[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>
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index ae924c4..905364d 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -56,6 +56,7 @@
#include <asm/tlbflush.h>
#include <asm/cpu.h>
+#include <asm/pda.h>
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -346,6 +347,7 @@
regs.xds = __USER_DS;
regs.xes = __USER_DS;
+ regs.xgs = __KERNEL_PDA;
regs.orig_eax = -1;
regs.eip = (unsigned long) kernel_thread_helper;
regs.xcs = __KERNEL_CS | get_kernel_rpl();
@@ -431,7 +433,6 @@
p->thread.eip = (unsigned long) ret_from_fork;
savesegment(fs,p->thread.fs);
- savesegment(gs,p->thread.gs);
tsk = current;
if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
@@ -659,16 +660,16 @@
load_esp0(tss, next);
/*
- * Save away %fs and %gs. No need to save %es and %ds, as
- * those are always kernel segments while inside the kernel.
- * Doing this before setting the new TLS descriptors avoids
- * the situation where we temporarily have non-reloadable
- * segments in %fs and %gs. This could be an issue if the
- * NMI handler ever used %fs or %gs (it does not today), or
- * if the kernel is running inside of a hypervisor layer.
+ * Save away %fs. No need to save %gs, as it was saved on the
+ * stack on entry. No need to save %es and %ds, as those are
+ * always kernel segments while inside the kernel. Doing this
+ * before setting the new TLS descriptors avoids the situation
+ * where we temporarily have non-reloadable segments in %fs
+ * and %gs. This could be an issue if the NMI handler ever
+ * used %fs or %gs (it does not today), or if the kernel is
+ * running inside of a hypervisor layer.
*/
savesegment(fs, prev->fs);
- savesegment(gs, prev->gs);
/*
* Load the per-thread Thread-Local Storage descriptor.
@@ -676,16 +677,13 @@
load_TLS(next, cpu);
/*
- * Restore %fs and %gs if needed.
+ * Restore %fs if needed.
*
- * Glibc normally makes %fs be zero, and %gs is one of
- * the TLS segments.
+ * Glibc normally makes %fs be zero.
*/
if (unlikely(prev->fs | next->fs))
loadsegment(fs, next->fs);
- if (prev->gs | next->gs)
- loadsegment(gs, next->gs);
/*
* Restore IOPL if needed.