[PATCH] i386: inline assembler: cleanup and encapsulate descriptor and task register management

i386 inline assembler cleanup.

This change encapsulates descriptor and task register management.  Also,
it is possible to improve assembler generation in two cases; savesegment
may store the value in a register instead of a memory location, which
allows GCC to optimize stack variables into registers, and MOV MEM, SEG
is always a 16-bit write to memory, making the casting in math-emu
unnecessary.

Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

11 files changed, 43 insertions, 40 deletions

diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 361f2e7..46ce9b2 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -613,8 +613,8 @@ void __devinit cpu_init(void)
 	memcpy(thread->tls_array, &per_cpu(cpu_gdt_table, cpu),
 		GDT_ENTRY_TLS_ENTRIES * 8);
 
-	__asm__ __volatile__("lgdt %0" : : "m" (cpu_gdt_descr[cpu]));
-	__asm__ __volatile__("lidt %0" : : "m" (idt_descr));
+	load_gdt(&cpu_gdt_descr[cpu]);
+	load_idt(&idt_descr);
 
 	/*
 	 * Delete NT
diff --git a/arch/i386/kernel/doublefault.c b/arch/i386/kernel/doublefault.c
index 789af3e..5edb1d3 100644
--- a/arch/i386/kernel/doublefault.c
+++ b/arch/i386/kernel/doublefault.c
@@ -20,7 +20,7 @@ static void doublefault_fn(void)
 	struct Xgt_desc_struct gdt_desc = {0, 0};
 	unsigned long gdt, tss;
 
-	__asm__ __volatile__("sgdt %0": "=m" (gdt_desc): :"memory");
+	store_gdt(&gdt_desc);
 	gdt = gdt_desc.address;
 
 	printk("double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size);
diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c
index 921fdb1..ecad519 100644
--- a/arch/i386/kernel/efi.c
+++ b/arch/i386/kernel/efi.c
@@ -104,8 +104,7 @@ static void efi_call_phys_prelog(void)
 	local_flush_tlb();
 
 	cpu_gdt_descr[0].address = __pa(cpu_gdt_descr[0].address);
-	__asm__ __volatile__("lgdt %0":"=m"
-			    (*(struct Xgt_desc_struct *) __pa(&cpu_gdt_descr[0])));
+	load_gdt((struct Xgt_desc_struct *) __pa(&cpu_gdt_descr[0]));
 }
 
 static void efi_call_phys_epilog(void)
@@ -114,7 +113,7 @@ static void efi_call_phys_epilog(void)
 
 	cpu_gdt_descr[0].address =
 		(unsigned long) __va(cpu_gdt_descr[0].address);
-	__asm__ __volatile__("lgdt %0":"=m"(cpu_gdt_descr));
+	load_gdt(&cpu_gdt_descr[0]);
 	cr4 = read_cr4();
 
 	if (cr4 & X86_CR4_PSE) {
diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c
index c71fef3..1cbb9c0 100644
--- a/arch/i386/kernel/reboot.c
+++ b/arch/i386/kernel/reboot.c
@@ -13,6 +13,7 @@
 #include <linux/dmi.h>
 #include <asm/uaccess.h>
 #include <asm/apic.h>
+#include <asm/desc.h>
 #include "mach_reboot.h"
 #include <linux/reboot_fixups.h>
 
@@ -242,13 +243,13 @@ void machine_real_restart(unsigned char *code, int length)
 
 	/* Set up the IDT for real mode. */
 
-	__asm__ __volatile__ ("lidt %0" : : "m" (real_mode_idt));
+	load_idt(&real_mode_idt);
 
 	/* Set up a GDT from which we can load segment descriptors for real
 	   mode.  The GDT is not used in real mode; it is just needed here to
 	   prepare the descriptors. */
 
-	__asm__ __volatile__ ("lgdt %0" : : "m" (real_mode_gdt));
+	load_gdt(&real_mode_gdt);
 
