[RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[Ingo Molnar]

Linus,

Please consider pulling the latest x86-nuke386-for-linus git 
tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-nuke386-for-linus

   HEAD: 11af32b69ef7ee64c7d8848cad71a6f3749d9e37 x86, 386 removal: Document Nx586 as a 386 and thus unsupported

This tree removes ancient-386-CPUs support and thus zaps quite a 
bit of complexity:

   24 files changed, 56 insertions(+), 425 deletions(-)

... which complexity has plagued us with extra work whenever we 
wanted to change SMP primitives, for years.

Unfortunately there's a nostalgic cost: your old original 386 
DX33 system from early 1991 won't be able to boot modern Linux 
kernels anymore. Sniff.

 Thanks,

	Ingo

------------------>
H. Peter Anvin (9):
      x86, 386 removal: Remove CONFIG_M386 from Kconfig
      x86, 386 removal: Remove CONFIG_CMPXCHG
      x86, 386 removal: Remove CONFIG_XADD
      x86, 386 removal: Remove CONFIG_BSWAP
      x86, 386 removal: Remove CONFIG_INVLPG
      x86, 386 removal: Remove CONFIG_X86_WP_WORKS_OK
      x86, 386 removal: Remove CONFIG_X86_POPAD_OK
      x86, cleanups: Simplify sync_core() in the case of no CPUID
      x86, 386 removal: Document Nx586 as a 386 and thus unsupported


 arch/x86/Kconfig                  | 11 ++----
 arch/x86/Kconfig.cpu              | 73 +++++++++++----------------------------
 arch/x86/Makefile_32.cpu          |  1 -
 arch/x86/include/asm/atomic.h     | 16 ---------
 arch/x86/include/asm/cmpxchg_32.h | 55 -----------------------------
 arch/x86/include/asm/cpufeature.h |  6 ----
 arch/x86/include/asm/futex.h      | 12 -------
 arch/x86/include/asm/local.h      | 18 +---------
 arch/x86/include/asm/module.h     |  2 --
 arch/x86/include/asm/percpu.h     |  3 --
 arch/x86/include/asm/processor.h  | 33 ++++++++++++------
 arch/x86/include/asm/swab.h       | 29 ++--------------
 arch/x86/include/asm/tlbflush.h   |  3 --
 arch/x86/include/asm/uaccess.h    | 42 ----------------------
 arch/x86/kernel/cpu/amd.c         |  3 --
 arch/x86/kernel/cpu/bugs.c        | 41 ++--------------------
 arch/x86/kernel/cpu/intel.c       |  4 ---
 arch/x86/lib/Makefile             |  1 -
 arch/x86/lib/cmpxchg.c            | 54 -----------------------------
 arch/x86/lib/usercopy_32.c        | 57 ------------------------------
 arch/x86/mm/init_32.c             |  5 +--
 arch/x86/mm/tlb.c                 |  8 ++---
 arch/x86/um/Kconfig               |  2 +-
 arch/x86/xen/Kconfig              |  2 +-
 24 files changed, 56 insertions(+), 425 deletions(-)
 delete mode 100644 arch/x86/lib/cmpxchg.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 46c3bff..631b298 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -69,8 +69,8 @@ config X86
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_DEBUG_KMEMLEAK
 	select ANON_INODES
-	select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
-	select HAVE_CMPXCHG_LOCAL if !M386
+	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
+	select HAVE_CMPXCHG_LOCAL
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
@@ -171,13 +171,8 @@ config ARCH_MAY_HAVE_PC_FDC
 	def_bool y
 	depends on ISA_DMA_API
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-	depends on !X86_XADD
-
 config RWSEM_XCHGADD_ALGORITHM
 	def_bool y
-	depends on X86_XADD
 
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
@@ -1100,7 +1095,7 @@ config HIGHMEM4G
 
 config HIGHMEM64G
 	bool "64GB"
-	depends on !M386 && !M486
+	depends on !M486
 	select X86_PAE
 	---help---
 	  Select this if you have a 32-bit processor and more than 4
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index f3b86d0..c026cca 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -4,23 +4,24 @@ choice
 	default M686 if X86_32
 	default GENERIC_CPU if X86_64
 
-config M386
-	bool "386"
-	depends on X86_32 && !UML
+config M486
+	bool "486"
+	depends on X86_32
 	---help---
-	  This is the processor type of your CPU. This information is used for
-	  optimizing purposes. In order to compile a kernel that can run on
-	  all x86 CPU types (albeit not optimally fast), you can specify
-	  "386" here.
+	  This is the processor type of your CPU. This information is
+	  used for optimizing purposes. In order to compile a kernel
+	  that can run on all supported x86 CPU types (albeit not
+	  optimally fast), you can specify "486" here.
+
+	  Note that the 386 is no longer supported, this includes
+	  AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI 486DLC/DLC2,
+	  UMC 486SX-S and the NexGen Nx586.
 
