x86: 64 bits: shrink and align IRQ stubs

Move the IRQ stub generation to assembly to simplify it and for
consistency with 32 bits.  Doing it in a C file with asm() statements
doesn't help clarity, and it prevents some optimizations.

Shrink the IRQ stubs down to just over four bytes per (we fit seven
into a 32-byte chunk.)  This shrinks the total icache consumption of
the IRQ stubs down to an even kilobyte, if all of them are in active
use.

The downside is that we end up with a double jump, which could have a
negative effect on some pipelines.  The double jump is always inside
the same cacheline on any modern chips.

To get the most effect, cache-align the IRQ stubs.

This makes the 64-bit code match changes already done to the 32-bit
code, and should open up irqinit*.c for unification.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>

2 files changed, 45 insertions, 69 deletions

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b86f332c96a6..9b2aeaac9a6b 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -627,6 +627,46 @@ END(stub_rt_sigreturn)
    vector already pushed) */
 #define XCPT_FRAME _frame ORIG_RAX
 
+/*
+ * Build the entry stubs and pointer table with some assembler magic.
+ * We pack 7 stubs into a single 32-byte chunk, which will fit in a
+ * single cache line on all modern x86 implementations.
+ */
+        .section .init.rodata,"a"
+ENTRY(interrupt)
+        .text
+        .p2align 5
+        .p2align CONFIG_X86_L1_CACHE_SHIFT
+ENTRY(irq_entries_start)
+        INTR_FRAME
+vector=FIRST_EXTERNAL_VECTOR
+.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+        .balign 32
+  .rept 7
+    .if vector < NR_VECTORS
+      .if vector != FIRST_EXTERNAL_VECTOR
+        CFI_ADJUST_CFA_OFFSET -8
+      .endif
+1:      pushq $(~vector+0x80)   /* Note: always in signed byte range */
+        CFI_ADJUST_CFA_OFFSET 8
+      .if ((vector-FIRST_EXTERNAL_VECTOR)%7) != 6
+        jmp 2f
+      .endif
+      .previous
+        .quad 1b
+      .text
+vector=vector+1
+    .endif
+  .endr
+2:      jmp common_interrupt
+.endr
+        CFI_ENDPROC
+END(irq_entries_start)
+
+.previous
+END(interrupt)
+.previous
+
 /* 
  * Interrupt entry/exit.
  *
@@ -635,11 +675,12 @@ END(stub_rt_sigreturn)
  * Entry runs with interrupts off.      
  */ 
 
-/* 0(%rsp): interrupt number */ 
+/* 0(%rsp): ~(interrupt number)+0x80 */ 
         .macro interrupt func
+        addq $-0x80,(%rsp)              /* Adjust vector to [-256,-1] range */
         cld
         SAVE_ARGS
-        leaq -ARGOFFSET(%rsp),%rdi      # arg1 for handler
+        leaq -ARGOFFSET(%rsp),%rdi      /* arg1 for handler */
         pushq %rbp
         /*
          * Save rbp twice: One is for marking the stack frame, as usual, and the
@@ -670,7 +711,8 @@ END(stub_rt_sigreturn)
         call \func
         .endm
 
-ENTRY(common_interrupt)
+        .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
         XCPT_FRAME
         interrupt do_IRQ
         /* 0(%rsp): oldrsp-ARGOFFSET */
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index ff0235391285..8670b3ce626e 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -24,41 +24,6 @@
 #include <asm/i8259.h>
 
 /*
- * Common place to define all x86 IRQ vectors
- *
- * This builds up the IRQ handler stubs using some ugly macros in irq.h
- *
- * These macros create the low-level assembly IRQ routines that save
- * register context and call do_IRQ(). do_IRQ() then does all the
- * operations that are needed to keep the AT (or SMP IOAPIC)
- * interrupt-controller happy.
- */
-
-#define IRQ_NAME2(nr) nr##_interrupt(void)
-#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
-
-/*
- *      SMP has a few special interrupts for IPI messages
- */
-
-#define BUILD_IRQ(nr)                           \
-        asmlinkage void IRQ_NAME(nr);           \
-        asm("\n.text\n.p2align\n"               \
-            "IRQ" #nr "_interrupt:\n\t"         \
-            "push $~(" #nr ") ; "               \
-            "jmp common_interrupt\n"            \
-            ".previous");
-
-#define BI(x,y) \
-        BUILD_IRQ(x##y)
-
-#define BUILD_16_IRQS(x) \
-        BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
-        BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
-        BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
-        BI(x,c) BI(x,d) BI(x,e) BI(x,f)
-
-/*
  * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
  * (these are usually mapped to vectors 0x30-0x3f)
  */
@@ -73,37 +38,6 @@
  *
  * (these are usually mapped into the 0x30-0xff vector range)
  */
-                                      BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
-BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
-BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
-BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
-
-#undef BUILD_16_IRQS
-#undef BI
-
-
-#define IRQ(x,y) \
-        IRQ##x##y##_interrupt
-
-#define IRQLIST_16(x) \
-        IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
-        IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
-        IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
-        IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
-
-/* for the irq vectors */
-static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
-                                          IRQLIST_16(0x2), IRQLIST_16(0x3),
-        IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
-        IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
-        IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
-};
-
-#undef IRQ
-#undef IRQLIST_16
-
-
-
 
 /*
  * IRQ2 is cascade interrupt to second interrupt controller