 	/* Load the data segment registers, and thus the descriptors ready for
 	   real mode.  The base address of each segment is 0x100, 16 times the
@@ -316,7 +317,7 @@ void machine_emergency_restart(void)
 	if (!reboot_thru_bios) {
 		if (efi_enabled) {
 			efi.reset_system(EFI_RESET_COLD, EFI_SUCCESS, 0, NULL);
-			__asm__ __volatile__("lidt %0": :"m" (no_idt));
+			load_idt(&no_idt);
 			__asm__ __volatile__("int3");
 		}
 		/* rebooting needs to touch the page at absolute addr 0 */
@@ -325,7 +326,7 @@ void machine_emergency_restart(void)
 			mach_reboot_fixups(); /* for board specific fixups */
 			mach_reboot();
 			/* That didn't work - force a triple fault.. */
-			__asm__ __volatile__("lidt %0": :"m" (no_idt));
+			load_idt(&no_idt);
 			__asm__ __volatile__("int3");
 		}
 	}
diff --git a/arch/i386/kernel/signal.c b/arch/i386/kernel/signal.c
index 140e340..7bcda6d 100644
--- a/arch/i386/kernel/signal.c
+++ b/arch/i386/kernel/signal.c
@@ -278,9 +278,9 @@ setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
 	int tmp, err = 0;
 
 	tmp = 0;
-	__asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp));
+	savesegment(gs, tmp);
 	err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
-	__asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp));
+	savesegment(fs, tmp);
 	err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
 
 	err |= __put_user(regs->xes, (unsigned int __user *)&sc->es);
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index cd2d5d5..1144df0 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -1008,7 +1008,7 @@ void __init trap_init_f00f_bug(void)
 	 * it uses the read-only mapped virtual address.
 	 */
 	idt_descr.address = fix_to_virt(FIX_F00F_IDT);
-	__asm__ __volatile__("lidt %0" : : "m" (idt_descr));
+	load_idt(&idt_descr);
 }
 #endif
 
diff --git a/arch/i386/kernel/vm86.c b/arch/i386/kernel/vm86.c
index 2daa06f..16b4850 100644
--- a/arch/i386/kernel/vm86.c
+++ b/arch/i386/kernel/vm86.c
@@ -294,8 +294,8 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
  */
 	info->regs32->eax = 0;
 	tsk->thread.saved_esp0 = tsk->thread.esp0;
-	asm volatile("mov %%fs,%0":"=m" (tsk->thread.saved_fs));
-	asm volatile("mov %%gs,%0":"=m" (tsk->thread.saved_gs));
+	savesegment(fs, tsk->thread.saved_fs);
+	savesegment(gs, tsk->thread.saved_gs);
 
 	tss = &per_cpu(init_tss, get_cpu());
 	tsk->thread.esp0 = (unsigned long) &info->VM86_TSS_ESP0;
diff --git a/arch/i386/math-emu/get_address.c b/arch/i386/math-emu/get_address.c
index 9117573..9819b70 100644
--- a/arch/i386/math-emu/get_address.c
+++ b/arch/i386/math-emu/get_address.c
@@ -155,7 +155,6 @@ static long pm_address(u_char FPU_modrm, u_char segment,
 { 
   struct desc_struct descriptor;
   unsigned long base_address, limit, address, seg_top;
-  unsigned short selector;
 
   segment--;
 
@@ -173,17 +172,11 @@ static long pm_address(u_char FPU_modrm, u_char segment,
       /* fs and gs aren't used by the kernel, so they still have their
 	 user-space values. */
     case PREFIX_FS_-1:
-      /* The cast is needed here to get gcc 2.8.0 to use a 16 bit register
-	 in the assembler statement. */
-
-      __asm__("mov %%fs,%0":"=r" (selector));
-      addr->selector = selector;
+      /* N.B. - movl %seg, mem is a 2 byte write regardless of prefix */
+      savesegment(fs, addr->selector);
       break;
     case PREFIX_GS_-1:
-      /* The cast is needed here to get gcc 2.8.0 to use a 16 bit register
-	 in the assembler statement. */
-      __asm__("mov %%gs,%0":"=r" (selector));
-      addr->selector = selector;
+      savesegment(gs, addr->selector);
       break;
     default:
       addr->selector = PM_REG_(segment);
diff --git a/arch/i386/power/cpu.c b/arch/i386/power/cpu.c
index 4e19c43..c7a6436 100644
--- a/arch/i386/power/cpu.c
+++ b/arch/i386/power/cpu.c
@@ -42,17 +42,17 @@ void __save_processor_state(struct saved_context *ctxt)
 	/*
 	 * descriptor tables
 	 */
-	asm volatile ("sgdt %0" : "=m" (ctxt->gdt_limit));
-	asm volatile ("sidt %0" : "=m" (ctxt->idt_limit));
-	asm volatile ("str %0"  : "=m" (ctxt->tr));
+ 	store_gdt(&ctxt->gdt_limit);
+ 	store_idt(&ctxt->idt_limit);
+ 	store_tr(ctxt->tr);
 
