ASI disabled | directmap | +* +--------------+--------------------------------+ +* +* There MUST NOT be outstanding maps of XSAVE areas of the non-current vCPU +* at the point of context switch. Otherwise, the unmap operation will +* misbehave. +*
Quoted 8 lines
xen/arch/x86/include/asm/xstate.h static inline bool xstate_all(const struct vcpu *v) · line 172
Quoted 5 lines
xen/arch/x86/include/asm/xstate.h +5
-0+* TODO: Expand the macro to the ASI cases after infra to do so is in place. +* +* @param v Owner of the XSAVE area +*/ +#define VCPU_MAP_XSAVE_AREA (v) ((v)->arch.xsave_area)When this is fleshed out, I expect (hope) type safety (type of "return value") will remain to be there. I think it would be nice ...
The return type will always be a pointer to struct xsave_struct, so that's definitely type-safe.
Quoted 17 lines
Quoted 4 lines
xen/arch/x86/include/asm/xstate.h +3
-0+/* +* Drops the mapping of a vCPU's XSAVE area and nullifies its pointer on exit +* xen/arch/x86/include/asm/xstate.h static inline bool xstate_all(const struct vcpu *v) · line 186
Quoted 10 lines
xen/arch/x86/include/asm/xstate.h +10
-0+* See VCPU_MAP_XSAVE_AREA() for additional information on the persistence of +* these mappings. This macro only tears down the mappings in the ASI=on && +* v!=current case. +* +* TODO: Expand the macro to the ASI cases after infra to do so is in place. +* +* @param v Owner of the XSAVE area +* @param x XSAVE blob of v +*/ +#define VCPU_UNMAP_XSAVE_AREA (v, x) ({ (x) = NULL; })... if this was typesafe (at least on x) from the very beginning as well. Thoughts?
I tentatively intend for both macros to involve a call to static inline functions when the real infrastructure is in place. By the time everything is fleshed out both will be definitely type-safe. Const-ness might suffer though, as there's a tension between clarity of static inlines and flexible qualifiers (i.e: having const outputs iff inputs are const).
Quoted 2 lines
Jan
Cheers,
Alejandro
Re: [PATCH v2 05/13] x86/xstate: Map/unmap xsave area in xstate_set_init() and handle_setbv()
In reply to Jan BeulichQuoted 6 lines · Jan Beulich
Quoted 3 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>Acked-by Jan Beulich <[email protected]>
Thanks (for this one and the others).
Quoted 15 lines
with ...
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 998
Quoted 10 lines
xen/arch/x86/xstate.c +3
-1@@ -993,7 +993,13 @@ int handle_xsetbv(u32 index, u64 new_bv)clts ();if ( curr->fpu_dirtied ) - asm ("stmxcsr %0" :"=m" (curr->arch.xsave_area->fpu_sse.mxcsr) ); + { +/* has a fastpath for `current`, so there's no actual map */ +struct xsave_struct *xsave_area =VCPU_MAP_XSAVE_AREA (curr);... comment style adhered to (capital 'H').
Quoted 1 line
Jan
Ah, yes. All those ought to be capitalized. My bad.
Cheers,
Alejandro
Re: [PATCH v2 08/13] x86/xstate: Map/unmap xsave area in {compress,expand}_xsave_states()
In reply to Jan BeulichQuoted 53 lines · Jan Beulich
Quoted 24 lines · Alejandro Vallejo
No functional change.
Signed-off-by Alejandro Vallejo <[email protected]>---
v2:
* No change--- xen/arch/x86/xstate.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)xen/arch/x86/xstate.c +1
-1@@ -177,7 +177,7 @@ static void setup_xstate_comp(uint16_t *comp_offsets,*/ void expand_xsave_states (const struct vcpu *v,void *dest,unsigned int size) { -const struct xsave_struct *xstate = v->arch.xsave_area; +const struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);const void *src;uint16_t comp_offsets[sizeof (xfeature_mask)*8 ];u64 xstate_bv = xstate->xsave_hdr.xstate_bv;xen/arch/x86/xstate.c void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size) · line 233
Quoted 6 lines
xen/arch/x86/xstate.c +2
-0@@ -228,6 +228,8 @@ void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size) valid &= ~feature; } + +VCPU_UNMAP_XSAVE_AREA (v, xstate); }In the middle of these two hunks there's an early return.
