[Xen-devel] [PATCH] x86/flush: use APIC ALLBUT destination shorthand when possible

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

If the flush mask matches the mask of online CPUs use the APIC ALLBUT
destination shorthand in order to send an IPI to all CPUs on the
system except the current one. This can only be safely used when no
CPU hotplug or unplug operations are taking place, no offline CPUs or
those have been onlined and parked and finally when all CPUs in the
system have been accounted for (ie: the number of CPUs doesn't exceed
NR_CPUS and APIC IDs are below MAX_APICS).

This is specially beneficial when using the PV shim, since using the
shorthand avoids performing an APIC register write (or multiple ones
if using xAPIC mode) for each destination in the flush mask.

The lock time on a 32 vCPU guest using the shim without the shorthand
is:

Global lock flush_lock: addr=ffff82d0804b21c0, lockval=f602f602, not locked
  lock:228455938(79406065573135), block:205908580(556416605761539)

Average lock time: 347577ns

While the same guest using the shorthand:

Global lock flush_lock: addr=ffff82d0804b41c0, lockval=d9c4d9bc, cpu=12
  lock:1890775(416719148054), block:1663958(2500161282949)

Average lock time: 220395ns

Approximately a 1/3 improvement in the lock time.

Signed-off-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
---
 xen/arch/x86/acpi/boot.c  |  1 +
 xen/arch/x86/mpparse.c    |  5 +++++
 xen/arch/x86/smp.c        | 41 ++++++++++++++++++++++++++++++++++++++-
 xen/include/asm-x86/smp.h |  2 ++
 4 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/xen/arch/x86/acpi/boot.c b/xen/arch/x86/acpi/boot.c
index 15542a9bdf..88e1a89ff0 100644
--- a/xen/arch/x86/acpi/boot.c
+++ b/xen/arch/x86/acpi/boot.c
@@ -103,6 +103,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, 
const unsigned long end)
                               processor->lapic_flags & ACPI_MADT_ENABLED
                               ? KERN_WARNING "WARNING: " : KERN_INFO,
                               processor->local_apic_id, processor->uid);
+               cpu_overflow = true;
                /*
                 * Must not return an error here, to prevent
                 * acpi_table_parse_entries() from terminating early.
diff --git a/xen/arch/x86/mpparse.c b/xen/arch/x86/mpparse.c
index f057d9162f..8d7739fbf4 100644
--- a/xen/arch/x86/mpparse.c
+++ b/xen/arch/x86/mpparse.c
@@ -66,6 +66,9 @@ static unsigned int __initdata disabled_cpus;
 /* Bitmask of physically existing CPUs */
 physid_mask_t phys_cpu_present_map;
 
+/* Record whether CPUs haven't been added due to overflows. */
+bool __read_mostly cpu_overflow;
+
 void __init set_nr_cpu_ids(unsigned int max_cpus)
 {
        unsigned int tot_cpus = num_processors + disabled_cpus;
@@ -160,6 +163,7 @@ static int MP_processor_info_x(struct mpc_config_processor 
*m,
                printk_once(XENLOG_WARNING
                            "WARNING: NR_CPUS limit of %u reached - ignoring 
further processors\n",
                            nr_cpu_ids);
+               cpu_overflow = true;
                return -ENOSPC;
        }
 
@@ -167,6 +171,7 @@ static int MP_processor_info_x(struct mpc_config_processor 
*m,
            && genapic.name == apic_default.name) {
                printk_once(XENLOG_WARNING
                            "WARNING: CPUs limit of 8 reached - ignoring futher 
processors\n");
+               cpu_overflow = true;
                return -ENOSPC;
        }
 
diff --git a/xen/arch/x86/smp.c b/xen/arch/x86/smp.c
index 6fb39a0a24..427c33db9d 100644
--- a/xen/arch/x86/smp.c
+++ b/xen/arch/x86/smp.c
@@ -8,6 +8,7 @@
  *     later.
  */
 
+#include <xen/cpu.h>
 #include <xen/irq.h>
 #include <xen/sched.h>
 #include <xen/delay.h>
@@ -123,6 +124,11 @@ void send_IPI_self_legacy(uint8_t vector)
     __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
 }
 
+static void send_IPI_allbutself(unsigned int vector)
+{
+    __default_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, APIC_DEST_PHYSICAL);
+}
+
 void send_IPI_mask_flat(const cpumask_t *cpumask, int vector)
 {
     unsigned long mask = cpumask_bits(cpumask)[0];
@@ -227,14 +233,47 @@ 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)) )
     {
+        bool cpus_locked = false;
+
         spin_lock(&flush_lock);
         cpumask_and(&flush_cpumask, mask, &cpu_online_map);
         cpumask_clear_cpu(cpu, &flush_cpumask);
         flush_va      = va;
         flush_flags   = flags;
-        send_IPI_mask(&flush_cpumask, INVALIDATE_TLB_VECTOR);
+
+        /*
+         * Prevent any CPU hot{un}plug while sending the IPIs if we are to use
+         * a shorthand, also refuse to use a shorthand if not all CPUs are
+         * online or have been parked.
+         */
+        if ( system_state > SYS_STATE_smp_boot && !cpu_overflow &&
+             (cpus_locked = get_cpu_maps()) &&
+             (park_offline_cpus ||
+              cpumask_equal(&cpu_online_map, &cpu_present_map)) )
+        {
+            cpumask_copy(this_cpu(scratch_cpumask), &cpu_online_map);
+            cpumask_clear_cpu(cpu, this_cpu(scratch_cpumask));
+        }
+        else
+        {
+            if ( cpus_locked )
+            {
+                put_cpu_maps();
+                cpus_locked = false;
+            }
+            cpumask_clear(this_cpu(scratch_cpumask));
+        }
+
+        if ( cpumask_equal(&flush_cpumask, this_cpu(scratch_cpumask)) )
+            send_IPI_allbutself(INVALIDATE_TLB_VECTOR);
+        else
+            send_IPI_mask(&flush_cpumask, INVALIDATE_TLB_VECTOR);
+
         while ( !cpumask_empty(&flush_cpumask) )
             cpu_relax();
+
+        if ( cpus_locked )
+            put_cpu_maps();
         spin_unlock(&flush_lock);
     }
 }
diff --git a/xen/include/asm-x86/smp.h b/xen/include/asm-x86/smp.h
index dbeed2fd41..3df4185744 100644
--- a/xen/include/asm-x86/smp.h
+++ b/xen/include/asm-x86/smp.h
@@ -84,6 +84,8 @@ extern cpumask_t **socket_cpumask;
 #define get_cpu_current(cpu) \
     (get_cpu_info_from_stack((unsigned long)stack_base[cpu])->current_vcpu)
 
+extern bool cpu_overflow;
+
 #endif /* !__ASSEMBLY__ */
 
 #endif
-- 
2.24.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel