boot with small GDT

Switch to larger operating GDT after moving to protected mode

This is necessary to boot on certain subarchs (voyager)

arch/i386/boot/compressed/head.S

@@ -31,7 +31,7 @@
 startup_32:
 	cld
 	cli
-	movl $(__KERNEL_DS),%eax
+	movl $(__BOOT_DS),%eax
 	movl %eax,%ds
 	movl %eax,%es
 	movl %eax,%fs
@@ -74,7 +74,7 @@ startup_32:
 	popl %esi	# discard address
 	popl %esi	# real mode pointer
 	xorl %ebx,%ebx
-	ljmp $(__KERNEL_CS), $0x100000
+	ljmp $(__BOOT_CS), $0x100000
 
 /*
  * We come here, if we were loaded high.
@@ -101,7 +101,7 @@ startup_32:
 	popl %eax	# hcount
 	movl $0x100000,%edi
 	cli		# make sure we don't get interrupted
-	ljmp $(__KERNEL_CS), $0x1000 # and jump to the move routine
+	ljmp $(__BOOT_CS), $0x1000 # and jump to the move routine
 
 /*
  * Routine (template) for moving the decompressed kernel in place,
@@ -124,5 +124,5 @@ move_routine_start:
 	movsl
 	movl %ebx,%esi	# Restore setup pointer
 	xorl %ebx,%ebx
-	ljmp $(__KERNEL_CS), $0x100000
+	ljmp $(__BOOT_CS), $0x100000
 move_routine_end:

arch/i386/boot/compressed/misc.c

@@ -299,7 +299,7 @@ long user_stack [STACK_SIZE];
 struct {
 	long * a;
 	short b;
-	} stack_start = { & user_stack [STACK_SIZE] , __KERNEL_DS };
+	} stack_start = { & user_stack [STACK_SIZE] , __BOOT_DS };
 
 static void setup_normal_output_buffer(void)
 {

arch/i386/boot/setup.S

@@ -894,7 +894,7 @@ flush_instr:
 	subw	$DELTA_INITSEG, %si
 	shll	$4, %esi			# Convert to 32-bit pointer
 # NOTE: For high loaded big kernels we need a
-#	jmpi    0x100000,__KERNEL_CS
+#	jmpi    0x100000,__BOOT_CS
 #
 #	but we yet haven't reloaded the CS register, so the default size 
 #	of the target offset still is 16 bit.
@@ -905,7 +905,7 @@ flush_instr:
 	.byte 0x66, 0xea			# prefix + jmpi-opcode
 code32:	.long	0x1000				# will be set to 0x100000
 						# for big kernels
-	.word	__KERNEL_CS
+	.word	__BOOT_CS
 
 # Here's a bunch of information about your current kernel..
 kernel_version:	.ascii	UTS_RELEASE
@@ -1102,13 +1102,19 @@ delay:
 
 # Descriptor tables
 #
-# NOTE: if you think the GDT is large, you can make it smaller by just
-# defining the KERNEL_CS and KERNEL_DS entries and shifting the gdt
-# address down by GDT_ENTRY_KERNEL_CS*8. This puts bogus entries into
-# the GDT, but those wont be used so it's not a problem.
+# NOTE: The intel manual says gdt should be sixteen bytes aligned for
+# efficiency reasons.  However, there are machines which are known not
+# to boot with misaligned GDTs, so alter this at your peril!  If you alter
+# GDT_ENTRY_BOOT_CS (in asm/segment.h) remember to leave at least two
+# empty GDT entries (one for NULL and one reserved).
 #
+# NOTE:	On some CPUs, the GDT must be 8 byte aligned.  This is
+# true for the Voyager Quad CPU card which will not boot without
+# This directive.  16 byte aligment is recommended by intel.
+#
+	.align 16
 gdt:
-	.fill GDT_ENTRY_KERNEL_CS,8,0
+	.fill GDT_ENTRY_BOOT_CS,8,0
 
 	.word	0xFFFF				# 4Gb - (0x100000*0x1000 = 4Gb)
 	.word	0				# base address = 0
@@ -1121,12 +1127,17 @@ gdt:
 	.word	0x9200				# data read/write
 	.word	0x00CF				# granularity = 4096, 386
 						#  (+5th nibble of limit)
+gdt_end:
+	.align	4
+	
+	.word	0				# alignment byte
 idt_48:
 	.word	0				# idt limit = 0
 	.word	0, 0				# idt base = 0L
-gdt_48:
-	.word	GDT_ENTRY_KERNEL_CS*8 + 16 - 1	# gdt limit
 
