[PATCHv3] x86/trampoline: Bypass compat mode in trampoline_start64() if not needed
Commit Message
The trampoline_start64() vector is used when a secondary CPU starts in
64-bit mode. The current implementation directly enters compatibility
mode. It is necessary to disable paging and re-enable it in the correct
paging mode: either 4- or 5-level, depending on the configuration.
The X86S[1] ISA does not support compatibility mode in ring 0, and
paging cannot be disabled.
The trampoline_start64() function is reworked to only enter compatibility
mode if it is necessary to change the paging mode. If the CPU is already
in the desired paging mode, it will proceed in long mode.
This change will allow a secondary CPU to boot on an X86S machine as
long as the CPU is already in the correct paging mode.
In the future, there will be a mechanism to switch between paging modes
without disabling paging.
[1] https://www.intel.com/content/www/us/en/developer/articles/technical/envisioning-future-simplified-architecture.html
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Sean Christopherson <seanjc@google.com>
---
v3:
- tr_cr4 is 32-bit, use 32-bit XOR to access it (Sean).
- Use 32-bit TEST instead of AND to check if LA57 different between
CR4 and tr_cr4 (Sean).
v2:
- Fix build with GCC;
---
arch/x86/realmode/rm/trampoline_64.S | 31 +++++++++++++++++++++++++++-
1 file changed, 30 insertions(+), 1 deletion(-)
Comments
On Tue, 2024-01-09 at 01:16 +0300, Kirill A. Shutemov wrote:
> The trampoline_start64() vector is used when a secondary CPU starts in
> 64-bit mode. The current implementation directly enters compatibility
> mode. It is necessary to disable paging and re-enable it in the correct
> paging mode: either 4- or 5-level, depending on the configuration.
>
> The X86S[1] ISA does not support compatibility mode in ring 0, and
> paging cannot be disabled.
>
> The trampoline_start64() function is reworked to only enter compatibility
> mode if it is necessary to change the paging mode. If the CPU is already
> in the desired paging mode, it will proceed in long mode.
>
> This change will allow a secondary CPU to boot on an X86S machine as
> long as the CPU is already in the correct paging mode.
>
> In the future, there will be a mechanism to switch between paging modes
> without disabling paging.
>
> [1] https://www.intel.com/content/www/us/en/developer/articles/technical/envisioning-future-simplified-architecture.html
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> Cc: Sean Christopherson <seanjc@google.com>
>
Reviewed-by: Kai Huang <kai.huang@intel.com>
> ---
> v3:
> - tr_cr4 is 32-bit, use 32-bit XOR to access it (Sean).
> - Use 32-bit TEST instead of AND to check if LA57 different between
> CR4 and tr_cr4 (Sean).
> v2:
> - Fix build with GCC;
> ---
> arch/x86/realmode/rm/trampoline_64.S | 31 +++++++++++++++++++++++++++-
> 1 file changed, 30 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
> index c9f76fae902e..608f108cba7d 100644
> --- a/arch/x86/realmode/rm/trampoline_64.S
> +++ b/arch/x86/realmode/rm/trampoline_64.S
> @@ -37,13 +37,15 @@
> .text
> .code16
>
> -.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0
> +.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 lock_rip=0
> /*
> * Make sure only one CPU fiddles with the realmode stack
> */
> .Llock_rm\@:
> .if \lock_pa
> lock btsl $0, pa_tr_lock
> + .elseif \lock_rip
> + lock btsl $0, tr_lock(%rip)
> .else
> lock btsl $0, tr_lock
> .endif
> @@ -220,6 +222,33 @@ SYM_CODE_START(trampoline_start64)
> lidt tr_idt(%rip)
> lgdt tr_gdt64(%rip)
>
> + /* Check if paging mode has to be changed */
> + movq %cr4, %rax
> + xorl tr_cr4(%rip), %eax
> + testl $X86_CR4_LA57, %eax
> + jnz .L_switch_paging
> +
> + /* Paging mode is correct proceed in 64-bit mode */
> +
> + LOCK_AND_LOAD_REALMODE_ESP lock_rip=1
> +
> + movw $__KERNEL_DS, %dx
> + movl %edx, %ss
> + addl $pa_real_mode_base, %esp
> + movl %edx, %ds
> + movl %edx, %es
> + movl %edx, %fs
> + movl %edx, %gs
> +
> + movl $pa_trampoline_pgd, %eax
> + movq %rax, %cr3
> +
> + jmpq *tr_start(%rip)
> +.L_switch_paging:
> + /*
> + * To switch between 4- and 5-level paging modes, it is necessary
> + * to disable paging. This must be done in the compatibility mode.
> + */
> ljmpl *tr_compat(%rip)
> SYM_CODE_END(trampoline_start64)
>
@@ -37,13 +37,15 @@
.text
.code16
-.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0
+.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 lock_rip=0
/*
* Make sure only one CPU fiddles with the realmode stack
*/
.Llock_rm\@:
.if \lock_pa
lock btsl $0, pa_tr_lock
+ .elseif \lock_rip
+ lock btsl $0, tr_lock(%rip)
.else
lock btsl $0, tr_lock
.endif
@@ -220,6 +222,33 @@ SYM_CODE_START(trampoline_start64)
lidt tr_idt(%rip)
lgdt tr_gdt64(%rip)
+ /* Check if paging mode has to be changed */
+ movq %cr4, %rax
+ xorl tr_cr4(%rip), %eax
+ testl $X86_CR4_LA57, %eax
+ jnz .L_switch_paging
+
+ /* Paging mode is correct proceed in 64-bit mode */
+
+ LOCK_AND_LOAD_REALMODE_ESP lock_rip=1
+
+ movw $__KERNEL_DS, %dx
+ movl %edx, %ss
+ addl $pa_real_mode_base, %esp
+ movl %edx, %ds
+ movl %edx, %es
+ movl %edx, %fs
+ movl %edx, %gs
+
+ movl $pa_trampoline_pgd, %eax
+ movq %rax, %cr3
+
+ jmpq *tr_start(%rip)
+.L_switch_paging:
+ /*
+ * To switch between 4- and 5-level paging modes, it is necessary
+ * to disable paging. This must be done in the compatibility mode.
+ */
ljmpl *tr_compat(%rip)
SYM_CODE_END(trampoline_start64)