Merge bk://kernel.bkbits.net/davem/net-2.5

into home.transmeta.com:/home/torvalds/v2.5/linux

9 files changed, 170 insertions, 43 deletions

diff --git a/include/asm-i386/cpufeature.h b/include/asm-i386/cpufeature.h
index 46a85b395db8..040e1f66ea48 100644
--- a/include/asm-i386/cpufeature.h
+++ b/include/asm-i386/cpufeature.h
@@ -63,6 +63,11 @@
 #define X86_FEATURE_K6_MTRR	(3*32+ 1) /* AMD K6 nonstandard MTRRs */
 #define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
 #define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
+/* cpu types for specific tunings: */
+#define X86_FEATURE_K8		(3*32+ 4) /* Opteron, Athlon64 */
+#define X86_FEATURE_K7		(3*32+ 5) /* Athlon */
+#define X86_FEATURE_P3		(3*32+ 6) /* P3 */
+#define X86_FEATURE_P4		(3*32+ 7) /* P4 */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 
diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h
index bc47e152108d..d69cc46d5866 100644
--- a/include/asm-i386/processor.h
+++ b/include/asm-i386/processor.h
@@ -15,6 +15,7 @@
 #include <asm/sigcontext.h>
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
+#include <asm/system.h>
 #include <linux/cache.h>
 #include <linux/config.h>
 #include <linux/threads.h>
@@ -495,32 +496,93 @@ static inline void rep_nop(void)
 
 #define cpu_relax()	rep_nop()
 
-/* Prefetch instructions for Pentium III and AMD Athlon */
-#ifdef 	CONFIG_X86_PREFETCH
+/* generic versions from gas */
+#define GENERIC_NOP1	".byte 0x90\n"
+#define GENERIC_NOP2    	".byte 0x89,0xf6\n"
+#define GENERIC_NOP3        ".byte 0x8d,0x76,0x00\n"
+#define GENERIC_NOP4        ".byte 0x8d,0x74,0x26,0x00\n"
+#define GENERIC_NOP5        GENERIC_NOP1 GENERIC_NOP4
+#define GENERIC_NOP6	".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP7	".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP8	GENERIC_NOP1 GENERIC_NOP7
+
+/* Opteron nops */
+#define K8_NOP1 GENERIC_NOP1
+#define K8_NOP2	".byte 0x66,0x90\n" 
+#define K8_NOP3	".byte 0x66,0x66,0x90\n" 
+#define K8_NOP4	".byte 0x66,0x66,0x66,0x90\n" 
+#define K8_NOP5	K8_NOP3 K8_NOP2 
+#define K8_NOP6	K8_NOP3 K8_NOP3
+#define K8_NOP7	K8_NOP4 K8_NOP3
+#define K8_NOP8	K8_NOP4 K8_NOP4
+
+/* K7 nops */
+/* uses eax dependencies (arbitary choice) */
+#define K7_NOP1  GENERIC_NOP1
+#define K7_NOP2	".byte 0x8b,0xc0\n" 
+#define K7_NOP3	".byte 0x8d,0x04,0x20\n"
+#define K7_NOP4	".byte 0x8d,0x44,0x20,0x00\n"
+#define K7_NOP5	K7_NOP4 ASM_NOP1
+#define K7_NOP6	".byte 0x8d,0x80,0,0,0,0\n"
+#define K7_NOP7        ".byte 0x8D,0x04,0x05,0,0,0,0\n"
+#define K7_NOP8        K7_NOP7 ASM_NOP1
+
+#ifdef CONFIG_MK8
+#define ASM_NOP1 K8_NOP1
+#define ASM_NOP2 K8_NOP2
+#define ASM_NOP3 K8_NOP3
+#define ASM_NOP4 K8_NOP4
+#define ASM_NOP5 K8_NOP5
+#define ASM_NOP6 K8_NOP6
+#define ASM_NOP7 K8_NOP7
+#define ASM_NOP8 K8_NOP8
+#elif CONFIG_MK7
+#define ASM_NOP1 K7_NOP1
+#define ASM_NOP2 K7_NOP2
+#define ASM_NOP3 K7_NOP3
+#define ASM_NOP4 K7_NOP4
+#define ASM_NOP5 K7_NOP5
+#define ASM_NOP6 K7_NOP6
+#define ASM_NOP7 K7_NOP7
+#define ASM_NOP8 K7_NOP8
+#else
+#define ASM_NOP1 GENERIC_NOP1
+#define ASM_NOP2 GENERIC_NOP2
+#define ASM_NOP3 GENERIC_NOP3
+#define ASM_NOP4 GENERIC_NOP4
+#define ASM_NOP5 GENERIC_NOP5
+#define ASM_NOP6 GENERIC_NOP6
+#define ASM_NOP7 GENERIC_NOP7
+#define ASM_NOP8 GENERIC_NOP8
+#endif
 