Quoted 10 lines
xen/arch/x86/xstate.c +1
-1@@ -242,7 +244,7 @@ void expand_xsave_states(const struct vcpu *v, void *dest, unsigned int size)*/ void compress_xsave_states (struct vcpu *v,const void *src,unsigned int size) { -struct xsave_struct *xstate = v->arch.xsave_area; +struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);void *dest;uint16_t comp_offsets[sizeof (xfeature_mask)*8 ];u64 xstate_bv, valid;xen/arch/x86/xstate.c void compress_xsave_states(struct vcpu *v, const void *src, unsigned int size) · line 301
Quoted 6 lines
xen/arch/x86/xstate.c +2
-0@@ -294,6 +296,8 @@ void compress_xsave_states(struct vcpu *v, const void *src, unsigned int size) valid &= ~feature; } + +VCPU_UNMAP_XSAVE_AREA (v, xstate); }Same here.
Quoted 1 line
Jan
Doh! Yes, good catch. I'll "goto out" on both rather than the early exit to ensure the unmap is invoked in the "already (de)compressed" cases.
Cheers,
Alejandro
Re: [PATCH v2 09/13] x86/emulator: Refactor FXSAVE_AREA to use wrappers
In reply to Jan BeulichQuoted 14 lines · Jan Beulich
xen/arch/x86/x86_emulate/blk.c line 16
Quoted 10 lines · Alejandro Vallejo
xen/arch/x86/x86_emulate/blk.c +3
-1@@ -11,9 +11,12 @@ !defined(X86EMUL_NO_SIMD)# ifdef __XEN__# include <asm/xstate.h> -# define FXSAVE_AREA ((void *)¤t->arch.xsave_area->fpu_sse) +/* has a fastpath for `current`, so there's no actual map */ +# define FXSAVE_AREA ((void *)VCPU_MAP_XSAVE_AREA(current)) +# define UNMAP_FXSAVE_AREA (x) VCPU_UNMAP_XSAVE_AREA(currt ent, x)The typo of the first argument strongly suggests that the macro should already now evaluate its parameters, also pleasing Misra.
Not an unreasonable takeaway. I can expand as follows instead:
#define VCPU_UNMAP_XSAVE_AREA(v, x) ({ (void)(v); x; })
Thoughts?
Quoted 7 lines
xen/arch/x86/x86_emulate/blk.c line 19
Quoted 4 lines
xen/arch/x86/x86_emulate/blk.c +1
-0# else # define FXSAVE_AREA get_fpu_save_area() +# define UNMAP_FXSAVE_AREA (x) ((void)x)If only for consistency and to avoid setting bad precedents - parentheses please around x.
Ack.
Quoted 25 lines
Quoted 12 lines
xen/arch/x86/x86_emulate/blk.c +3
-0@@ -292,6 +295,9 @@ int x86_emul_blk( }else asmvolatile ("fxrstor %0" ::"m" (*fxsr) ); + +UNMAP_FXSAVE_AREA (fxsr); +break ; }xen/arch/x86/x86_emulate/blk.c int x86_emul_blk( · line 333
Quoted 8 lines
xen/arch/x86/x86_emulate/blk.c +3
-0@@ -320,6 +326,9 @@ int x86_emul_blk(if ( fxsr != ptr )/* i.e. s->op_bytes < sizeof(*fxsr) */ memcpy (ptr, fxsr, s->op_bytes); + +UNMAP_FXSAVE_AREA (fxsr); +break ; }So for now the emulator only supports FXSAVE / FXRSTOR. That'll need to change sooner or later. Is it really appropriate in that light to name the new macro after FXSAVE, when the underlying machinery uses all XSAVE?
Quoted 1 line
Jan
I have no strong feeling one way or the other, except that it should mirror the other macro's name. I'd say it makes more sense to rename _both_ after the emulator is XSAVE-aware. That the internal machinery is actually XSAVE-based is an implementation detail largely irrelevant at the call sites.
Cheers,
Alejandro
Re: [PATCH v2 10/13] x86/mpx: Map/unmap xsave area in in read_bndcfgu()
In reply to Jan BeulichQuoted 18 lines · Jan Beulich
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1027
Quoted 11 lines · Alejandro Vallejo
xen/arch/x86/xstate.c +2
-2@@ -1022,9 +1022,10 @@ int handle_xsetbv(u32 index, u64 new_bv)uint64_t read_bndcfgu (void ) { +uint64_t bndcfgu =0 ;unsigned long cr0 =read_cr0 (); -struct xsave_struct *xstate - = idle_vcpu[smp_processor_id ()]->arch.xsave_area; +struct vcpu *v = idle_vcpu[smp_processor_id ()];Can this be pointer-to-const? Certainly right now, so the question is rather meant to be forward looking.
