Later commits will rely on this information to defer kernel TLB flush
IPIs. Update it when switching to and from the kernel CR3.

This will only be really useful for NOHZ_FULL CPUs, but it should be
cheaper to unconditionally update a never-used per-CPU variable living in
its own cacheline than to check a shared cpumask such as
  housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)
at every entry.

Note that the COALESCE_TLBI config option is introduced in a later commit,
when the whole feature is implemented.

Signed-off-by: Valentin Schneider <vschneid@redhat.com>
---
Per the cover letter, I really hate this, but couldn't come up with
anything better.
---
 arch/x86/entry/calling.h        | 16 ++++++++++++++++
 arch/x86/entry/syscall_64.c     |  4 ++++
 arch/x86/include/asm/tlbflush.h |  3 +++
 3 files changed, 23 insertions(+)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 94519688b0071..813451b1ddecc 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -171,11 +171,24 @@ For 32-bit we have the following conventions - kernel is built with
	andq    $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
 .endm

+.macro COALESCE_TLBI
+#ifdef CONFIG_COALESCE_TLBI
+	movl     $1, PER_CPU_VAR(kernel_cr3_loaded)
+#endif // CONFIG_COALESCE_TLBI
+.endm
+
+.macro NOTE_SWITCH_TO_USER_CR3
+#ifdef CONFIG_COALESCE_TLBI
+	movl     $0, PER_CPU_VAR(kernel_cr3_loaded)
+#endif // CONFIG_COALESCE_TLBI
+.endm
+
 .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
	mov	%cr3, \scratch_reg
	ADJUST_KERNEL_CR3 \scratch_reg
	mov	\scratch_reg, %cr3
+	COALESCE_TLBI
 .Lend_\@:
 .endm

@@ -183,6 +196,7 @@ For 32-bit we have the following conventions - kernel is built with
	PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask)

 .macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req
+	NOTE_SWITCH_TO_USER_CR3
	mov	%cr3, \scratch_reg

	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
@@ -242,6 +256,7 @@ For 32-bit we have the following conventions - kernel is built with

	ADJUST_KERNEL_CR3 \scratch_reg
	movq	\scratch_reg, %cr3
+	COALESCE_TLBI

 .Ldone_\@:
 .endm
@@ -258,6 +273,7 @@ For 32-bit we have the following conventions - kernel is built with
	bt	$PTI_USER_PGTABLE_BIT, \save_reg
	jnc	.Lend_\@

+	NOTE_SWITCH_TO_USER_CR3
	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID

	/*
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index b6e68ea98b839..2589d232e0ba1 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -83,6 +83,10 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
	return false;
 }

+#ifdef CONFIG_COALESCE_TLBI
+DEFINE_PER_CPU(bool, kernel_cr3_loaded) = true;
+#endif
+
 /* Returns true to return using SYSRET, or false to use IRET */
 __visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
 {
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 00daedfefc1b0..e39ae95b85072 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -17,6 +17,9 @@
 #include <asm/pgtable.h>

 DECLARE_PER_CPU(u64, tlbstate_untag_mask);
+#ifdef CONFIG_COALESCE_TLBI
+DECLARE_PER_CPU(bool, kernel_cr3_loaded);
+#endif

 void __flush_tlb_all(void);

--
2.51.0