paravirt: clean up lazy mode handling

Currently, the set_lazy_mode pv_op is overloaded with 5 functions:
 1. enter lazy cpu mode
 2. leave lazy cpu mode
 3. enter lazy mmu mode
 4. leave lazy mmu mode
 5. flush pending batched operations

This complicates each paravirt backend, since it needs to deal with
all the possible state transitions, handling flushing, etc. In
particular, flushing is quite distinct from the other 4 functions, and
seems to just cause complication.

This patch removes the set_lazy_mode operation, and adds "enter" and
"leave" lazy mode operations on mmu_ops and cpu_ops.  All the logic
associated with enter and leaving lazy states is now in common code
(basically BUG_ONs to make sure that no mode is current when entering
a lazy mode, and make sure that the mode is current when leaving).
Also, flush is handled in a common way, by simply leaving and
re-entering the lazy mode.

The result is that the Xen, lguest and VMI lazy mode implementations
are much simpler.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Zach Amsden <zach@vmware.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Avi Kivity <avi@qumranet.com>
Cc: Anthony Liguory <aliguori@us.ibm.com>
Cc: "Glauber de Oliveira Costa" <glommer@gmail.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>

1 files changed, 11 insertions, 21 deletions

diff --git a/drivers/lguest/lguest.c b/drivers/lguest/lguest.c
index ca9b844f37c2..c302629e0895 100644
--- a/drivers/lguest/lguest.c
+++ b/drivers/lguest/lguest.c
@@ -97,29 +97,17 @@ static cycle_t clock_base;
  * them as a batch when lazy_mode is eventually turned off.  Because hypercalls
  * are reasonably expensive, batching them up makes sense.  For example, a
  * large mmap might update dozens of page table entries: that code calls
- * lguest_lazy_mode(PARAVIRT_LAZY_MMU), does the dozen updates, then calls
- * lguest_lazy_mode(PARAVIRT_LAZY_NONE).
+ * paravirt_enter_lazy_mmu(), does the dozen updates, then calls
+ * lguest_leave_lazy_mode().
  *
  * So, when we're in lazy mode, we call async_hypercall() to store the call for
  * future processing.  When lazy mode is turned off we issue a hypercall to
  * flush the stored calls.
- *
- * There's also a hack where "mode" is set to "PARAVIRT_LAZY_FLUSH" which
- * indicates we're to flush any outstanding calls immediately.  This is used
- * when an interrupt handler does a kmap_atomic(): the page table changes must
- * happen immediately even if we're in the middle of a batch.  Usually we're
- * not, though, so there's nothing to do. */
-static enum paravirt_lazy_mode lazy_mode; /* Note: not SMP-safe! */
-static void lguest_lazy_mode(enum paravirt_lazy_mode mode)
+ */
+static void lguest_leave_lazy_mode(void)
 {
-        if (mode == PARAVIRT_LAZY_FLUSH) {
-                if (unlikely(lazy_mode != PARAVIRT_LAZY_NONE))
-                        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
-        } else {
-                lazy_mode = mode;
-                if (mode == PARAVIRT_LAZY_NONE)
-                        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
-        }
+        paravirt_leave_lazy(paravirt_get_lazy_mode());
+        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
 }
 
 static void lazy_hcall(unsigned long call,
@@ -127,7 +115,7 @@ static void lazy_hcall(unsigned long call,
                        unsigned long arg2,
                        unsigned long arg3)
 {
-        if (lazy_mode == PARAVIRT_LAZY_NONE)
+        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
                 hcall(call, arg1, arg2, arg3);
         else
                 async_hcall(call, arg1, arg2, arg3);
@@ -1011,6 +999,8 @@ __init void lguest_init(void *boot)
         pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
         pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
         pv_cpu_ops.wbinvd = lguest_wbinvd;
+        pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
+        pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
 
         /* pagetable management */
         pv_mmu_ops.write_cr3 = lguest_write_cr3;
@@ -1022,6 +1012,8 @@ __init void lguest_init(void *boot)
         pv_mmu_ops.set_pmd = lguest_set_pmd;
         pv_mmu_ops.read_cr2 = lguest_read_cr2;
         pv_mmu_ops.read_cr3 = lguest_read_cr3;
+        pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
+        pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
 
 #ifdef CONFIG_X86_LOCAL_APIC
         /* apic read/write intercepts */
@@ -1034,8 +1026,6 @@ __init void lguest_init(void *boot)
         pv_time_ops.get_wallclock = lguest_get_wallclock;
         pv_time_ops.time_init = lguest_time_init;
 
-        pv_misc_ops.set_lazy_mode = lguest_lazy_mode;
-
         /* Now is a good time to look at the implementations of these functions
          * before returning to the rest of lguest_init(). */