diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 112cefacf2af07b216cb598232bcc586a76fa919..b419f43ce0c589ce934195b77296760dc300830c 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -32,7 +32,7 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/aes.h>
 #include <crypto/ablk_helper.h>
 #include <crypto/scatterwalk.h>
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 1937fc1d876338aa0aa9bb5fddea9e0aa3541707..07d2c6c86a5483216684970489fcba3b4478007d 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -35,7 +35,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index b6c67bf30fdf6704f6d83b093ee73ae7d9b77fcf..a3fcfc97a311d5b660e0dcda3be489038f231dce 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -29,7 +29,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
 
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index f368ba261739fa09be28bc02fe34cf3112099fa8..5a2f30f9f52dca78820b67cef7c025c53aa0b735 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -18,7 +18,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct crypto_fpu_ctx {
 	struct crypto_blkcipher *child;
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 2079baf06bdd3b64e7f61ec3fecf088c4bd8bc24..64d7cf1b50e112ab370ac63e59e9ff89d4d677e0 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -19,7 +19,7 @@
 #include <crypto/cryptd.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/hash.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpu_device_id.h>
 
 #define GHASH_BLOCK_SIZE	16
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 33d1b9dc14cc751203ba72af1585f6685558b7fc..cb3bf19dca5a3262c74ae98ac36709e49e12c20d 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -29,7 +29,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index ccc338881ee81886b6de43963df23d179d510b22..9eaf7abaf4dc8744096efb25c18690965dc0a411 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -37,7 +37,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 #include <linux/string.h>
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index d9fa4c1e063ff631cc09e168c6c6747527edf334..e0d6a67f567d235ebf63ec065f00c681d264ffbd 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -35,7 +35,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b5e2d56518517010e6869d592aa505450965e36f..1a66e6110f4bd909193b76c025ddd9107f29ea86 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -36,7 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/xcr.h>
 #include <asm/xsave.h>
 #include <asm/crypto/twofish.h>
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index 1eef55596e82cade6ecc0e910488a6fcc9e0b74a..03bb1065c3352826843a305b15399751a5c860ae 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -7,7 +7,7 @@
 
 #include <linux/kernel.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <crypto/b128ops.h>
 
 typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3738b138b843d46467c75a910d916cc79ebad25f..155162ea0e00292b619cc2a02ff8b2f31fafd02b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_EFI_H
 #define _ASM_X86_EFI_H
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/pgtable.h>
 
 /*
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 21ad681794548b47e8e5bf186cf12bfee5252143..d68b349b424777def239b8661354bd43aa3558aa 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -15,7 +15,7 @@
 #include <linux/slab.h>
 
 #include <asm/user.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/xsave.h>
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/fpu/api.h
similarity index 96%
rename from arch/x86/include/asm/i387.h
rename to arch/x86/include/asm/fpu/api.h
index b8f7d76ac0662444e485bd4ed46a13f125fb1935..9d3a6f3cfc1b6587c5bdf0b92695ddbebf6d8047 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -7,8 +7,8 @@
  * x86-64 work by Andi Kleen 2002
  */
 
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
+#ifndef _ASM_X86_FPU_API_H
+#define _ASM_X86_FPU_API_H
 
 #ifndef __ASSEMBLY__
 
@@ -104,4 +104,4 @@ extern void fpu__save(struct fpu *fpu);
 
 #endif /* __ASSEMBLY__ */
 
-#endif /* _ASM_X86_I387_H */
+#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h
index ee80b92f00962a392a824221dbdbeb781b6312bf..6c8a7ed13365ae5dd675fd4b158c8034ba213a29 100644
--- a/arch/x86/include/asm/simd.h
+++ b/arch/x86/include/asm/simd.h
@@ -1,5 +1,5 @@
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * may_use_simd - whether it is allowable at this time to issue SIMD
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 552d6c90a6d43dbebbae0756ba10061bc0969e8d..d1793f06854d28f22481c40f03cd2171d7b13495 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_32_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /* image of the saved processor state */
 struct saved_context {
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index bc6232834babf33973c8a4e6da1ce63cd159dce4..7ebf0ebe4e687f3704cac47b3de3dd1b906d27e8 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_64_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index d8829751b3f895e9fd19fa6bd597758650f417b8..1f5c5161ead682664dc30fc5dda802de2de0bc4b 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -36,7 +36,7 @@
  * no advantages to be gotten from x86-64 here anyways.
  */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #ifdef CONFIG_X86_32
 /* reduce register pressure */
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index ce05722e3c68bce4d72a1bcdc9e798b5014581cf..5a08bc8bff33934e10b4b9afe8e3236ac8c5ce93 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -26,7 +26,7 @@
 #define XO3(x, y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
 #define XO4(x, y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 static void
 xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 492b29802f571b0363a22fe686f708c8235c317a..7c0a517ec7511a667166c216df8357087ff3e7b0 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -18,7 +18,7 @@
 #ifdef CONFIG_AS_AVX
 