+	.word	0				# alignment byte
+gdt_48:
+	.word	gdt_end - gdt - 1		# gdt limit
 	.word	0, 0				# gdt base (filled in later)
 
 # Include video setup & detection code

arch/i386/kernel/head.S

@@ -15,6 +15,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/desc.h>
+#include <asm/cache.h>
 
 #define OLD_CL_MAGIC_ADDR	0x90020
 #define OLD_CL_MAGIC		0xA33F
@@ -46,7 +47,7 @@ startup_32:
  * Set segments to known values
  */
 	cld
-	movl $(__KERNEL_DS),%eax
+	movl $(__BOOT_DS),%eax
 	movl %eax,%ds
 	movl %eax,%es
 	movl %eax,%fs
@@ -309,7 +310,7 @@ rp_sidt:
 
 ENTRY(stack_start)
 	.long init_thread_union+8192
-	.long __KERNEL_DS
+	.long __BOOT_DS
 
 /* This is the default interrupt "handler" :-) */
 int_msg:
@@ -352,12 +353,12 @@ idt_descr:
 	.long idt_table
 
 # boot GDT descriptor (later on used by CPU#0):
-
+	.word 0				# 32 bit align gdt_desc.address
 cpu_gdt_descr:
 	.word GDT_ENTRIES*8-1
 	.long cpu_gdt_table
 
-	.fill NR_CPUS-1,6,0		# space for the other GDT descriptors
+	.fill NR_CPUS-1,8,0		# space for the other GDT descriptors
 
 /*
  * This is initialized to create an identity-mapping at 0-8M (for bootup
@@ -408,10 +409,21 @@ ENTRY(_stext)
  */
 .data
 
-ALIGN
 /*
  * The Global Descriptor Table contains 28 quadwords, per-CPU.
  */
+#ifdef CONFIG_SMP
+/*
+ * The boot_gdt_table must mirror the equivalent in setup.S and is
+ * used only by the trampoline for booting other CPUs
+ */
+	.align L1_CACHE_BYTES
+ENTRY(boot_gdt_table)
+	.fill GDT_ENTRY_BOOT_CS,8,0
+	.quad 0x00cf9a000000ffff	/* kernel 4GB code at 0x00000000 */
+	.quad 0x00cf92000000ffff	/* kernel 4GB data at 0x00000000 */
+#endif
+	.align L1_CACHE_BYTES
 ENTRY(cpu_gdt_table)
 	.quad 0x0000000000000000	/* NULL descriptor */
 	.quad 0x0000000000000000	/* 0x0b reserved */

arch/i386/kernel/trampoline.S

@@ -54,7 +54,7 @@ r_base = .
 	lmsw	%ax		# into protected mode
 	jmp	flush_instr
 flush_instr:
-	ljmpl	$__KERNEL_CS, $0x00100000
+	ljmpl	$__BOOT_CS, $0x00100000
 			# jump to startup_32 in arch/i386/kernel/head.S
 
 idt_48:
@@ -67,8 +67,8 @@ idt_48:
 #
 
 gdt_48:
-	.word	0x0800			# gdt limit = 2048, 256 GDT entries
-	.long	cpu_gdt_table-__PAGE_OFFSET	# gdt base = gdt (first SMP CPU)
+	.word	__BOOT_DS + 7			# gdt limit
+	.long	boot_gdt_table-__PAGE_OFFSET	# gdt base = gdt (first SMP CPU)
 
 .globl trampoline_end
 trampoline_end:

include/asm-i386/desc.h

@@ -16,6 +16,7 @@ extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES];
 struct Xgt_desc_struct {
 	unsigned short size;
 	unsigned long address __attribute__((packed));
+	unsigned short pad;
 } __attribute__ ((packed));
 
 extern struct Xgt_desc_struct idt_descr, cpu_gdt_descr[NR_CPUS];

include/asm-i386/segment.h

@@ -71,6 +71,14 @@
 
 #define GDT_SIZE (GDT_ENTRIES * 8)
 
+/* Simple and small GDT entries for booting only */
+
+#define GDT_ENTRY_BOOT_CS		2
+#define __BOOT_CS	(GDT_ENTRY_BOOT_CS * 8)
+
+#define GDT_ENTRY_BOOT_DS		(GDT_ENTRY_BOOT_CS + 1)
+#define __BOOT_DS	(GDT_ENTRY_BOOT_DS * 8)
+
 /*
  * The interrupt descriptor table has room for 256 idt's,
  * the global descriptor table is dependent on the number