Merge tag 'x86-cpu-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu updates from Ingo Molnar:
 "Misc updates:

   - Extend the x86 family/model macros with a steppings dimension,
     because x86 life isn't complex enough and Intel uses steppings to
     differentiate between different CPUs. :-/

   - Convert the TSC deadline timer quirks to the steppings macros.

   - Clean up asm mnemonics.

   - Fix the handling of an AMD erratum, or in other words, fix a kernel
     erratum"

* tag 'x86-cpu-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Use RDRAND and RDSEED mnemonics in archrandom.h
  x86/cpu: Use INVPCID mnemonic in invpcid.h
  x86/cpu/amd: Make erratum #1054 a legacy erratum
  x86/apic: Convert the TSC deadline timer matching to steppings macro
  x86/cpu: Add a X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS() macro
  x86/cpu: Add a steppings field to struct x86_cpu_id

diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 7a4bb1b..ebc248e 100644 (file)
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -15,16 +15,6 @@
 
 #define RDRAND_RETRY_LOOPS     10
 
-#define RDRAND_INT     ".byte 0x0f,0xc7,0xf0"
-#define RDSEED_INT     ".byte 0x0f,0xc7,0xf8"
-#ifdef CONFIG_X86_64
-# define RDRAND_LONG   ".byte 0x48,0x0f,0xc7,0xf0"
-# define RDSEED_LONG   ".byte 0x48,0x0f,0xc7,0xf8"
-#else
-# define RDRAND_LONG   RDRAND_INT
-# define RDSEED_LONG   RDSEED_INT
-#endif
-
 /* Unconditional execution of RDRAND and RDSEED */
 
 static inline bool __must_check rdrand_long(unsigned long *v)
@@ -32,9 +22,9 @@ static inline bool __must_check rdrand_long(unsigned long *v)
        bool ok;
        unsigned int retry = RDRAND_RETRY_LOOPS;
        do {
-               asm volatile(RDRAND_LONG
+               asm volatile("rdrand %[out]"
                             CC_SET(c)
-                            : CC_OUT(c) (ok), "=a" (*v));
+                            : CC_OUT(c) (ok), [out] "=r" (*v));
                if (ok)
                        return true;
        } while (--retry);
@@ -46,9 +36,9 @@ static inline bool __must_check rdrand_int(unsigned int *v)
        bool ok;
        unsigned int retry = RDRAND_RETRY_LOOPS;
        do {
-               asm volatile(RDRAND_INT
+               asm volatile("rdrand %[out]"
                             CC_SET(c)
-                            : CC_OUT(c) (ok), "=a" (*v));
+                            : CC_OUT(c) (ok), [out] "=r" (*v));
                if (ok)
                        return true;
        } while (--retry);
@@ -58,18 +48,18 @@ static inline bool __must_check rdrand_int(unsigned int *v)
 static inline bool __must_check rdseed_long(unsigned long *v)
 {
        bool ok;
-       asm volatile(RDSEED_LONG
+       asm volatile("rdseed %[out]"
                     CC_SET(c)
-                    : CC_OUT(c) (ok), "=a" (*v));
+                    : CC_OUT(c) (ok), [out] "=r" (*v));
        return ok;
 }
 
 static inline bool __must_check rdseed_int(unsigned int *v)
 {
        bool ok;
-       asm volatile(RDSEED_INT
+       asm volatile("rdseed %[out]"
                     CC_SET(c)
-                    : CC_OUT(c) (ok), "=a" (*v));
+                    : CC_OUT(c) (ok), [out] "=r" (*v));
        return ok;
 }
 

diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index cf3d621..eb8fced 100644 (file)
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -20,12 +20,14 @@
 #define X86_CENTAUR_FAM6_C7_D          0xd
 #define X86_CENTAUR_FAM6_NANO          0xf
 
+#define X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
 /**
- * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Base macro for CPU matching
+ * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
  * @_vendor:   The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
  *             The name is expanded to X86_VENDOR_@_vendor
  * @_family:   The family number or X86_FAMILY_ANY
  * @_model:    The model number, model constant or X86_MODEL_ANY
+ * @_steppings:        Bitmask for steppings, stepping constant or X86_STEPPING_ANY
  * @_feature:  A X86_FEATURE bit or X86_FEATURE_ANY
  * @_data:     Driver specific data or NULL. The internal storage
  *             format is unsigned long. The supplied value, pointer
@@ -37,15 +39,34 @@
  * into another macro at the usage site for good reasons, then please
  * start this local macro with X86_MATCH to allow easy grepping.
  */
-#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(_vendor, _family, _model,   \
-                                          _feature, _data) {           \
+#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+                                                   _steppings, _feature, _data) { \
        .vendor         = X86_VENDOR_##_vendor,                         \
        .family         = _family,                                      \
        .model          = _model,                                       \
+       .steppings      = _steppings,                                   \
        .feature        = _feature,                                     \
        .driver_data    = (unsigned long) _data                         \
 }
 