 	  The kernel will not necessarily run on earlier architectures than
 	  the one you have chosen, e.g. a Pentium optimized kernel will run on
 	  a PPro, but not necessarily on a i486.
 
 	  Here are the settings recommended for greatest speed:
-	  - "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI
-	  486DLC/DLC2, and UMC 486SX-S.  Only "386" kernels will run on a 386
-	  class machine.
 	  - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or
 	  SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S.
 	  - "586" for generic Pentium CPUs lacking the TSC
@@ -43,16 +44,7 @@ config M386
 	  - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above).
 	  - "VIA C7" for VIA C7.
 
-	  If you don't know what to do, choose "386".
-
-config M486
-	bool "486"
-	depends on X86_32
-	---help---
-	  Select this for a 486 series processor, either Intel or one of the
-	  compatible processors from AMD, Cyrix, IBM, or Intel.  Includes DX,
-	  DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or
-	  U5S.
+	  If you don't know what to do, choose "486".
 
 config M586
 	bool "586/K5/5x86/6x86/6x86MX"
@@ -305,24 +297,16 @@ config X86_INTERNODE_CACHE_SHIFT
 	default "12" if X86_VSMP
 	default X86_L1_CACHE_SHIFT
 
-config X86_CMPXCHG
-	def_bool y
-	depends on X86_64 || (X86_32 && !M386)
-
 config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || MPSC
 	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
-	default "4" if MELAN || M486 || M386 || MGEODEGX1
+	default "4" if MELAN || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
-config X86_XADD
-	def_bool y
-	depends on !M386
-
 config X86_PPRO_FENCE
 	bool "PentiumPro memory ordering errata workaround"
-	depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1
+	depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1
 	---help---
 	  Old PentiumPro multiprocessor systems had errata that could cause
 	  memory operations to violate the x86 ordering standard in rare cases.
@@ -335,27 +319,11 @@ config X86_PPRO_FENCE
 
 config X86_F00F_BUG
 	def_bool y
-	depends on M586MMX || M586TSC || M586 || M486 || M386
+	depends on M586MMX || M586TSC || M586 || M486
 
 config X86_INVD_BUG
 	def_bool y
-	depends on M486 || M386
-
-config X86_WP_WORKS_OK
-	def_bool y
-	depends on !M386
-
-config X86_INVLPG
-	def_bool y
-	depends on X86_32 && !M386
-
-config X86_BSWAP
-	def_bool y
-	depends on X86_32 && !M386
-
-config X86_POPAD_OK
-	def_bool y
-	depends on X86_32 && !M386
+	depends on M486
 
 config X86_ALIGNMENT_16
 	def_bool y
@@ -412,12 +380,11 @@ config X86_MINIMUM_CPU_FAMILY
 	default "64" if X86_64
 	default "6" if X86_32 && X86_P6_NOP
 	default "5" if X86_32 && X86_CMPXCHG64
-	default "4" if X86_32 && (X86_XADD || X86_CMPXCHG || X86_BSWAP || X86_WP_WORKS_OK)
-	default "3"
+	default "4"
 
 config X86_DEBUGCTLMSR
 	def_bool y
-	depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486 || M386) && !UML
+	depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486) && !UML
 
 menuconfig PROCESSOR_SELECT
 	bool "Supported processor vendors" if EXPERT
@@ -441,7 +408,7 @@ config CPU_SUP_INTEL
 config CPU_SUP_CYRIX_32
 	default y
 	bool "Support Cyrix processors" if PROCESSOR_SELECT
-	depends on M386 || M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT)
+	depends on M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT)
 	---help---
 	  This enables detection, tunings and quirks for Cyrix processors
 
