[PATCH 13/23] x86/fpu: Make get_xsave_field_ptr() and get_xsave_addr() use feature number instead of mask
After changing the argument of __raw_xsave_addr() from a mask to number Dave suggested to check if it makes sense to do the same for get_xsave_addr(). As it turns out it does. Only get_xsave_addr() needs the mask to check if the requested feature is part of what is support/saved and then uses the number again. The shift operation is cheaper compared to "find last bit set". Also, the feature number uses less opcode space compared to the mask :) Make get_xsave_addr() argument a xfeature number instead of mask and fix up its callers. As part of this use xfeature_nr and xfeature_mask consistently. This results in changes to the kvm code as: feature -> xfeature_mask index -> xfeature_nr Suggested-by: Dave Hansen Signed-off-by: Sebastian Andrzej Siewior --- arch/x86/include/asm/fpu/xstate.h | 4 ++-- arch/x86/kernel/fpu/xstate.c | 23 +++ arch/x86/kernel/traps.c | 2 +- arch/x86/kvm/x86.c| 28 ++-- arch/x86/mm/mpx.c | 6 +++--- 5 files changed, 31 insertions(+), 32 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 48581988d78c7..fbe41f808e5d8 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -46,8 +46,8 @@ extern void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask); void fpu__xstate_clear_all_cpu_caps(void); -void *get_xsave_addr(struct xregs_state *xsave, int xstate); -const void *get_xsave_field_ptr(int xstate_field); +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); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 3dfe3627deaf6..375226055a413 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -832,15 +832,15 @@ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) * * Inputs: * xstate: the thread's storage area for all FPU data - * xstate_feature: state which is defined in xsave.h (e.g. - * XFEATURE_MASK_FP, XFEATURE_MASK_SSE, etc...) + * xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, + * XFEATURE_SSE, etc...) * Output: * address of the state in the xsave area, or NULL if the * field is not present in the xsave buffer. */ -void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) +void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { - int xfeature_nr; + u64 xfeature_mask = 1ULL << xfeature_nr; /* * Do we even *have* xsave state? */ @@ -852,11 +852,11 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) * have not enabled. Remember that pcntxt_mask is * what we write to the XCR0 register. */ - WARN_ONCE(!(xfeatures_mask & xstate_feature), + WARN_ONCE(!(xfeatures_mask & xfeature_mask), "get of unsupported state"); /* * This assumes the last 'xsave*' instruction to -* have requested that 'xstate_feature' be saved. +* have requested that 'xfeature_mask' be saved. * If it did not, we might be seeing and old value * of the field in the buffer. * @@ -865,10 +865,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) * or because the "init optimization" caused it * to not be saved. */ - if (!(xsave->header.xfeatures & xstate_feature)) + if (!(xsave->header.xfeatures & xfeature_mask)) return NULL; - xfeature_nr = fls64(xstate_feature) - 1; return __raw_xsave_addr(xsave, xfeature_nr); } EXPORT_SYMBOL_GPL(get_xsave_addr); @@ -884,13 +883,13 @@ EXPORT_SYMBOL_GPL(get_xsave_addr); * Note that this only works on the current task. * * Inputs: - * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, - * XFEATURE_MASK_SSE, etc...) + * @xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, + * XFEATURE_SSE, etc...) * Output: * address of the state in the xsave area or NULL if the state * is not present or is in its 'init state'. */ -const void *get_xsave_field_ptr(int xsave_state) +const void *get_xsave_field_ptr(int xfeature_nr) { struct fpu *fpu = >thread.fpu; @@ -900,7 +899,7 @@ const void *get_xsave_field_ptr(int xsave_state) */ fpu__save(fpu); - return get_xsave_addr(>state.xsave, xsave_state); + return get_xsave_addr(>state.xsave, xfeature_nr); } #ifdef CONFIG_ARCH_HAS_PKEYS diff --git
[PATCH 13/23] x86/fpu: Make get_xsave_field_ptr() and get_xsave_addr() use feature number instead of mask
After changing the argument of __raw_xsave_addr() from a mask to number Dave suggested to check if it makes sense to do the same for get_xsave_addr(). As it turns out it does. Only get_xsave_addr() needs the mask to check if the requested feature is part of what is support/saved and then uses the number again. The shift operation is cheaper compared to "find last bit set". Also, the feature number uses less opcode space compared to the mask :) Make get_xsave_addr() argument a xfeature number instead of mask and fix up its callers. As part of this use xfeature_nr and xfeature_mask consistently. This results in changes to the kvm code as: feature -> xfeature_mask index -> xfeature_nr Suggested-by: Dave Hansen Signed-off-by: Sebastian Andrzej Siewior --- arch/x86/include/asm/fpu/xstate.h | 4 ++-- arch/x86/kernel/fpu/xstate.c | 23 +++ arch/x86/kernel/traps.c | 2 +- arch/x86/kvm/x86.c| 28 ++-- arch/x86/mm/mpx.c | 6 +++--- 5 files changed, 31 insertions(+), 32 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 48581988d78c7..fbe41f808e5d8 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -46,8 +46,8 @@ extern void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask); void fpu__xstate_clear_all_cpu_caps(void); -void *get_xsave_addr(struct xregs_state *xsave, int xstate); -const void *get_xsave_field_ptr(int xstate_field); +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); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 3dfe3627deaf6..375226055a413 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -832,15 +832,15 @@ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) * * Inputs: * xstate: the thread's storage area for all FPU data - * xstate_feature: state which is defined in xsave.h (e.g. - * XFEATURE_MASK_FP, XFEATURE_MASK_SSE, etc...) + * xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, + * XFEATURE_SSE, etc...) * Output: * address of the state in the xsave area, or NULL if the * field is not present in the xsave buffer. */ -void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) +void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { - int xfeature_nr; + u64 xfeature_mask = 1ULL << xfeature_nr; /* * Do we even *have* xsave state? */ @@ -852,11 +852,11 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) * have not enabled. Remember that pcntxt_mask is * what we write to the XCR0 register. */ - WARN_ONCE(!(xfeatures_mask & xstate_feature), + WARN_ONCE(!(xfeatures_mask & xfeature_mask), "get of unsupported state"); /* * This assumes the last 'xsave*' instruction to -* have requested that 'xstate_feature' be saved. +* have requested that 'xfeature_mask' be saved. * If it did not, we might be seeing and old value * of the field in the buffer. * @@ -865,10 +865,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) * or because the "init optimization" caused it * to not be saved. */ - if (!(xsave->header.xfeatures & xstate_feature)) + if (!(xsave->header.xfeatures & xfeature_mask)) return NULL; - xfeature_nr = fls64(xstate_feature) - 1; return __raw_xsave_addr(xsave, xfeature_nr); } EXPORT_SYMBOL_GPL(get_xsave_addr); @@ -884,13 +883,13 @@ EXPORT_SYMBOL_GPL(get_xsave_addr); * Note that this only works on the current task. * * Inputs: - * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, - * XFEATURE_MASK_SSE, etc...) + * @xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, + * XFEATURE_SSE, etc...) * Output: * address of the state in the xsave area or NULL if the state * is not present or is in its 'init state'. */ -const void *get_xsave_field_ptr(int xsave_state) +const void *get_xsave_field_ptr(int xfeature_nr) { struct fpu *fpu = >thread.fpu; @@ -900,7 +899,7 @@ const void *get_xsave_field_ptr(int xsave_state) */ fpu__save(fpu); - return get_xsave_addr(>state.xsave, xsave_state); + return get_xsave_addr(>state.xsave, xfeature_nr); } #ifdef CONFIG_ARCH_HAS_PKEYS diff --git