[PATCH 3/3] x86/pv: Compile out compat_gdt in !CONFIG_PV builds

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

There is no need for the Compat GDT if there are no 32bit PV guests.  This
saves 4k per online CPU

Bloat-o-meter reports the following savings in Xen itself:

  add/remove: 0/3 grow/shrink: 1/4 up/down: 7/-4612 (-4605)
  Function                                     old     new   delta
  cpu_smpboot_free                            1249    1256      +7
  per_cpu__compat_gdt_l1e                        8       -      -8
  per_cpu__compat_gdt                            8       -      -8
  init_idt_traps                               442     420     -22
  load_system_tables                           414     364     -50
  trap_init                                    444     280    -164
  cpu_smpboot_callback                        1255     991    -264
  boot_compat_gdt                             4096       -   -4096
  Total: Before=3062726, After=3058121, chg -0.15%

Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
---
CC: Jan Beulich <JBeulich@xxxxxxxx>
CC: Wei Liu <wl@xxxxxxx>
CC: Roger Pau Monné <roger.pau@xxxxxxxxxx>

The increase in cpu_smpboot_free() appears to be a consequence of a totally
different layout of basic blocks.
---
 xen/arch/x86/cpu/common.c |  5 +++--
 xen/arch/x86/desc.c       |  2 ++
 xen/arch/x86/smpboot.c    |  5 ++++-
 xen/arch/x86/traps.c      | 10 +++++++---
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/xen/arch/x86/cpu/common.c b/xen/arch/x86/cpu/common.c
index 1b33f1ed71..7b093cb421 100644
--- a/xen/arch/x86/cpu/common.c
+++ b/xen/arch/x86/cpu/common.c
@@ -752,8 +752,9 @@ void load_system_tables(void)
 
        _set_tssldt_desc(gdt + TSS_ENTRY, (unsigned long)tss,
                         sizeof(*tss) - 1, SYS_DESC_tss_avail);
-       _set_tssldt_desc(compat_gdt + TSS_ENTRY, (unsigned long)tss,
-                        sizeof(*tss) - 1, SYS_DESC_tss_busy);
+       if ( IS_ENABLED(CONFIG_PV32) )
+               _set_tssldt_desc(compat_gdt + TSS_ENTRY, (unsigned long)tss,
+                                sizeof(*tss) - 1, SYS_DESC_tss_busy);
 
        per_cpu(full_gdt_loaded, cpu) = false;
        lgdt(&gdtr);
diff --git a/xen/arch/x86/desc.c b/xen/arch/x86/desc.c
index dfeb1beaa8..39080ca672 100644
--- a/xen/arch/x86/desc.c
+++ b/xen/arch/x86/desc.c
@@ -55,6 +55,7 @@ seg_desc_t boot_gdt[PAGE_SIZE / sizeof(seg_desc_t)] =
     [SEL2GDT(PER_CPU_SELECTOR)] =     { 0x0000910000000000 },
 };
 
+#ifdef CONFIG_PV32
 __section(".data.page_aligned") __aligned(PAGE_SIZE)
 seg_desc_t boot_compat_gdt[PAGE_SIZE / sizeof(seg_desc_t)] =
 {
@@ -83,6 +84,7 @@ seg_desc_t boot_compat_gdt[PAGE_SIZE / sizeof(seg_desc_t)] =
     /* 0xe060 - per-CPU entry (limit == cpu) */
     [SEL2GDT(PER_CPU_SELECTOR)] =     { 0x0000910000000000 },
 };
+#endif
 
 /*
  * Used by each CPU as it starts up, to enter C with a suitable %cs.
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index 09264b02d1..f9f63e496f 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -959,7 +959,8 @@ static void cpu_smpboot_free(unsigned int cpu, bool remove)
             free_domheap_page(mfn_to_page(mfn));
     }
 
-    FREE_XENHEAP_PAGE(per_cpu(compat_gdt, cpu));
+    if ( IS_ENABLED(CONFIG_PV32) )
+        FREE_XENHEAP_PAGE(per_cpu(compat_gdt, cpu));
 
     if ( remove )
     {
@@ -1001,6 +1002,7 @@ static int cpu_smpboot_alloc(unsigned int cpu)
     BUILD_BUG_ON(NR_CPUS > 0x10000);
     gdt[PER_CPU_GDT_ENTRY - FIRST_RESERVED_GDT_ENTRY].a = cpu;
 
+#ifdef CONFIG_PV32
     per_cpu(compat_gdt, cpu) = gdt = alloc_xenheap_pages(0, memflags);
     if ( gdt == NULL )
         goto out;
@@ -1008,6 +1010,7 @@ static int cpu_smpboot_alloc(unsigned int cpu)
         l1e_from_pfn(virt_to_mfn(gdt), __PAGE_HYPERVISOR_RW);
     memcpy(gdt, boot_compat_gdt, NR_RESERVED_GDT_PAGES * PAGE_SIZE);
     gdt[PER_CPU_GDT_ENTRY - FIRST_RESERVED_GDT_ENTRY].a = cpu;
+#endif
 
     if ( idt_tables[cpu] == NULL )
         idt_tables[cpu] = alloc_xenheap_pages(0, memflags);
diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index e838846c6b..0bcf554e93 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -100,8 +100,10 @@ static DEFINE_PER_CPU(unsigned long, last_extable_addr);
 
 DEFINE_PER_CPU_READ_MOSTLY(seg_desc_t *, gdt);
 DEFINE_PER_CPU_READ_MOSTLY(l1_pgentry_t, gdt_l1e);
+#ifdef CONFIG_PV32
 DEFINE_PER_CPU_READ_MOSTLY(seg_desc_t *, compat_gdt);
 DEFINE_PER_CPU_READ_MOSTLY(l1_pgentry_t, compat_gdt_l1e);
+#endif
 
 /* Master table, used by CPU0. */
 idt_entry_t __section(".bss.page_aligned") __aligned(PAGE_SIZE)
@@ -1999,7 +2001,8 @@ void __init init_idt_traps(void)
     idt_tables[0] = idt_table;
 
     this_cpu(gdt) = boot_gdt;
-    this_cpu(compat_gdt) = boot_compat_gdt;
+    if ( IS_ENABLED(CONFIG_PV32) )
+        this_cpu(compat_gdt) = boot_compat_gdt;
 }
 
 extern void (*const autogen_entrypoints[X86_NR_VECTORS])(void);
@@ -2030,8 +2033,9 @@ void __init trap_init(void)
     /* Cache {,compat_}gdt_l1e now that physically relocation is done. */
     this_cpu(gdt_l1e) =
         l1e_from_pfn(virt_to_mfn(boot_gdt), __PAGE_HYPERVISOR_RW);
-    this_cpu(compat_gdt_l1e) =
-        l1e_from_pfn(virt_to_mfn(boot_compat_gdt), __PAGE_HYPERVISOR_RW);
+    if ( IS_ENABLED(CONFIG_PV32) )
+        this_cpu(compat_gdt_l1e) =
+            l1e_from_pfn(virt_to_mfn(boot_compat_gdt), __PAGE_HYPERVISOR_RW);
 
     percpu_traps_init();
 
-- 
2.11.0