+#define ASM_NOP_MAX 8
+
+/* Prefetch instructions for Pentium III and AMD Athlon */
+/* It's not worth to care about 3dnow! prefetches for the K6
+   because they are microcoded there and very slow. */
 #define ARCH_HAS_PREFETCH
 extern inline void prefetch(const void *x)
 {
-	__asm__ __volatile__ ("prefetchnta (%0)" : : "r"(x));
+	alternative_input(ASM_NOP3,
+			  "prefetchnta (%1)",
+			  X86_FEATURE_XMM,
+			  "r" (x));
 }
 
-#elif defined CONFIG_X86_USE_3DNOW
-
 #define ARCH_HAS_PREFETCH
 #define ARCH_HAS_PREFETCHW
 #define ARCH_HAS_SPINLOCK_PREFETCH
 
-extern inline void prefetch(const void *x)
-{
-	 __asm__ __volatile__ ("prefetch (%0)" : : "r"(x));
-}
-
+/* 3dnow! prefetch to get an exclusive cache line. Useful for 
+   spinlocks to avoid one state transition in the cache coherency protocol. */
 extern inline void prefetchw(const void *x)
 {
-	 __asm__ __volatile__ ("prefetchw (%0)" : : "r"(x));
+	alternative_input(ASM_NOP3,
+			  "prefetchw (%1)",
+			  X86_FEATURE_3DNOW,
+			  "r" (x));
 }
 #define spin_lock_prefetch(x)	prefetchw(x)
 
-#endif
-
 #endif /* __ASM_I386_PROCESSOR_H */
diff --git a/include/asm-i386/system.h b/include/asm-i386/system.h
index 5831f6d34ad7..71b9dd77ed04 100644
--- a/include/asm-i386/system.h
+++ b/include/asm-i386/system.h
@@ -277,13 +277,16 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 /* Compiling for a 386 proper.	Is it worth implementing via cli/sti?  */
 #endif
 
+#ifdef __KERNEL__
 struct alt_instr { 
-	u8 *instr; 		/* original instruction */
-	u8  cpuid;		/* cpuid bit set for replacement */
-	u8  instrlen;		/* length of original instruction */
-	u8  replacementlen; 	/* length of new instruction, <= instrlen */ 
-	u8  replacement[0];   	/* new instruction */
+	__u8 *instr; 		/* original instruction */
+	__u8 *replacement;
+	__u8  cpuid;		/* cpuid bit set for replacement */
+	__u8  instrlen;		/* length of original instruction */
+	__u8  replacementlen; 	/* length of new instruction, <= instrlen */ 
+	__u8  pad;
 }; 
+#endif
 
 /* 
  * Alternative instructions for different CPU types or capabilities.
@@ -302,13 +305,40 @@ struct alt_instr {
 		      ".section .altinstructions,\"a\"\n"     	     \
 		      "  .align 4\n"				       \
 		      "  .long 661b\n"            /* label */          \
+		      "  .long 663f\n"		  /* new instruction */ 	\
 		      "  .byte %c0\n"             /* feature bit */    \
 		      "  .byte 662b-661b\n"       /* sourcelen */      \
 		      "  .byte 664f-663f\n"       /* replacementlen */ \
+		      ".previous\n"						\
+		      ".section .altinstr_replacement,\"ax\"\n"			\
 		      "663:\n\t" newinstr "\n664:\n"   /* replacement */    \
 		      ".previous" :: "i" (feature) : "memory")  
 