@@ -495,7 +462,7 @@ config CPU_SUP_TRANSMETA_32
 config CPU_SUP_UMC_32
 	default y
 	bool "Support UMC processors" if PROCESSOR_SELECT
-	depends on M386 || M486 || (EXPERT && !64BIT)
+	depends on M486 || (EXPERT && !64BIT)
 	---help---
 	  This enables detection, tunings and quirks for UMC processors
 
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 86cee7b..6647ed4 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -10,7 +10,6 @@ tune		= $(call cc-option,-mcpu=$(1),$(2))
 endif
 
 align := $(cc-option-align)
-cflags-$(CONFIG_M386)		+= -march=i386
 cflags-$(CONFIG_M486)		+= -march=i486
 cflags-$(CONFIG_M586)		+= -march=i586
 cflags-$(CONFIG_M586TSC)	+= -march=i586
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index b6c3b82..722aa3b 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -172,23 +172,7 @@ static inline int atomic_add_negative(int i, atomic_t *v)
  */
 static inline int atomic_add_return(int i, atomic_t *v)
 {
-#ifdef CONFIG_M386
-	int __i;
-	unsigned long flags;
-	if (unlikely(boot_cpu_data.x86 <= 3))
-		goto no_xadd;
-#endif
-	/* Modern 486+ processor */
 	return i + xadd(&v->counter, i);
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
-	raw_local_irq_save(flags);
-	__i = atomic_read(v);
-	atomic_set(v, i + __i);
-	raw_local_irq_restore(flags);
-	return i + __i;
-#endif
 }
 
 /**
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 53f4b21..f8bf2ee 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -34,9 +34,7 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
 		     : "memory");
 }
 
-#ifdef CONFIG_X86_CMPXCHG
 #define __HAVE_ARCH_CMPXCHG 1
-#endif
 
 #ifdef CONFIG_X86_CMPXCHG64
 #define cmpxchg64(ptr, o, n)						\
@@ -73,59 +71,6 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
 	return prev;
 }
 
-#ifndef CONFIG_X86_CMPXCHG
-/*
- * Building a kernel capable running on 80386. It may be necessary to
- * simulate the cmpxchg on the 80386 CPU. For that purpose we define
- * a function for each of the sizes we support.
- */
-
-extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
-extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
-extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
-
-static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
-					unsigned long new, int size)
-{
-	switch (size) {
-	case 1:
-		return cmpxchg_386_u8(ptr, old, new);
-	case 2:
-		return cmpxchg_386_u16(ptr, old, new);
-	case 4:
-		return cmpxchg_386_u32(ptr, old, new);
-	}
-	return old;
-}
-
-#define cmpxchg(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 3))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg((ptr),		\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr),		\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	__ret;								\
-})
-#define cmpxchg_local(ptr, o, n)					\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 3))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg_local((ptr),	\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr),		\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	__ret;								\
-})
-#endif
-
 #ifndef CONFIG_X86_CMPXCHG64
 /*
  * Building a kernel capable running on 80386 and 80486. It may be necessary
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 8c297aa..ff8dd62 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -312,12 +312,6 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
 #define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
 
-#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
-# define cpu_has_invlpg		1
-#else
-# define cpu_has_invlpg		(boot_cpu_data.x86 > 3)
-#endif
-
 #ifdef CONFIG_X86_64
 
 #undef  cpu_has_vme
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index f373046..be27ba1 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -55,12 +55,6 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
-	/* Real i386 machines can only support FUTEX_OP_SET */
-	if (op != FUTEX_OP_SET && boot_cpu_data.x86 == 3)
-		return -ENOSYS;
-#endif
-
 	pagefault_disable();
 
 	switch (op) {
@@ -118,12 +112,6 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 {
 	int ret = 0;
 
