x86/irq: Track if IRQ was found in PIR during initial loop (to load PIR vals)

Track whether or not at least one IRQ was found in PIR during the initial
loop to load PIR chunks from memory.  Doing so generates slightly better
code (arguably) for processing the for-loop of XCHGs, especially for the
case where there are no pending IRQs.

Note, while PIR can be modified between the initial load and the XCHG, it
can only _gain_ new IRQs, i.e. there is no danger of a false positive due
to the final version of pir_copy[] being empty.

Opportunistically convert the boolean to an "unsigned long" and compute
the effective boolean result via bitwise-OR.  Some compilers, e.g.
clang-14, need the extra "hint" to elide conditional branches.

Opportunistically rename the variable in anticipation of moving the PIR
accesses to a common helper that can be shared by posted MSIs and KVM.

Old:
   <+74>:	test   %rdx,%rdx
   <+77>:	je     0xffffffff812bbeb0 <handle_pending_pir+144>
   <pir[0]>
   <+88>:	mov    $0x1,%dl>
   <+90>:	test   %rsi,%rsi
   <+93>:	je     0xffffffff812bbe8c <handle_pending_pir+108>
   <pir[1]>
   <+106>:	mov    $0x1,%dl
   <+108>:	test   %rcx,%rcx
   <+111>:	je     0xffffffff812bbe9e <handle_pending_pir+126>
   <pir[2]>
   <+124>:	mov    $0x1,%dl
   <+126>:	test   %rax,%rax
   <+129>:	je     0xffffffff812bbeb9 <handle_pending_pir+153>
   <pir[3]>
   <+142>:	jmp    0xffffffff812bbec1 <handle_pending_pir+161>
   <+144>:	xor    %edx,%edx
   <+146>:	test   %rsi,%rsi
   <+149>:	jne    0xffffffff812bbe7f <handle_pending_pir+95>
   <+151>:	jmp    0xffffffff812bbe8c <handle_pending_pir+108>
   <+153>:	test   %dl,%dl
   <+155>:	je     0xffffffff812bbf8e <handle_pending_pir+366>

New:
   <+74>:	mov    %rax,%r8
   <+77>:	or     %rcx,%r8
   <+80>:	or     %rdx,%r8
   <+83>:	or     %rsi,%r8
   <+86>:	setne  %bl
   <+89>:	je     0xffffffff812bbf88 <handle_pending_pir+360>
   <+95>:	test   %rsi,%rsi
   <+98>:	je     0xffffffff812bbe8d <handle_pending_pir+109>
   <pir[0]>
   <+109>:	test   %rdx,%rdx
   <+112>:	je     0xffffffff812bbe9d <handle_pending_pir+125>
   <pir[1]>
   <+125>:	test   %rcx,%rcx
   <+128>:	je     0xffffffff812bbead <handle_pending_pir+141>
   <pir[2]>
   <+141>:	test   %rax,%rax
   <+144>:	je     0xffffffff812bbebd <handle_pending_pir+157>
   <pir[3]>

Link: https://lore.kernel.org/r/20250401163447.846608-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 6cd5d2d6c58af6b2b17e69195a33928b937e5e9d..6d2c8894877e86a089d8119040e48e9973defb09 100644 (file)
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -414,27 +414,28 @@ void intel_posted_msi_init(void)
  */
 static __always_inline bool handle_pending_pir(u64 *pir, struct pt_regs *regs)
 {
+       unsigned long pir_copy[4], pending = 0;
        int i, vec = FIRST_EXTERNAL_VECTOR;
-       unsigned long pir_copy[4];
-       bool handled = false;
 
-       for (i = 0; i < 4; i++)
+       for (i = 0; i < 4; i++) {
                pir_copy[i] = READ_ONCE(pir[i]);
+               pending |= pir_copy[i];
+       }
+
+       if (!pending)
+               return false;
 
        for (i = 0; i < 4; i++) {
                if (!pir_copy[i])
                        continue;
 
                pir_copy[i] = arch_xchg(&pir[i], 0);
-               handled = true;
        }
 
-       if (handled) {
-               for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
-                       call_irq_handler(vec, regs);
-       }
+       for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
+               call_irq_handler(vec, regs);
 
-       return handled;
+       return true;
 }
 
 /*