 /*
+ * Alternative inline assembly with input.
+ * 
+ * Pecularities:
+ * No memory clobber here. 
+ * Argument numbers start with 1.
+ * Best is to use constraints that are fixed size (like (%1) ... "r")
+ * If you use variable sized constraints like "m" or "g" in the 
+ * replacement maake sure to pad to the worst case length.
+ */
+#define alternative_input(oldinstr, newinstr, feature, input)			\
+	asm volatile ("661:\n\t" oldinstr "\n662:\n"				\
+		      ".section .altinstructions,\"a\"\n"			\
+		      "  .align 4\n"						\
+		      "  .long 661b\n"            /* label */			\
+		      "  .long 663f\n"		  /* new instruction */ 	\
+		      "  .byte %c0\n"             /* feature bit */		\
+		      "  .byte 662b-661b\n"       /* sourcelen */		\
+		      "  .byte 664f-663f\n"       /* replacementlen */ 		\
+		      ".previous\n"						\
+		      ".section .altinstr_replacement,\"ax\"\n"			\
+		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ 	\
+		      ".previous" :: "i" (feature), input)  
+
+/*
  * Force strict CPU ordering.
  * And yes, this is required on UP too when we're talking
  * to devices.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 572b92e6f443..b9b2cf5b69e8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1068,10 +1068,7 @@ extern int chrdev_open(struct inode *, struct file *);
 /* fs/block_dev.c */
 #define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
 extern const char *__bdevname(dev_t, char *buffer);
-extern inline const char *bdevname(struct block_device *bdev, char *buffer)
-{
-	return __bdevname(bdev->bd_dev, buffer);
-}
+extern const char *bdevname(struct block_device *bdev, char *buffer);
 extern struct block_device *lookup_bdev(const char *);
 extern struct block_device *open_bdev_excl(const char *, int, int, void *);
 extern void close_bdev_excl(struct block_device *, int);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index ade6d9e97475..be82baa340fa 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -31,6 +31,7 @@
 #define __GFP_REPEAT	0x400	/* Retry the allocation.  Might fail */
 #define __GFP_NOFAIL	0x800	/* Retry for ever.  Cannot fail */
 #define __GFP_NORETRY	0x1000	/* Do not retry.  Might fail */
+#define __GFP_NO_GROW	0x2000	/* Slab internal usage */
 
 #define GFP_ATOMIC	(__GFP_HIGH)
 #define GFP_NOIO	(__GFP_WAIT)
diff --git a/include/linux/module.h b/include/linux/module.h
index 657802c8af75..4ddc5edcd22f 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -20,10 +20,7 @@
 #include <asm/module.h>
 
 /* Not Yet Implemented */
-#define MODULE_AUTHOR(name)
-#define MODULE_DESCRIPTION(desc)
 #define MODULE_SUPPORTED_DEVICE(name)
-#define MODULE_PARM_DESC(var,desc)
 #define print_modules()
 
 /* v850 toolchain uses a `_' prefix for all user symbols */
@@ -58,12 +55,11 @@ search_extable(const struct exception_table_entry *first,
 	       unsigned long value);
 
 #ifdef MODULE
-#define ___module_cat(a,b) a ## b
+#define ___module_cat(a,b) __mod_ ## a ## b
 #define __module_cat(a,b) ___module_cat(a,b)
-/* For userspace: you can also call me... */
-#define MODULE_ALIAS(alias)					\
-	static const char __module_cat(__alias_,__LINE__)[]	\
-		__attribute__((section(".modinfo"),unused)) = "alias=" alias
+#define __MODULE_INFO(tag, name, info)					  \
+static const char __module_cat(name,__LINE__)[]				  \
+  __attribute__((section(".modinfo"),unused)) = __stringify(tag) "=" info
 
 #define MODULE_GENERIC_TABLE(gtype,name)			\
 extern const struct gtype##_id __mod_##gtype##_table		\
@@ -71,6 +67,19 @@ extern const struct gtype##_id __mod_##gtype##_table		\
 
 #define THIS_MODULE (&__this_module)
 
+#else  /* !MODULE */
+
+#define MODULE_GENERIC_TABLE(gtype,name)
+#define __MODULE_INFO(tag, name, info)
+#define THIS_MODULE ((struct module *)0)
+#endif
+
+/* Generic info of form tag = "info" */
+#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
+
+/* For userspace: you can also call me... */
+#define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias)
+
 /*
  * The following license idents are currently accepted as indicating free
  * software modules
@@ -97,17 +106,18 @@ extern const struct gtype##_id __mod_##gtype##_table		\
  * 2.	So the community can ignore bug reports including proprietary modules
  * 3.	So vendors can do likewise based on their own policies
  */
-#define MODULE_LICENSE(license)					\
-	static const char __module_license[]			\
-		__attribute__((section(".init.license"), unused)) = license
+#define MODULE_LICENSE(_license) MODULE_INFO(license, _license)
 