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
-	/* Real i386 machines have no cmpxchg instruction */
-	if (boot_cpu_data.x86 == 3)
-		return -ENOSYS;
-#endif
-
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index c8bed0d..2d89e39 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -124,27 +124,11 @@ static inline int local_add_negative(long i, local_t *l)
  */
 static inline long local_add_return(long i, local_t *l)
 {
-	long __i;
-#ifdef CONFIG_M386
-	unsigned long flags;
-	if (unlikely(boot_cpu_data.x86 <= 3))
-		goto no_xadd;
-#endif
-	/* Modern 486+ processor */
-	__i = i;
+	long __i = i;
 	asm volatile(_ASM_XADD "%0, %1;"
 		     : "+r" (i), "+m" (l->a.counter)
 		     : : "memory");
 	return i + __i;
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
-	local_irq_save(flags);
-	__i = local_read(l);
-	local_set(l, i + __i);
-	local_irq_restore(flags);
-	return i + __i;
-#endif
 }
 
 static inline long local_sub_return(long i, local_t *l)
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 9eae775..e3b7819 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -5,8 +5,6 @@
 
 #ifdef CONFIG_X86_64
 /* X86_64 does not define MODULE_PROC_FAMILY */
-#elif defined CONFIG_M386
-#define MODULE_PROC_FAMILY "386 "
 #elif defined CONFIG_M486
 #define MODULE_PROC_FAMILY "486 "
 #elif defined CONFIG_M586
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 1104afa..0da5200 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -406,7 +406,6 @@ do {									\
 #define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
 #define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
 
-#ifndef CONFIG_M386
 #define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val)
 #define __this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val)
 #define __this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val)
@@ -421,8 +420,6 @@ do {									\
 #define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 #define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
-#endif /* !CONFIG_M386 */
-
 #ifdef CONFIG_X86_CMPXCHG64
 #define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2)		\
 ({									\
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ad1fc85..b0d3e73 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -672,18 +672,29 @@ static inline void sync_core(void)
 {
 	int tmp;
 
-#if defined(CONFIG_M386) || defined(CONFIG_M486)
-	if (boot_cpu_data.x86 < 5)
-		/* There is no speculative execution.
-		 * jmp is a barrier to prefetching. */
-		asm volatile("jmp 1f\n1:\n" ::: "memory");
-	else
+#ifdef CONFIG_M486
+	/*
+	 * Do a CPUID if available, otherwise do a jump.  The jump
+	 * can conveniently enough be the jump around CPUID.
+	 */
+	asm volatile("cmpl %2,%1\n\t"
+		     "jl 1f\n\t"
+		     "cpuid\n"
+		     "1:"
+		     : "=a" (tmp)
+		     : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1)
+		     : "ebx", "ecx", "edx", "memory");
+#else
+	/*
+	 * CPUID is a barrier to speculative execution.
+	 * Prefetched instructions are automatically
+	 * invalidated when modified.
+	 */
+	asm volatile("cpuid"
+		     : "=a" (tmp)
+		     : "0" (1)
+		     : "ebx", "ecx", "edx", "memory");
 #endif
-		/* cpuid is a barrier to speculative execution.
-		 * Prefetched instructions are automatically
-		 * invalidated when modified. */
-		asm volatile("cpuid" : "=a" (tmp) : "0" (1)
-			     : "ebx", "ecx", "edx", "memory");
 }
 
 static inline void __monitor(const void *eax, unsigned long ecx,
diff --git a/arch/x86/include/asm/swab.h b/arch/x86/include/asm/swab.h
index 557cd9f..7f235c7 100644
--- a/arch/x86/include/asm/swab.h
+++ b/arch/x86/include/asm/swab.h
@@ -6,22 +6,7 @@
 
 static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
 {
-#ifdef __i386__
-# ifdef CONFIG_X86_BSWAP
-	asm("bswap %0" : "=r" (val) : "0" (val));
-# else
-	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
-	    "rorl $16,%0\n\t"	/* swap words		*/
-	    "xchgb %b0,%h0"	/* swap higher bytes	*/
-	    : "=q" (val)
-	    : "0" (val));
-# endif
-
-#else /* __i386__ */
-	asm("bswapl %0"
-	    : "=r" (val)
-	    : "0" (val));
-#endif
+	asm("bswapl %0" : "=r" (val) : "0" (val));
 	return val;
 }
 #define __arch_swab32 __arch_swab32
@@ -37,22 +22,12 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
 		__u64 u;
 	} v;
 	v.u = val;
-# ifdef CONFIG_X86_BSWAP
 	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
 	    : "=r" (v.s.a), "=r" (v.s.b)
 	    : "0" (v.s.a), "1" (v.s.b));
-# else
-	v.s.a = __arch_swab32(v.s.a);
-	v.s.b = __arch_swab32(v.s.b);
-	asm("xchgl %0,%1"
-	    : "=r" (v.s.a), "=r" (v.s.b)
-	    : "0" (v.s.a), "1" (v.s.b));
-# endif
 	return v.u;
 #else /* __i386__ */
-	asm("bswapq %0"
-	    : "=r" (val)
-	    : "0" (val));
+	asm("bswapq %0" : "=r" (val) : "0" (val));
 	return val;
 #endif
 }
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 74a4433..0fee48e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -56,10 +56,7 @@ static inline void __flush_tlb_all(void)
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
-	if (cpu_has_invlpg)
 		__flush_tlb_single(addr);
-	else
-		__flush_tlb();
 }
 
