[PATCH] i386: Use %gs as the PDA base-segment in the kernel

This patch is the meat of the PDA change.  This patch makes several related
changes:

1: Most significantly, %gs is now used in the kernel.  This means that on
   entry, the old value of %gs is saved away, and it is reloaded with
   __KERNEL_PDA.

2: entry.S constructs the stack in the shape of struct pt_regs, and this
   is passed around the kernel so that the process's saved register
   state can be accessed.

   Unfortunately struct pt_regs doesn't currently have space for %gs
   (or %fs). This patch extends pt_regs to add space for gs (no space
   is allocated for %fs, since it won't be used, and it would just
   complicate the code in entry.S to work around the space).

3: Because %gs is now saved on the stack like %ds, %es and the integer
   registers, there are a number of places where it no longer needs to
   be handled specially; namely context switch, and saving/restoring the
   register state in a signal context.

4: And since kernel threads run in kernel space and call normal kernel
   code, they need to be created with their %gs == __KERNEL_PDA.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Chuck Ebbert <76306.1226@compuserve.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>

1 files changed, 27 insertions, 4 deletions

diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index 4a83384..5b14e95 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -302,6 +302,7 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%cr0
 
 	call check_x87
+	call setup_pda
 	lgdt cpu_gdt_descr
 	lidt idt_descr
 	ljmp $(__KERNEL_CS),$1f
@@ -312,10 +313,13 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%ds
 	movl %eax,%es
 
-	xorl %eax,%eax			# Clear FS/GS and LDT
+	xorl %eax,%eax			# Clear FS and LDT
 	movl %eax,%fs
-	movl %eax,%gs
 	lldt %ax
+
+	movl $(__KERNEL_PDA),%eax
+	mov  %eax,%gs
+
 	cld			# gcc2 wants the direction flag cleared at all times
 	pushl $0		# fake return address for unwinder
 #ifdef CONFIG_SMP
@@ -346,6 +350,23 @@ check_x87:
 	ret
 
 /*
+ * Point the GDT at this CPU's PDA.  On boot this will be
+ * cpu_gdt_table and boot_pda; for secondary CPUs, these will be
+ * that CPU's GDT and PDA.
+ */
+setup_pda:
+	/* get the PDA pointer */
+	movl start_pda, %eax
+
+	/* slot the PDA address into the GDT */
+	mov cpu_gdt_descr+2, %ecx
+	mov %ax, (__KERNEL_PDA+0+2)(%ecx)		/* base & 0x0000ffff */
+	shr $16, %eax
+	mov %al, (__KERNEL_PDA+4+0)(%ecx)		/* base & 0x00ff0000 */
+	mov %ah, (__KERNEL_PDA+4+3)(%ecx)		/* base & 0xff000000 */
+	ret
+
+/*
  *  setup_idt
  *
  *  sets up a idt with 256 entries pointing to
@@ -484,6 +505,8 @@ ENTRY(empty_zero_page)
  * This starts the data section.
  */
 .data
+ENTRY(start_pda)
+	.long boot_pda
 
 ENTRY(stack_start)
 	.long init_thread_union+THREAD_SIZE
@@ -525,7 +548,7 @@ idt_descr:
 
 # boot GDT descriptor (later on used by CPU#0):
 	.word 0				# 32 bit align gdt_desc.address
-cpu_gdt_descr:
+ENTRY(cpu_gdt_descr)
 	.word GDT_ENTRIES*8-1
 	.long cpu_gdt_table
 
@@ -585,7 +608,7 @@ ENTRY(cpu_gdt_table)
 	.quad 0x004092000000ffff	/* 0xc8 APM DS    data */
 
 	.quad 0x00c0920000000000	/* 0xd0 - ESPFIX SS */
-	.quad 0x0000000000000000	/* 0xd8 - PDA */
+	.quad 0x00cf92000000ffff	/* 0xd8 - PDA */
 	.quad 0x0000000000000000	/* 0xe0 - unused */
 	.quad 0x0000000000000000	/* 0xe8 - unused */
 	.quad 0x0000000000000000	/* 0xf0 - unused */