+/**
+ * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Macro for CPU matching
+ * @_vendor:   The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *             The name is expanded to X86_VENDOR_@_vendor
+ * @_family:   The family number or X86_FAMILY_ANY
+ * @_model:    The model number, model constant or X86_MODEL_ANY
+ * @_feature:  A X86_FEATURE bit or X86_FEATURE_ANY
+ * @_data:     Driver specific data or NULL. The internal storage
+ *             format is unsigned long. The supplied value, pointer
+ *             etc. is casted to unsigned long internally.
+ *
+ * The steppings arguments of X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE() is
+ * set to wildcards.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model, feature, data) \
+       X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(vendor, family, model, \
+                                               X86_STEPPING_ANY, feature, data)
+
 /**
  * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature
  * @vendor:    The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
@@ -139,6 +160,10 @@
 #define X86_MATCH_INTEL_FAM6_MODEL(model, data)                                \
        X86_MATCH_VENDOR_FAM_MODEL(INTEL, 6, INTEL_FAM6_##model, data)
 
+#define X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(model, steppings, data)   \
+       X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
+                                                    steppings, X86_FEATURE_ANY, data)
+
 /*
  * Match specific microcode revisions.
  *

diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
index 989cfa8..734482a 100644 (file)
--- a/arch/x86/include/asm/invpcid.h
+++ b/arch/x86/include/asm/invpcid.h
@@ -12,12 +12,9 @@ static inline void __invpcid(unsigned long pcid, unsigned long addr,
         * stale TLB entries and, especially if we're flushing global
         * mappings, we don't want the compiler to reorder any subsequent
         * memory accesses before the TLB flush.
-        *
-        * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
-        * invpcid (%rcx), %rax in long mode.
         */
-       asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-                     : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+       asm volatile("invpcid %[desc], %[type]"
+                    :: [desc] "m" (desc), [type] "r" (type) : "memory");
 }
 
 #define INVPCID_TYPE_INDIV_ADDR                0

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e53dda2..4b1d31b 100644 (file)
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -544,46 +544,20 @@ static struct clock_event_device lapic_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
-static __init u32 hsx_deadline_rev(void)
-{
-       switch (boot_cpu_data.x86_stepping) {
-       case 0x02: return 0x3a; /* EP */
-       case 0x04: return 0x0f; /* EX */
-       }
-
-       return ~0U;
-}
-
-static __init u32 bdx_deadline_rev(void)
-{
-       switch (boot_cpu_data.x86_stepping) {
-       case 0x02: return 0x00000011;
-       case 0x03: return 0x0700000e;
-       case 0x04: return 0x0f00000c;
-       case 0x05: return 0x0e000003;
-       }
-
-       return ~0U;
-}
-
-static __init u32 skx_deadline_rev(void)
-{
-       switch (boot_cpu_data.x86_stepping) {
-       case 0x03: return 0x01000136;
-       case 0x04: return 0x02000014;
-       }
+static const struct x86_cpu_id deadline_match[] __initconst = {
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */
 
-       if (boot_cpu_data.x86_stepping > 4)
-               return 0;
+       X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X,        0x0b000020),
 
-       return ~0U;
-}
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011),
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e),
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c),
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003),
 
-static const struct x86_cpu_id deadline_match[] __initconst = {
-       X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X,          &hsx_deadline_rev),
-       X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X,        0x0b000020),
-       X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D,        &bdx_deadline_rev),
-       X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_X,          &skx_deadline_rev),
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136),
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014),
+       X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0),
 
        X86_MATCH_INTEL_FAM6_MODEL( HASWELL,            0x22),
        X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L,          0x20),
@@ -615,14 +589,7 @@ static __init bool apic_validate_deadline_timer(void)
        if (!m)
                return true;
 
-       /*
-        * Function pointers will have the MSB set due to address layout,
-        * immediate revisions will not.
-        */
-       if ((long)m->driver_data < 0)
-               rev = ((u32 (*)(void))(m->driver_data))();
-       else
-               rev = (u32)m->driver_data;
+       rev = (u32)m->driver_data;
 
        if (boot_cpu_data.microcode >= rev)
                return true;

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c36e899..d4806ea 100644 (file)
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1145,8 +1145,7 @@ static const int amd_erratum_383[] =
 
 /* #1054: Instructions Retired Performance Counter May Be Inaccurate */
 static const int amd_erratum_1054[] =
-       AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
-
+       AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
 
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {

diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index d3482eb..ad67760 100644 (file)
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -39,13 +39,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
        const struct x86_cpu_id *m;
        struct cpuinfo_x86 *c = &boot_cpu_data;
 
-       for (m = match; m->vendor | m->family | m->model | m->feature; m++) {
+       for (m = match;
+            m->vendor | m->family | m->model | m->steppings | m->feature;
+            m++) {
                if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor)
                        continue;
                if (m->family != X86_FAMILY_ANY && c->x86 != m->family)
                        continue;
                if (m->model != X86_MODEL_ANY && c->x86_model != m->model)
                        continue;
+               if (m->steppings != X86_STEPPING_ANY &&
+                   !(BIT(c->x86_stepping) & m->steppings))
+                       continue;
                if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature))
                        continue;
                return m;

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 4c2ddd0..0754b8d 100644 (file)
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -663,6 +663,7 @@ struct x86_cpu_id {
        __u16 vendor;
        __u16 family;
        __u16 model;
+       __u16 steppings;
        __u16 feature;  /* bit index */
        kernel_ulong_t driver_data;
 };
@@ -671,6 +672,7 @@ struct x86_cpu_id {
 #define X86_VENDOR_ANY 0xffff
 #define X86_FAMILY_ANY 0
 #define X86_MODEL_ANY  0
+#define X86_STEPPING_ANY 0
 #define X86_FEATURE_ANY 0      /* Same as FPU, you can't test for that */
 
 /*