 #define TLB_FLUSH_ALL	-1UL
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 7ccf8d1..1709801 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -237,8 +237,6 @@ extern void __put_user_2(void);
 extern void __put_user_4(void);
 extern void __put_user_8(void);
 
-#ifdef CONFIG_X86_WP_WORKS_OK
-
 /**
  * put_user: - Write a simple value into user space.
  * @x:   Value to copy to user space.
@@ -326,29 +324,6 @@ do {									\
 	}								\
 } while (0)
 
-#else
-
-#define __put_user_size(x, ptr, size, retval, errret)			\
-do {									\
-	__typeof__(*(ptr))__pus_tmp = x;				\
-	retval = 0;							\
-									\
-	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0))	\
-		retval = errret;					\
-} while (0)
-
-#define put_user(x, ptr)					\
-({								\
-	int __ret_pu;						\
-	__typeof__(*(ptr))__pus_tmp = x;			\
-	__ret_pu = 0;						\
-	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp,		\
-				       sizeof(*(ptr))) != 0))	\
-		__ret_pu = -EFAULT;				\
-	__ret_pu;						\
-})
-#endif
-
 #ifdef CONFIG_X86_32
 #define __get_user_asm_u64(x, ptr, retval, errret)	(x) = __get_user_bad()
 #define __get_user_asm_ex_u64(x, ptr)			(x) = __get_user_bad()
@@ -543,29 +518,12 @@ struct __large_struct { unsigned long buf[100]; };
 	(x) = (__force __typeof__(*(ptr)))__gue_val;			\
 } while (0)
 
-#ifdef CONFIG_X86_WP_WORKS_OK
-
 #define put_user_try		uaccess_try
 #define put_user_catch(err)	uaccess_catch(err)
 
 #define put_user_ex(x, ptr)						\
 	__put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 
-#else /* !CONFIG_X86_WP_WORKS_OK */
-
-#define put_user_try		do {		\
-	int __uaccess_err = 0;
-
-#define put_user_catch(err)			\
-	(err) |= __uaccess_err;			\
-} while (0)
-
-#define put_user_ex(x, ptr)	do {		\
-	__uaccess_err |= __put_user(x, ptr);	\
-} while (0)
-
-#endif /* CONFIG_X86_WP_WORKS_OK */
-
 extern unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
 extern __must_check long
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1b7d165..a025d8c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -753,9 +753,6 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c,
 
 static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
 {
-	if (!cpu_has_invlpg)
-		return;
-
 	tlb_flushall_shift = 5;
 
 	if (c->x86 <= 0x11)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d0e910d..92dfec9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -107,53 +107,17 @@ static void __init check_hlt(void)
 }
 
 /*
- *	Most 386 processors have a bug where a POPAD can lock the
- *	machine even from user space.
- */
-
-static void __init check_popad(void)
-{
-#ifndef CONFIG_X86_POPAD_OK
-	int res, inp = (int) &res;
-
-	pr_info("Checking for popad bug... ");
-	__asm__ __volatile__(
-	  "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx "
-	  : "=&a" (res)
-	  : "d" (inp)
-	  : "ecx", "edi");
-	/*
-	 * If this fails, it means that any user program may lock the
-	 * CPU hard. Too bad.
-	 */
-	if (res != 12345678)
-		pr_cont("Buggy\n");
-	else
-		pr_cont("OK\n");
-#endif
-}
-
-/*
  * Check whether we are able to run this kernel safely on SMP.
  *
- * - In order to run on a i386, we need to be compiled for i386
- *   (for due to lack of "invlpg" and working WP on a i386)
+ * - i386 is no longer supported.
  * - In order to run on anything without a TSC, we need to be
  *   compiled for a i486.
  */
 