 	/*
 	 * segment registers
 	 */
-	asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
-	asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
-	asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
-	asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
+ 	savesegment(es, ctxt->es);
+ 	savesegment(fs, ctxt->fs);
+ 	savesegment(gs, ctxt->gs);
+ 	savesegment(ss, ctxt->ss);
 
 	/*
 	 * control registers 
@@ -118,16 +118,16 @@ void __restore_processor_state(struct saved_context *ctxt)
 	 * now restore the descriptor tables to their proper values
 	 * ltr is done i fix_processor_context().
 	 */
-	asm volatile ("lgdt %0" :: "m" (ctxt->gdt_limit));
-	asm volatile ("lidt %0" :: "m" (ctxt->idt_limit));
+ 	load_gdt(&ctxt->gdt_limit);
+ 	load_idt(&ctxt->idt_limit);
 
 	/*
 	 * segment registers
 	 */
-	asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
-	asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
-	asm volatile ("movw %0, %%gs" :: "r" (ctxt->gs));
-	asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
+ 	loadsegment(es, ctxt->es);
+ 	loadsegment(fs, ctxt->fs);
+ 	loadsegment(gs, ctxt->gs);
+ 	loadsegment(ss, ctxt->ss);
 
 	/*
 	 * sysenter MSRs
diff --git a/include/asm-i386/desc.h b/include/asm-i386/desc.h
index 11e6781..9a0b85a 100644
--- a/include/asm-i386/desc.h
+++ b/include/asm-i386/desc.h
@@ -30,6 +30,16 @@ extern struct Xgt_desc_struct idt_descr, cpu_gdt_descr[NR_CPUS];
 #define load_TR_desc() __asm__ __volatile__("ltr %%ax"::"a" (GDT_ENTRY_TSS*8))
 #define load_LDT_desc() __asm__ __volatile__("lldt %%ax"::"a" (GDT_ENTRY_LDT*8))
 
+#define load_gdt(dtr) __asm__ __volatile("lgdt %0"::"m" (*dtr))
+#define load_idt(dtr) __asm__ __volatile("lidt %0"::"m" (*dtr))
+#define load_tr(tr) __asm__ __volatile("ltr %0"::"mr" (tr))
+#define load_ldt(ldt) __asm__ __volatile("lldt %0"::"mr" (ldt))
+
+#define store_gdt(dtr) __asm__ ("sgdt %0":"=m" (*dtr))
+#define store_idt(dtr) __asm__ ("sidt %0":"=m" (*dtr))
+#define store_tr(tr) __asm__ ("str %0":"=mr" (tr))
+#define store_ldt(ldt) __asm__ ("sldt %0":"=mr" (ldt))
+
 /*
  * This is the ldt that every process will get unless we need
  * something other than this.
diff --git a/include/asm-i386/system.h b/include/asm-i386/system.h
index 8048a5e..37fd2f8 100644
--- a/include/asm-i386/system.h
+++ b/include/asm-i386/system.h
@@ -93,13 +93,13 @@ static inline unsigned long _get_base(char * addr)
 		".align 4\n\t"			\
 		".long 1b,3b\n"			\
 		".previous"			\
-		: :"m" (value))
+		: :"rm" (value))
 
 /*
  * Save a segment register away
  */
 #define savesegment(seg, value) \
-	asm volatile("mov %%" #seg ",%0":"=m" (value))
+	asm volatile("mov %%" #seg ",%0":"=rm" (value))
 
 /*
  * Clear and set 'TS' bit respectively