x86/fpu: Introduce cpu_has_xfeatures(xfeatures_mask, feature_name)

A lot of FPU using driver code is querying complex CPU features to be
able to figure out whether a given set of xstate features is supported
by the CPU or not.

Introduce a simplified API function that can be used on any CPU type
to get this information. Also add an error string return pointer,
so that the driver can print a meaningful error message with a
standardized feature name.

Also mark xfeatures_mask as __read_only.

Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 62035cc1d9614b237f35a60db879b3ddd4324c34..1429a7c736db813e84dc50ab9ee3644f33030f6d 100644 (file)
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -36,4 +36,13 @@ extern bool irq_fpu_usable(void);
 extern int  irq_ts_save(void);
 extern void irq_ts_restore(int TS_state);
 
+/*
+ * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
+ *
+ * If 'feature_name' is set then put a human-readable description of
+ * the feature there as well - this can be used to print error (or success)
+ * messages.
+ */
+extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+
 #endif /* _ASM_X86_FPU_API_H */

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index f549e2a443361f96b46bfdc4b24c4045bf4a09d9..2e52f01f4931bf3599263c771385bcbe481af452 100644 (file)
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -11,10 +11,23 @@
 #include <asm/tlbflush.h>
 #include <asm/xcr.h>
 
+static const char *xfeature_names[] =
+{
+       "x87 floating point registers"  ,
+       "SSE registers"                 ,
+       "AVX registers"                 ,
+       "MPX bounds registers"          ,
+       "MPX CSR"                       ,
+       "AVX-512 opmask"                ,
+       "AVX-512 Hi256"                 ,
+       "AVX-512 ZMM_Hi256"             ,
+       "unknown xstate feature"        ,
+};
+
 /*
  * Mask of xstate features supported by the CPU and the kernel:
  */
-u64 xfeatures_mask;
+u64 xfeatures_mask __read_mostly;
 
 /*
  * Represents init state for the supported extended state.
@@ -28,6 +41,44 @@ static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
 /* The number of supported xfeatures in xfeatures_mask: */
 static unsigned int xfeatures_nr;
 
+/*
+ * Return whether the system supports a given xfeature.
+ *
+ * Also return the name of the (most advanced) feature that the caller requested:
+ */
+int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
+{
+       u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+
+       if (unlikely(feature_name)) {
+               long xfeature_idx, max_idx;
+               u64 xfeatures_print;
+               /*
+                * So we use FLS here to be able to print the most advanced
+                * feature that was requested but is missing. So if a driver
+                * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the
+                * missing AVX feature - this is the most informative message
+                * to users:
+                */
+               if (xfeatures_missing)
+                       xfeatures_print = xfeatures_missing;
+               else
+                       xfeatures_print = xfeatures_needed;
+
+               xfeature_idx = fls64(xfeatures_print)-1;
+               max_idx = ARRAY_SIZE(xfeature_names)-1;
+               xfeature_idx = min(xfeature_idx, max_idx);
+
+               *feature_name = xfeature_names[xfeature_idx];
+       }
+
+       if (xfeatures_missing)
+               return 0;
+
+       return 1;
+}
+EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
+
 /*
  * When executing XSAVEOPT (optimized XSAVE), if a processor implementation
  * detects that an FPU state component is still (or is again) in its