-#else  /* !MODULE */
+/* Author, ideally of form NAME <EMAIL>[, NAME <EMAIL>]*[ and NAME <EMAIL>] */
+#define MODULE_AUTHOR(_author) MODULE_INFO(author, _author)
+  
+/* What your module does. */
+#define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description)
 
-#define MODULE_ALIAS(alias)
-#define MODULE_GENERIC_TABLE(gtype,name)
-#define THIS_MODULE ((struct module *)0)
-#define MODULE_LICENSE(license)
-#endif
+/* One for each parameter, describing how to use it.  Some files do
+   multiple of these per line, so can't just use MODULE_INFO. */
+#define MODULE_PARM_DESC(_parm, desc) \
+	__MODULE_INFO(parm, _parm, #_parm ":" desc)
 
 #define MODULE_DEVICE_TABLE(type,name)		\
   MODULE_GENERIC_TABLE(type##_device,name)
@@ -255,6 +265,7 @@ struct module *module_text_address(unsigned long addr);
 
 #ifdef CONFIG_MODULE_UNLOAD
 
+unsigned int module_refcount(struct module *mod);
 void __symbol_put(const char *symbol);
 #define symbol_put(x) __symbol_put(MODULE_SYMBOL_PREFIX #x)
 void symbol_put_addr(void *addr);
@@ -265,6 +276,17 @@ void symbol_put_addr(void *addr);
 #define local_dec(x) atomic_dec(x)
 #endif
 
+/* Sometimes we know we already have a refcount, and it's easier not
+   to handle the error case (which only happens with rmmod --wait). */
+static inline void __module_get(struct module *module)
+{
+	if (module) {
+		BUG_ON(module_refcount(module) == 0);
+		local_inc(&module->ref[get_cpu()].count);
+		put_cpu();
+	}
+}
+
 static inline int try_module_get(struct module *module)
 {
 	int ret = 1;
@@ -300,6 +322,9 @@ static inline int try_module_get(struct module *module)
 static inline void module_put(struct module *module)
 {
 }
+static inline void __module_get(struct module *module)
+{
+}
 #define symbol_put(x) do { } while(0)
 #define symbol_put_addr(p) do { } while(0)
 
@@ -357,6 +382,10 @@ static inline struct module *module_text_address(unsigned long addr)
 #define symbol_put(x) do { } while(0)
 #define symbol_put_addr(x) do { } while(0)
 
+static inline void __module_get(struct module *module)
+{
+}
+
 static inline int try_module_get(struct module *module)
 {
 	return 1;
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 69d0a66b662e..53c52176c391 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -7,7 +7,7 @@
 #include <linux/config.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/preempt.h>
+#include <linux/threads.h>
 
 #ifdef CONFIG_SMP
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 603748b9b349..49374df2d450 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -22,8 +22,11 @@ typedef struct kmem_cache_s kmem_cache_t;
 #define	SLAB_KERNEL		GFP_KERNEL
 #define	SLAB_DMA		GFP_DMA
 
-#define SLAB_LEVEL_MASK		(__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|__GFP_COLD|__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|__GFP_NORETRY)
-#define	SLAB_NO_GROW		0x00001000UL	/* don't grow a cache */
+#define SLAB_LEVEL_MASK		(__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\
+				__GFP_COLD|__GFP_NOWARN|__GFP_REPEAT|\
+				__GFP_NOFAIL|__GFP_NORETRY)
+
+#define	SLAB_NO_GROW		__GFP_NO_GROW	/* don't grow a cache */
 
 /* flags to pass to kmem_cache_create().
  * The first 3 are only valid when the allocator as been build
diff --git a/include/net/irda/irport.h b/include/net/irda/irport.h
index e5877f66fab8..79b4d8904346 100644
--- a/include/net/irda/irport.h
+++ b/include/net/irda/irport.h
@@ -73,7 +73,7 @@ struct irport_cb {
 	/* For piggyback drivers */
 	void *priv;                
 	void (*change_speed)(void *priv, __u32 speed);
-	void (*interrupt)(int irq, void *dev_id, struct pt_regs *regs);
+	int (*interrupt)(int irq, void *dev_id, struct pt_regs *regs);
 };
 
 struct irport_cb *irport_open(int i, unsigned int iobase, unsigned int irq);