[PATCH 4.4 21/37] kaiser: x86_cr3_pcid_noflush and x86_cr3_pcid_user

[Greg Kroah-Hartman]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hugh Dickins <hughd@xxxxxxxxxx>


Mostly this commit is just unshouting X86_CR3_PCID_KERN_VAR and
X86_CR3_PCID_USER_VAR: we usually name variables in lower-case.

But why does x86_cr3_pcid_noflush need to be __aligned(PAGE_SIZE)?
Ah, it's a leftover from when kaiser_add_user_map() once complained
about mapping the same page twice.  Make it __read_mostly instead.
(I'm a little uneasy about all the unrelated data which shares its
page getting user-mapped too, but that was so before, and not a big
deal: though we call it user-mapped, it's not mapped with _PAGE_USER.)

And there is a little change around the two calls to do_nmi().
Previously they set the NOFLUSH bit (if PCID supported) when
forcing to kernel context before do_nmi(); now they also have the
NOFLUSH bit set (if PCID supported) when restoring context after:
nothing done in do_nmi() should require a TLB to be flushed here.

Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Acked-by: Jiri Kosina <jkosina@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 arch/x86/entry/entry_64.S     |    8 ++++----
 arch/x86/include/asm/kaiser.h |   11 +++++------
 arch/x86/mm/kaiser.c          |   13 +++++++------
 3 files changed, 16 insertions(+), 16 deletions(-)

--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1290,11 +1290,11 @@ ENTRY(nmi)
 	/* Unconditionally use kernel CR3 for do_nmi() */
 	/* %rax is saved above, so OK to clobber here */
 	movq	%cr3, %rax
+	/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+	orq	x86_cr3_pcid_noflush, %rax
 	pushq	%rax
 	/* mask off "user" bit of pgd address and 12 PCID bits: */
 	andq	$(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
-	/* Add back kernel PCID and "no flush" bit */
-	orq	X86_CR3_PCID_KERN_VAR, %rax
 	movq	%rax, %cr3
 #endif
 	call	do_nmi
@@ -1534,11 +1534,11 @@ end_repeat_nmi:
 	/* Unconditionally use kernel CR3 for do_nmi() */
 	/* %rax is saved above, so OK to clobber here */
 	movq	%cr3, %rax
+	/* If PCID enabled, NOFLUSH now and NOFLUSH on return */
+	orq	x86_cr3_pcid_noflush, %rax
 	pushq	%rax
 	/* mask off "user" bit of pgd address and 12 PCID bits: */
 	andq	$(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), %rax
-	/* Add back kernel PCID and "no flush" bit */
-	orq	X86_CR3_PCID_KERN_VAR, %rax
 	movq	%rax, %cr3
 #endif
 
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -25,7 +25,7 @@
 .macro _SWITCH_TO_KERNEL_CR3 reg
 movq %cr3, \reg
 andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq  X86_CR3_PCID_KERN_VAR, \reg
+orq  x86_cr3_pcid_noflush, \reg
 movq \reg, %cr3
 .endm
 
@@ -37,11 +37,10 @@ movq \reg, %cr3
  * not enabled): so that the one register can update both memory and cr3.
  */
 movq %cr3, \reg
-andq $(~(X86_CR3_PCID_ASID_MASK | KAISER_SHADOW_PGD_OFFSET)), \reg
-orq  PER_CPU_VAR(X86_CR3_PCID_USER_VAR), \reg
+orq  PER_CPU_VAR(x86_cr3_pcid_user), \reg
 js   9f
 /* FLUSH this time, reset to NOFLUSH for next time (if PCID enabled) */
-movb \regb, PER_CPU_VAR(X86_CR3_PCID_USER_VAR+7)
+movb \regb, PER_CPU_VAR(x86_cr3_pcid_user+7)
 9:
 movq \reg, %cr3
 .endm
@@ -94,8 +93,8 @@ movq PER_CPU_VAR(unsafe_stack_register_b
 */
 DECLARE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
 
-extern unsigned long X86_CR3_PCID_KERN_VAR;
-DECLARE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+extern unsigned long x86_cr3_pcid_noflush;
+DECLARE_PER_CPU(unsigned long, x86_cr3_pcid_user);
 
 extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
 
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -29,8 +29,8 @@ DEFINE_PER_CPU_USER_MAPPED(unsigned long
  * This is also handy because systems that do not support PCIDs
  * just end up or'ing a 0 into their CR3, which does no harm.
  */
-__aligned(PAGE_SIZE) unsigned long X86_CR3_PCID_KERN_VAR;
-DEFINE_PER_CPU(unsigned long, X86_CR3_PCID_USER_VAR);
+unsigned long x86_cr3_pcid_noflush __read_mostly;
+DEFINE_PER_CPU(unsigned long, x86_cr3_pcid_user);
 
 /*
  * At runtime, the only things we map are some things for CPU
@@ -304,7 +304,8 @@ void __init kaiser_init(void)
 				  sizeof(gate_desc) * NR_VECTORS,
 				  __PAGE_KERNEL);
 
-	kaiser_add_user_map_early(&X86_CR3_PCID_KERN_VAR, PAGE_SIZE,
+	kaiser_add_user_map_early(&x86_cr3_pcid_noflush,
+				  sizeof(x86_cr3_pcid_noflush),
 				  __PAGE_KERNEL);
 }
 
@@ -384,8 +385,8 @@ void kaiser_setup_pcid(void)
 	 * These variables are used by the entry/exit
 	 * code to change PCID and pgd and TLB flushing.
 	 */
-	X86_CR3_PCID_KERN_VAR = kern_cr3;
-	this_cpu_write(X86_CR3_PCID_USER_VAR, user_cr3);
+	x86_cr3_pcid_noflush = kern_cr3;
+	this_cpu_write(x86_cr3_pcid_user, user_cr3);
 }
 
 /*
@@ -395,7 +396,7 @@ void kaiser_setup_pcid(void)
  */
 void kaiser_flush_tlb_on_return_to_user(void)
 {
-	this_cpu_write(X86_CR3_PCID_USER_VAR,
+	this_cpu_write(x86_cr3_pcid_user,
 			X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
 }
 EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);