Messages in this thread Patch in this message | | | From | Lai Jiangshan <> | Subject | [PATCH V4 32/50] x86/entry: Skip CR3 write when the saved CR3 is kernel CR3 in RESTORE_CR3 | Date | Tue, 26 Oct 2021 22:34:18 +0800 |
| |
From: Lai Jiangshan <laijs@linux.alibaba.com>
When the original CR3 is kernel CR3, paranoid_entry() hasn't changed the CR3, so the CR3 doesn't need to restored when paranoid_exit() in the this case.
Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com> --- arch/x86/entry/calling.h | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 996b041e92d2..9065c31d2875 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -231,14 +231,11 @@ For 32-bit we have the following conventions - kernel is built with .macro RESTORE_CR3 scratch_reg:req save_reg:req ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI - ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID - - /* - * KERNEL pages can always resume with NOFLUSH as we do - * explicit flushes. - */ + /* No need to restore when the saved CR3 is kernel CR3. */ bt $PTI_USER_PGTABLE_BIT, \save_reg - jnc .Lnoflush_\@ + jnc .Lend_\@ + + ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID /* * Check if there's a pending flush for the user ASID we're @@ -256,10 +253,6 @@ For 32-bit we have the following conventions - kernel is built with SET_NOFLUSH_BIT \save_reg .Lwrcr3_\@: - /* - * The CR3 write could be avoided when not changing its value, - * but would require a CR3 read *and* a scratch register. - */ movq \save_reg, %cr3 .Lend_\@: .endm -- 2.19.1.6.gb485710b
| |