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1028
Quoted 1 line
xen/arch/x86/xstate.c +1
-0+struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);
Quoted 7 lines
This certainly can be pointer-to-const, just like ...
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1029
Quoted 1 line
xen/arch/x86/xstate.c +0
-0const struct xstate_bndcsr *bndcsr;... this is.
Jan
Yes, those retained non-const because of the now missing patch to zero-out bndcfgu.
Cheers,
Alejandro
Re: [PATCH v2 09/13] x86/emulator: Refactor FXSAVE_AREA to use wrappers
In reply to Alejandro VallejoQuoted 16 lines · Alejandro Vallejo
Quoted 14 lines · Jan Beulich
xen/arch/x86/x86_emulate/blk.c line 16
Quoted 10 lines · Alejandro Vallejo
xen/arch/x86/x86_emulate/blk.c +3
-1@@ -11,9 +11,12 @@ !defined(X86EMUL_NO_SIMD)# ifdef __XEN__# include <asm/xstate.h> -# define FXSAVE_AREA ((void *)¤t->arch.xsave_area->fpu_sse) +/* has a fastpath for `current`, so there's no actual map */ +# define FXSAVE_AREA ((void *)VCPU_MAP_XSAVE_AREA(current)) +# define UNMAP_FXSAVE_AREA (x) VCPU_UNMAP_XSAVE_AREA(currt ent, x)The typo of the first argument strongly suggests that the macro should already now evaluate its parameters, also pleasing Misra.
Quoted 5 lines
Not an unreasonable takeaway. I can expand as follows instead:
#define
VCPU_UNMAP_XSAVE_AREA(v, x)({ (void)(v); x; })Thoughts?
Why would x not also be cast to void?
Jan
Re: [PATCH v2 10/13] x86/mpx: Map/unmap xsave area in in read_bndcfgu()
In reply to Alejandro VallejoQuoted 19 lines · Alejandro Vallejo
Quoted 18 lines · Jan Beulich
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1027
Quoted 11 lines · Alejandro Vallejo
xen/arch/x86/xstate.c +2
-2@@ -1022,9 +1022,10 @@ int handle_xsetbv(u32 index, u64 new_bv)uint64_t read_bndcfgu (void ) { +uint64_t bndcfgu =0 ;unsigned long cr0 =read_cr0 (); -struct xsave_struct *xstate - = idle_vcpu[smp_processor_id ()]->arch.xsave_area; +struct vcpu *v = idle_vcpu[smp_processor_id ()];Can this be pointer-to-const? Certainly right now, so the question is rather meant to be forward looking.
Quoted 1 line
xen/arch/x86/xstate.c +1
-0+struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);
Quoted 8 lines
Quoted 5 lines
This certainly can be pointer-to-const, just like ...
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1029
Quoted 1 line
xen/arch/x86/xstate.c +0
-0const struct xstate_bndcsr *bndcsr;... this is.
Yes, those retained non-const because of the now missing patch to zero-out bndcfgu.
I'm afraid this reply is ambiguous as to what's going to happen in the next version. I can read both "will change" and "needs to stay" into it.
Jan
Re: [PATCH v2 10/13] x86/mpx: Map/unmap xsave area in in read_bndcfgu()
Quoted 26 lines · Jan Beulich
Quoted 25 lines · Alejandro Vallejo
Quoted 23 lines · Jan Beulich
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1027
Quoted 11 lines · Alejandro Vallejo
xen/arch/x86/xstate.c +2
-2@@ -1022,9 +1022,10 @@ int handle_xsetbv(u32 index, u64 new_bv)uint64_t read_bndcfgu (void ) { +uint64_t bndcfgu =0 ;unsigned long cr0 =read_cr0 (); -struct xsave_struct *xstate - = idle_vcpu[smp_processor_id ()]->arch.xsave_area; +struct vcpu *v = idle_vcpu[smp_processor_id ()];Can this be pointer-to-const? Certainly right now, so the question is rather meant to be forward looking.