 static void __init check_config(void)
 {
-/*
- * We'd better not be a i386 if we're configured to use some
- * i486+ only features! (WP works in supervisor mode and the
- * new "invlpg" and "bswap" instructions)
- */
-#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) || \
-	defined(CONFIG_X86_BSWAP)
-	if (boot_cpu_data.x86 == 3)
+	if (boot_cpu_data.x86 < 4)
 		panic("Kernel requires i486+ for 'invlpg' and other features");
-#endif
 }
 
 
@@ -166,7 +130,6 @@ void __init check_bugs(void)
 #endif
 	check_config();
 	check_hlt();
-	check_popad();
 	init_utsname()->machine[1] =
 		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 198e019..fcaabd0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -612,10 +612,6 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc)
 
 static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
 {
-	if (!cpu_has_invlpg) {
-		tlb_flushall_shift = -1;
-		return;
-	}
 	switch ((c->x86 << 8) + c->x86_model) {
 	case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
 	case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index b00f678..96b2c66 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -32,7 +32,6 @@ ifeq ($(CONFIG_X86_32),y)
         lib-y += checksum_32.o
         lib-y += strstr_32.o
         lib-y += string_32.o
-        lib-y += cmpxchg.o
 ifneq ($(CONFIG_X86_CMPXCHG64),y)
         lib-y += cmpxchg8b_emu.o atomic64_386_32.o
 endif
diff --git a/arch/x86/lib/cmpxchg.c b/arch/x86/lib/cmpxchg.c
deleted file mode 100644
index 5d619f6..0000000
--- a/arch/x86/lib/cmpxchg.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * cmpxchg*() fallbacks for CPU not supporting these instructions
- */
-
-#include <linux/kernel.h>
-#include <linux/smp.h>
-#include <linux/module.h>
-
-#ifndef CONFIG_X86_CMPXCHG
-unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
-{
-	u8 prev;
-	unsigned long flags;
-
-	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
-	local_irq_save(flags);
-	prev = *(u8 *)ptr;
-	if (prev == old)
-		*(u8 *)ptr = new;
-	local_irq_restore(flags);
-	return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u8);
-
-unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
-{
-	u16 prev;
-	unsigned long flags;
-
-	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
-	local_irq_save(flags);
-	prev = *(u16 *)ptr;
-	if (prev == old)
-		*(u16 *)ptr = new;
-	local_irq_restore(flags);
-	return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u16);
-
-unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
-{
-	u32 prev;
-	unsigned long flags;
-
-	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
-	local_irq_save(flags);
-	prev = *(u32 *)ptr;
-	if (prev == old)
-		*(u32 *)ptr = new;
-	local_irq_restore(flags);
-	return prev;
-}
-EXPORT_SYMBOL(cmpxchg_386_u32);
-#endif
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 98f6d6b6..f0312d7 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,63 +570,6 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-#ifndef CONFIG_X86_WP_WORKS_OK
-	if (unlikely(boot_cpu_data.wp_works_ok == 0) &&
-			((unsigned long)to) < TASK_SIZE) {
-		/*
-		 * When we are in an atomic section (see
-		 * mm/filemap.c:file_read_actor), return the full
-		 * length to take the slow path.
-		 */
-		if (in_atomic())
-			return n;
-
-		/*
-		 * CPU does not honor the WP bit when writing
-		 * from supervisory mode, and due to preemption or SMP,
-		 * the page tables can change at any time.
-		 * Do it manually.	Manfred <manfred@colorfullife.com>
-		 */
-		while (n) {
-			unsigned long offset = ((unsigned long)to)%PAGE_SIZE;
-			unsigned long len = PAGE_SIZE - offset;
-			int retval;
-			struct page *pg;
-			void *maddr;
-
-			if (len > n)
-				len = n;
-
-survive:
-			down_read(&current->mm->mmap_sem);
-			retval = get_user_pages(current, current->mm,
-					(unsigned long)to, 1, 1, 0, &pg, NULL);
-
-			if (retval == -ENOMEM && is_global_init(current)) {
-				up_read(&current->mm->mmap_sem);
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
-				goto survive;
-			}
-
-			if (retval != 1) {
-				up_read(&current->mm->mmap_sem);
-				break;
-			}
-
-			maddr = kmap_atomic(pg);
-			memcpy(maddr + offset, from, len);
-			kunmap_atomic(maddr);
-			set_page_dirty_lock(pg);
-			put_page(pg);
-			up_read(&current->mm->mmap_sem);
-
-			from += len;
-			to += len;
-			n -= len;
-		}
-		return n;
-	}
-#endif
 	stac();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 11a5800..745d66b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -715,10 +715,7 @@ static void __init test_wp_bit(void)
 
