[PATCH v10 2/3] x86/tlb: allow disabling the TLB clock

[Roger Pau Monne <roger.pau@xxxxxxxxxx>]

The TLB clock is helpful when running Xen on bare metal because when
doing a TLB flush each CPU is IPI'ed and can keep a timestamp of the
last flush.

This is not the case however when Xen is running virtualized, and the
underlying hypervisor provides mechanism to assist in performing TLB
flushes: Xen itself for example offers a HVMOP_flush_tlbs hypercall in
order to perform a TLB flush without having to IPI each CPU. When
using such mechanisms it's no longer possible to keep a timestamp of
the flushes on each CPU, as they are performed by the underlying
hypervisor.

Offer a boolean in order to signal Xen that the timestamped TLB
shouldn't be used. This avoids keeping the timestamps of the flushes,
and also forces NEED_FLUSH to always return true.

No functional change intended, as this change doesn't introduce any
user that disables the timestamped TLB.

Signed-off-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
Reviewed-by: Wei Liu <wl@xxxxxxx>
Acked-by: Jan Beulich <jbeulich@xxxxxxxx>
---
 xen/arch/x86/flushtlb.c        | 19 +++++++++++++------
 xen/include/asm-x86/flushtlb.h | 17 ++++++++++++++++-
 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/xen/arch/x86/flushtlb.c b/xen/arch/x86/flushtlb.c
index 7d261aef32..e1b1e98c23 100644
--- a/xen/arch/x86/flushtlb.c
+++ b/xen/arch/x86/flushtlb.c
@@ -33,6 +33,9 @@
 u32 tlbflush_clock = 1U;
 DEFINE_PER_CPU(u32, tlbflush_time);
 
+/* Signals whether the TLB flush clock is in use. */
+bool __read_mostly tlb_clk_enabled = true;
+
 /*
  * pre_flush(): Increment the virtual TLB-flush clock. Returns new clock value.
  * 
@@ -83,12 +86,13 @@ static void post_flush(u32 t)
 static void do_tlb_flush(void)
 {
     unsigned long flags, cr4;
-    u32 t;
+    u32 t = 0;
 
     /* This non-reentrant function is sometimes called in interrupt context. */
     local_irq_save(flags);
 
-    t = pre_flush();
+    if ( tlb_clk_enabled )
+        t = pre_flush();
 
     if ( use_invpcid )
         invpcid_flush_all();
@@ -100,7 +104,8 @@ static void do_tlb_flush(void)
     else
         write_cr3(read_cr3());
 
-    post_flush(t);
+    if ( tlb_clk_enabled )
+        post_flush(t);
 
     local_irq_restore(flags);
 }
@@ -108,7 +113,7 @@ static void do_tlb_flush(void)
 void switch_cr3_cr4(unsigned long cr3, unsigned long cr4)
 {
     unsigned long flags, old_cr4;
-    u32 t;
+    u32 t = 0;
 
     /* Throughout this function we make this assumption: */
     ASSERT(!(cr4 & X86_CR4_PCIDE) || !(cr4 & X86_CR4_PGE));
@@ -116,7 +121,8 @@ void switch_cr3_cr4(unsigned long cr3, unsigned long cr4)
     /* This non-reentrant function is sometimes called in interrupt context. */
     local_irq_save(flags);
 
-    t = pre_flush();
+    if ( tlb_clk_enabled )
+        t = pre_flush();
     hvm_flush_guest_tlbs();
 
     old_cr4 = read_cr4();
@@ -169,7 +175,8 @@ void switch_cr3_cr4(unsigned long cr3, unsigned long cr4)
     if ( cr4 & X86_CR4_PCIDE )
         invpcid_flush_all_nonglobals();
 
-    post_flush(t);
+    if ( tlb_clk_enabled )
+        post_flush(t);
 
     local_irq_restore(flags);
 }
diff --git a/xen/include/asm-x86/flushtlb.h b/xen/include/asm-x86/flushtlb.h
index 50df468c16..d5ca4bad57 100644
--- a/xen/include/asm-x86/flushtlb.h
+++ b/xen/include/asm-x86/flushtlb.h
@@ -21,10 +21,21 @@ extern u32 tlbflush_clock;
 /* Time at which each CPU's TLB was last flushed. */
 DECLARE_PER_CPU(u32, tlbflush_time);
 
-#define tlbflush_current_time() tlbflush_clock
+/* TLB clock is in use. */
+extern bool tlb_clk_enabled;
+
+static inline uint32_t tlbflush_current_time(void)
+{
+    /* Returning 0 from tlbflush_current_time will always force a flush. */
+    return tlb_clk_enabled ? tlbflush_clock : 0;
+}
 
 static inline void page_set_tlbflush_timestamp(struct page_info *page)
 {
+    /* Avoid the write if the TLB clock is disabled. */
+    if ( !tlb_clk_enabled )
+        return;
+
     /*
      * Prevent storing a stale time stamp, which could happen if an update
      * to tlbflush_clock plus a subsequent flush IPI happen between the
@@ -67,6 +78,10 @@ static inline void tlbflush_filter(cpumask_t *mask, uint32_t 
page_timestamp)
 {
     unsigned int cpu;
 
+    /* Short-circuit: there's no need to iterate if the clock is disabled. */
+    if ( !tlb_clk_enabled )
+        return;
+
     for_each_cpu ( cpu, mask )
         if ( !NEED_FLUSH(per_cpu(tlbflush_time, cpu), page_timestamp) )
             __cpumask_clear_cpu(cpu, mask);
-- 
2.26.0