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1028
Quoted 1 line
xen/arch/x86/xstate.c +1
-0+struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);This certainly can be pointer-to-const, just like ...
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1029
Quoted 1 line
xen/arch/x86/xstate.c +0
-0const struct xstate_bndcsr *bndcsr;... this is.
Quoted 7 lines
Quoted 2 lines
Yes, those retained non-const because of the now missing patch to zero-out bndcfgu.
I'm afraid this reply is ambiguous as to what's going to happen in the next version. I can read both "will change" and "needs to stay" into it.
Jan
It was an answer to "Can this be pointer to const?". Yes, I'll put the const back.
Cheers,
Alejandro
Re: [PATCH v2 09/13] x86/emulator: Refactor FXSAVE_AREA to use wrappers
In reply to Jan BeulichQuoted 19 lines · Jan Beulich
Quoted 18 lines · Alejandro Vallejo
Quoted 14 lines · Jan Beulich
xen/arch/x86/x86_emulate/blk.c line 16
Quoted 10 lines · Alejandro Vallejo
xen/arch/x86/x86_emulate/blk.c +3
-1@@ -11,9 +11,12 @@ !defined(X86EMUL_NO_SIMD)# ifdef __XEN__# include <asm/xstate.h> -# define FXSAVE_AREA ((void *)¤t->arch.xsave_area->fpu_sse) +/* has a fastpath for `current`, so there's no actual map */ +# define FXSAVE_AREA ((void *)VCPU_MAP_XSAVE_AREA(current)) +# define UNMAP_FXSAVE_AREA (x) VCPU_UNMAP_XSAVE_AREA(currt ent, x)The typo of the first argument strongly suggests that the macro should already now evaluate its parameters, also pleasing Misra.
Not an unreasonable takeaway. I can expand as follows instead:
Quoted 7 lines
Quoted 3 lines
#define
VCPU_UNMAP_XSAVE_AREA(v, x)({ (void)(v); x; })Thoughts?
Why would x not also be cast to void?
Jan
it should have the "x = NULL", in fact.
#define VCPU_UNMAP_XSAVE_AREA(v, x) do { (void)(v); (x) = NULL; } while(0)Regardless, the important bit was adding a separate statement for (v) casted to void. Leaving the rest as-is.
Cheers,
Alejandro
Re: [PATCH v2 10/13] x86/mpx: Map/unmap xsave area in in read_bndcfgu()
In reply to Alejandro VallejoQuoted 33 lines · Alejandro Vallejo
Quoted 32 lines · Jan Beulich
Quoted 19 lines · Alejandro Vallejo
Quoted 18 lines · Jan Beulich
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1027
Quoted 11 lines · Alejandro Vallejo
xen/arch/x86/xstate.c +2
-2@@ -1022,9 +1022,10 @@ int handle_xsetbv(u32 index, u64 new_bv)uint64_t read_bndcfgu (void ) { +uint64_t bndcfgu =0 ;unsigned long cr0 =read_cr0 (); -struct xsave_struct *xstate - = idle_vcpu[smp_processor_id ()]->arch.xsave_area; +struct vcpu *v = idle_vcpu[smp_processor_id ()];Can this be pointer-to-const? Certainly right now, so the question is rather meant to be forward looking.
Quoted 1 line
xen/arch/x86/xstate.c +1
-0+struct xsave_struct *xstate =VCPU_MAP_XSAVE_AREA (v);Quoted 8 lines
Quoted 5 lines
This certainly can be pointer-to-const, just like ...
xen/arch/x86/xstate.c int handle_xsetbv(u32 index, u64 new_bv) · line 1029
Quoted 1 line
xen/arch/x86/xstate.c +0
-0const struct xstate_bndcsr *bndcsr;... this is.
Yes, those retained non-const because of the now missing patch to zero-out bndcfgu.
I'm afraid this reply is ambiguous as to what's going to happen in the next version. I can read both "will change" and "needs to stay" into it.
Quoted 7 lines
Quoted 1 line
Jan
It was an answer to "Can this be pointer to const?". Yes, I'll put the const back.
Cheers,
Alejandro
Actually, xstate is the target of the assembly, so it will be written to (though not from C). It seems like asking for trouble modifying the target of a pointer to non-volatile const from inline assembly.
I'll leave it as-is in the interest of safety.
Cheers,
Alejandro