 	if (!boot_cpu_data.wp_works_ok) {
 		printk(KERN_CONT "No.\n");
-#ifdef CONFIG_X86_WP_WORKS_OK
-		panic(
-  "This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
-#endif
+		panic("Linux doesn't support CPUs with broken WP.");
 	} else {
 		printk(KERN_CONT "Ok.\n");
 	}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 60f926c..13a6b29 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -104,7 +104,7 @@ static void flush_tlb_func(void *info)
 		return;
 
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
-		if (f->flush_end == TLB_FLUSH_ALL || !cpu_has_invlpg)
+		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
 		else if (!f->flush_end)
 			__flush_tlb_single(f->flush_start);
@@ -337,10 +337,8 @@ static const struct file_operations fops_tlbflush = {
 
 static int __cpuinit create_tlb_flushall_shift(void)
 {
-	if (cpu_has_invlpg) {
-		debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
-			arch_debugfs_dir, NULL, &fops_tlbflush);
-	}
+	debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
+			    arch_debugfs_dir, NULL, &fops_tlbflush);
 	return 0;
 }
 late_initcall(create_tlb_flushall_shift);
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 0761175..b0c30da 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -31,7 +31,7 @@ config X86_64
 	select MODULES_USE_ELF_RELA
 
 config RWSEM_XCHGADD_ALGORITHM
-	def_bool X86_XADD && 64BIT
+	def_bool 64BIT
 
 config RWSEM_GENERIC_SPINLOCK
 	def_bool !RWSEM_XCHGADD_ALGORITHM
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index fdce49c..9a6775c 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -7,7 +7,7 @@ config XEN
 	select PARAVIRT
 	select PARAVIRT_CLOCK
 	depends on X86_64 || (X86_32 && X86_PAE && !X86_VISWS)
-	depends on X86_CMPXCHG && X86_TSC
+	depends on X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the

Re: [RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[Linus Torvalds]

On Tue, Dec 11, 2012 at 3:10 AM, Ingo Molnar <mingo@kernel.org> wrote:
>
> This tree removes ancient-386-CPUs support and thus zaps quite a
> bit of complexity:

Btw, I think we should probably at least consider taking this one step
further, and remove the dear old FPU emulation support too. Remove
CONFIG_MATH_EMULATION and all of arch/x86/math-emu, along with a lot
of small special cases.

Or do people still use the 486SX?

Now, the math emulation hasn't been all that fundamentally problematic
(compared to lack of xadd etc), but it does result in some
complexities in exception handling and ptrace (grep for HAVE_HWFP or
"hard_math" or a number of other magic things). None of which have
likely been tested at all in the last ten years, so who knows if it
actually *works* or not.

Maybe somebody could try booting with "no387". Does it actually work?

              Linus

Re: [RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[H. Peter Anvin]

On 12/12/2012 10:04 AM, Linus Torvalds wrote:
> On Tue, Dec 11, 2012 at 3:10 AM, Ingo Molnar <mingo@kernel.org> wrote:
>>
>> This tree removes ancient-386-CPUs support and thus zaps quite a
>> bit of complexity:
>
> Btw, I think we should probably at least consider taking this one step
> further, and remove the dear old FPU emulation support too. Remove
> CONFIG_MATH_EMULATION and all of arch/x86/math-emu, along with a lot
> of small special cases.
>
> Or do people still use the 486SX?
>
> Now, the math emulation hasn't been all that fundamentally problematic
> (compared to lack of xadd etc), but it does result in some
> complexities in exception handling and ptrace (grep for HAVE_HWFP or
> "hard_math" or a number of other magic things). None of which have
> likely been tested at all in the last ten years, so who knows if it
> actually *works* or not.
>
> Maybe somebody could try booting with "no387". Does it actually work?
>

It builds and boots, at least.  I'm currently installing Red Hat 4.1 in 
a VM so I can test to see if it does anything more than that.  It 
doesn't get in the way the same case the old 386 bits does, so I'm more 
reluctant to remove it, but it does touch a lot of paths.

