x86/tlb: use Xen L0 assisted TLB flush when available

Use Xen's L0 HVMOP_flush_tlbs hypercall in order to perform flushes.
This greatly increases the performance of TLB flushes when running
with a high amount of vCPUs as a Xen guest, and is specially important
when running in shim mode.

The following figures are from a PV guest running `make -j32 xen` in
shim mode with 32 vCPUs and HAP.

Using x2APIC and ALLBUT shorthand:
real	4m35.973s
user	4m35.110s
sys	36m24.117s

Using L0 assisted flush:
real    1m2.596s
user    4m34.818s
sys     5m16.374s

The implementation adds a new hook to hypervisor_ops so other
enlightenments can also implement such assisted flush just by filling
the hook.

Note that the Xen implementation completely ignores the dirty CPU mask
and the linear address passed in, and always performs a global TLB
flush on all vCPUs. This is a limitation of the hypercall provided by
Xen. Also note that local TLB flushes are not performed using the
assisted TLB flush, only remote ones.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Wei Liu <wl@xen.org>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/guest/hypervisor.c

@@ -18,6 +18,7 @@
  *
  * Copyright (c) 2019 Microsoft.
  */
+#include <xen/cpumask.h>
 #include <xen/init.h>
 #include <xen/types.h>
 
@@ -51,6 +52,10 @@ void __init hypervisor_setup(void)
 {
     if ( ops.setup )
         ops.setup();
+
+    /* Check if assisted flush is available and disable the TLB clock if so. */
+    if ( !hypervisor_flush_tlb(cpumask_of(smp_processor_id()), NULL, 0) )
+        tlb_clk_enabled = false;
 }
 
 int hypervisor_ap_setup(void)
@@ -73,6 +78,15 @@ void __init hypervisor_e820_fixup(struct e820map *e820)
         ops.e820_fixup(e820);
 }
 
+int hypervisor_flush_tlb(const cpumask_t *mask, const void *va,
+                         unsigned int order)
+{
+    if ( ops.flush_tlb )
+        return alternative_call(ops.flush_tlb, mask, va, order);
+
+    return -EOPNOTSUPP;
+}
+
 /*
  * Local variables:
  * mode: C

xen/arch/x86/guest/xen/xen.c

@@ -324,12 +324,18 @@ static void __init e820_fixup(struct e820map *e820)
         pv_shim_fixup_e820(e820);
 }
 
+static int flush_tlb(const cpumask_t *mask, const void *va, unsigned int order)
+{
+    return xen_hypercall_hvm_op(HVMOP_flush_tlbs, NULL);
+}
+
 static const struct hypervisor_ops __initconstrel ops = {
     .name = "Xen",
     .setup = setup,
     .ap_setup = ap_setup,
     .resume = resume,
     .e820_fixup = e820_fixup,
+    .flush_tlb = flush_tlb,
 };
 
 const struct hypervisor_ops *__init xg_probe(void)

xen/arch/x86/smp.c

@@ -15,6 +15,7 @@
 #include <xen/perfc.h>
 #include <xen/spinlock.h>
 #include <asm/current.h>
+#include <asm/guest.h>
 #include <asm/smp.h>
 #include <asm/mc146818rtc.h>
 #include <asm/flushtlb.h>
@@ -268,6 +269,12 @@ void flush_area_mask(const cpumask_t *mask, const void *va, unsigned int flags)
     if ( (flags & ~FLUSH_ORDER_MASK) &&
          !cpumask_subset(mask, cpumask_of(cpu)) )
     {
+        if ( cpu_has_hypervisor &&
+             !(flags & ~(FLUSH_TLB | FLUSH_TLB_GLOBAL | FLUSH_VA_VALID |
+                         FLUSH_ORDER_MASK)) &&
+             !hypervisor_flush_tlb(mask, va, (flags - 1) & FLUSH_ORDER_MASK) )
+            return;
+
         spin_lock(&flush_lock);
         cpumask_and(&flush_cpumask, mask, &cpu_online_map);
         cpumask_clear_cpu(cpu, &flush_cpumask);

xen/include/asm-x86/guest/hypervisor.h

@@ -19,6 +19,8 @@
 #ifndef __X86_HYPERVISOR_H__
 #define __X86_HYPERVISOR_H__
 
+#include <xen/cpumask.h>
+
 #include <asm/e820.h>
 
 struct hypervisor_ops {
@@ -32,6 +34,8 @@ struct hypervisor_ops {
     void (*resume)(void);
     /* Fix up e820 map */
     void (*e820_fixup)(struct e820map *e820);
+    /* L0 assisted TLB flush */
+    int (*flush_tlb)(const cpumask_t *mask, const void *va, unsigned int order);
 };
 
 #ifdef CONFIG_GUEST
@@ -41,6 +45,14 @@ void hypervisor_setup(void);
 int hypervisor_ap_setup(void);
 void hypervisor_resume(void);
 void hypervisor_e820_fixup(struct e820map *e820);
+/*
+ * L0 assisted TLB flush.
+ * mask: cpumask of the dirty vCPUs that should be flushed.
+ * va: linear address to flush, or NULL for global flushes.
+ * order: order of the linear address pointed by va.
+ */
+int hypervisor_flush_tlb(const cpumask_t *mask, const void *va,
+                         unsigned int order);
 
 #else
 
@@ -52,6 +64,11 @@ static inline void hypervisor_setup(void) { ASSERT_UNREACHABLE(); }
 static inline int hypervisor_ap_setup(void) { return 0; }
 static inline void hypervisor_resume(void) { ASSERT_UNREACHABLE(); }
 static inline void hypervisor_e820_fixup(struct e820map *e820) {}
+static inline int hypervisor_flush_tlb(const cpumask_t *mask, const void *va,
+                                       unsigned int order)
+{
+    return -EOPNOTSUPP;
+}
 
 #endif  /* CONFIG_GUEST */