 #include <linux/compiler.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define BLOCK4(i) \
 		BLOCK(32 * i, 0) \
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index eb8be0c5823b2dfe9cf670fe7d5d71a0c7305cb9..29dd74318ec6f726b816b4d6b09f30e12fe7f6c6 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,7 +12,7 @@
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/msr.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
diff --git a/arch/x86/kernel/fpu/xsave.c b/arch/x86/kernel/fpu/xsave.c
index 80b0c8fa50c50c091fc5a63ce72a863808ed5633..8aa3b864a2e07b577c76ee6547e6ef7a2bc4c800 100644
--- a/arch/x86/kernel/fpu/xsave.c
+++ b/arch/x86/kernel/fpu/xsave.c
@@ -9,7 +9,7 @@
 #include <linux/bootmem.h>
 #include <linux/compat.h>
 #include <linux/cpu.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/fpu-internal.h>
 #include <asm/sigframe.h>
 #include <asm/tlbflush.h>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b61687bd79facc3f6ed0339b68ecf3fcf43aed..5cb738a18ca337534b40de44802c4c0dd2ffdafb 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -40,7 +40,7 @@
 #include <asm/vmx.h>
 #include <asm/virtext.h>
 #include <asm/mce.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/xcr.h>
 #include <asm/perf_event.h>
 #include <asm/debugreg.h>
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 8f9a133cc09934c2de2fa77a1eecb14ce5f94c06..27f8eea0d6eb0c9798f4c45e18fa8099c452a2a8 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -70,7 +70,7 @@
 #include <asm/e820.h>
 #include <asm/mce.h>
 #include <asm/io.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/stackprotector.h>
 #include <asm/reboot.h>		/* for struct machine_ops */
 #include <asm/kvm_para.h>
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index c9f2d9ba8dd8c2da54b0bbd07c37be1d38aa49c4..e5e3ed8dc0798bd007e8573ddbf57dc4e2312049 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -22,7 +22,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/asm.h>
 
 void *_mmx_memcpy(void *to, const void *from, size_t len)
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index e394bcb4275dfac0946d383569729adbf34f6d53..3bb4c6a24ea5060aed6e62f5ee7baa51959a3ed7 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -31,7 +31,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/user.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #include "fpu_system.h"
 #include "fpu_emu.h"
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index a3bebef255ad3af669c2134ce85805d0af4b0523..0c98a9d51a2494e6a49ef49e6bfb557cefca1974 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -33,7 +33,7 @@
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 
 
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index c178ed8c3908d3a92e55432aecb86e0e6e1501ee..da2d6777bd092f0a373e14cc960514b8a4f5d148 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -22,7 +22,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/byteorder.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Number of data blocks actually fetched for each xcrypt insn.
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 95f7d27ce491f000458a257e5dfa55a6105b433b..4e154c9b92064bb1fbafeb805bcb77f9cc2d1bdf 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/scatterlist.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct padlock_sha_desc {
 	struct shash_desc fallback;
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index bcb534a5512d6b1e5c517b11146e4c3e42765bb8..fce5989e66d91acdbf5528000ec673944763c97d 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -46,7 +46,7 @@
 #include <asm/setup.h>
 #include <asm/lguest.h>
 #include <asm/uaccess.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/tlbflush.h>
 #include "../lg.h"
 
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
index b7595484a8150c02e086f5d1a3ac41cd971bd91b..8fe9d9662abbcda7563000c00e5f516dc156f05f 100644
--- a/lib/raid6/x86.h
+++ b/lib/raid6/x86.h
@@ -23,7 +23,7 @@
 
 #ifdef __KERNEL__ /* Real code */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #else /* Dummy code for user space testing */