There were a *bunch* of embedded 486 clones made, some still in 
production as far as I know, and I wouldn't be surprised if some of them 
lacked FPU.  I guess we'll see.

	-hpa

-- 
H. Peter Anvin, Intel Open Source Technology Center
I work for Intel.  I don't speak on their behalf.

Re: [RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[H. Peter Anvin]

On 12/12/2012 11:00 AM, H. Peter Anvin wrote:
>
> It builds and boots, at least.  I'm currently installing Red Hat 4.1 in
> a VM so I can test to see if it does anything more than that.  It
> doesn't get in the way the same case the old 386 bits does, so I'm more
> reluctant to remove it, but it does touch a lot of paths.
>

Well... it turns out to boot and run Red Hat 4.1 just fine (using qemu 
-cpu 486 and the no387 option) once I changed /dev/hda1 to /dev/sda1.

I'm actually kind of impressed.

	-hpa

-- 
H. Peter Anvin, Intel Open Source Technology Center
I work for Intel.  I don't speak on their behalf.

Re: [RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[Bernd Petrovitsch]

On Mit, 2012-12-12 at 11:00 -0800, H. Peter Anvin wrote:
[...]
> There were a *bunch* of embedded 486 clones made, some still in 
> production as far as I know, and I wouldn't be surprised if some of them 
> lacked FPU.  I guess we'll see.

And there is an x86 emulator written in Javascript at
http://www.bellard.org/jslinux/.

http://www.bellard.org/jslinux/tech.html says that it (also) lacks an
FPU.

	Bernd
-- 
Bernd Petrovitsch                  Email : bernd@petrovitsch.priv.at
                     LUGA : http://www.luga.at

Re: [RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[Thorsten Glaser]

H. Peter Anvin <hpa <at> zytor.com> writes:

> On 12/12/2012 10:04 AM, Linus Torvalds wrote:

> > Or do people still use the 486SX?

> There were a *bunch* of embedded 486 clones made, some still in 
> production as far as I know, and I wouldn't be surprised if some of them 
> lacked FPU.  I guess we'll see.

This one is fairly recent: Bifferboard ⇒ http://bifferos.co.uk/

bye,
//mirabilos

Re: [RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[Linus Torvalds]

On Wed, Dec 12, 2012 at 2:24 PM, H. Peter Anvin <hpa@zytor.com> wrote:
>
> Well... it turns out to boot and run Red Hat 4.1 just fine (using qemu -cpu
> 486 and the no387 option) once I changed /dev/hda1 to /dev/sda1.

Ok. It sounds like the code actually works despite lack of testing,
and it clearly hasn't been the same kind of maintenance pain and
problem that the lack of cmpxchg and friends, so let's leave it alone.
Thanks,

                Linus

Re: [RFC GIT PULL] "Nuke 386-DX/SX support" changes for v3.8

[Florian Fainelli]

Le 12/12/12 19:04, Linus Torvalds a écrit :
> On Tue, Dec 11, 2012 at 3:10 AM, Ingo Molnar <mingo@kernel.org> wrote:
>>
>> This tree removes ancient-386-CPUs support and thus zaps quite a
>> bit of complexity:
>
> Btw, I think we should probably at least consider taking this one step
> further, and remove the dear old FPU emulation support too. Remove
> CONFIG_MATH_EMULATION and all of arch/x86/math-emu, along with a lot
> of small special cases.
>
> Or do people still use the 486SX?

Yes, the RDC-R321x SoC which is supported by mainline actually needs 
Math emulation to properly work.

>
> Now, the math emulation hasn't been all that fundamentally problematic
> (compared to lack of xadd etc), but it does result in some
> complexities in exception handling and ptrace (grep for HAVE_HWFP or
> "hard_math" or a number of other magic things). None of which have
> likely been tested at all in the last ten years, so who knows if it
> actually *works* or not.
>
> Maybe somebody could try booting with "no387". Does it actually work?

Ok, I could try that.
--
Florian