x86_64: Early segment setup for VT
VT is very picky about when it can enter execution. Get all segments setup and get LDT and TR into valid state to allow VT execution under VMware and KVM (untested). This makes the boot decompression run under VT, which makes it several orders of magnitude faster on 64-bit Intel hardware. Before, I was seeing times up to a minute or more to decompress a 1.3MB kernel on a very fast box. Signed-off-by: Zachary Amsden <zach@vmware.com> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
ab144f5ec6
commit
08da5a2ca4
1 changed files with 7 additions and 0 deletions
|
@ -195,6 +195,11 @@ ENTRY(startup_64)
|
||||||
movl %eax, %ds
|
movl %eax, %ds
|
||||||
movl %eax, %es
|
movl %eax, %es
|
||||||
movl %eax, %ss
|
movl %eax, %ss
|
||||||
|
movl %eax, %fs
|
||||||
|
movl %eax, %gs
|
||||||
|
lldt %ax
|
||||||
|
movl $0x20, %eax
|
||||||
|
ltr %ax
|
||||||
|
|
||||||
/* Compute the decompressed kernel start address. It is where
|
/* Compute the decompressed kernel start address. It is where
|
||||||
* we were loaded at aligned to a 2M boundary. %rbp contains the
|
* we were loaded at aligned to a 2M boundary. %rbp contains the
|
||||||
|
@ -295,6 +300,8 @@ gdt:
|
||||||
.quad 0x0000000000000000 /* NULL descriptor */
|
.quad 0x0000000000000000 /* NULL descriptor */
|
||||||
.quad 0x00af9a000000ffff /* __KERNEL_CS */
|
.quad 0x00af9a000000ffff /* __KERNEL_CS */
|
||||||
.quad 0x00cf92000000ffff /* __KERNEL_DS */
|
.quad 0x00cf92000000ffff /* __KERNEL_DS */
|
||||||
|
.quad 0x0080890000000000 /* TS descriptor */
|
||||||
|
.quad 0x0000000000000000 /* TS continued */
|
||||||
gdt_end:
|
gdt_end:
|
||||||
.bss
|
.bss
|
||||||
/* Stack for uncompression */
|
/* Stack for uncompression */
|
||||||
|
|
Loading…
Reference in a new issue