x86/boot: Fix early exception handling with CONFIG_PERF_COUNTERS

The PERFC_INCR() macro uses current->processor, but current is not valid
during early boot.  This causes the following crash to occur if
e.g. rdmsr_safe() has to recover from a #GP fault.

  (XEN) Early fatal page fault at e008:ffff82d0803b1a39 (cr2=0000000000000004, ec=0000)
  (XEN) ----[ Xen-4.14-unstable  x86_64  debug=y   Not tainted ]----
  (XEN) CPU:    0
  (XEN) RIP:    e008:[<ffff82d0803b1a39>] x86_64/entry.S#handle_exception_saved+0x64/0xb8
  ...
  (XEN) Xen call trace:
  (XEN)    [<ffff82d0803b1a39>] R x86_64/entry.S#handle_exception_saved+0x64/0xb8
  (XEN)    [<ffff82d0806394fe>] F __start_xen+0x2cd/0x2980
  (XEN)    [<ffff82d0802000ec>] F __high_start+0x4c/0x4e

Furthermore, the PERFC_INCR() macro is wildly inefficient.  There has been a
single caller for many releases now, so inline it and delete the macro
completely.

There is no need to reference current at all.  What is actually needed is the
per_cpu_offset which can be obtained directly from the top-of-stack block.
This simplifies the counter handling to 3 instructions and no spilling to the
stack at all.

The same breakage from above is now handled properly:

  (XEN) traps.c:1591: GPF (0000): ffff82d0806394fe [__start_xen+0x2cd/0x2980] -> ffff82d0803b3bfb

Reported-by: Julien Grall <jgrall@amazon.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Julien Grall <jgrall@amazon.com>
master commit: 615bfe42c6
master date: 2020-04-16 09:48:38 +0100

xen/arch/x86/x86_64/asm-offsets.c

@@ -112,6 +112,7 @@ void __dummy__(void)
     OFFSET(CPUINFO_guest_cpu_user_regs, struct cpu_info, guest_cpu_user_regs);
     OFFSET(CPUINFO_verw_sel, struct cpu_info, verw_sel);
     OFFSET(CPUINFO_current_vcpu, struct cpu_info, current_vcpu);
+    OFFSET(CPUINFO_per_cpu_offset, struct cpu_info, per_cpu_offset);
     OFFSET(CPUINFO_cr4, struct cpu_info, cr4);
     OFFSET(CPUINFO_xen_cr3, struct cpu_info, xen_cr3);
     OFFSET(CPUINFO_pv_cr3, struct cpu_info, pv_cr3);

xen/arch/x86/x86_64/entry.S

@@ -682,7 +682,11 @@ handle_exception_saved:
 1:      movq  %rsp,%rdi
         movzbl UREGS_entry_vector(%rsp),%eax
         leaq  exception_table(%rip),%rdx
-        PERFC_INCR(exceptions, %rax, %rbx)
+#ifdef CONFIG_PERF_COUNTERS
+        lea   per_cpu__perfcounters(%rip), %rcx
+        add   STACK_CPUINFO_FIELD(per_cpu_offset)(%r14), %rcx
+        incl  ASM_PERFC_exceptions * 4(%rcx, %rax, 4)
+#endif
         mov   (%rdx, %rax, 8), %rdx
         INDIRECT_CALL %rdx
         mov   %r15, STACK_CPUINFO_FIELD(xen_cr3)(%r14)

xen/include/asm-x86/asm_defns.h

@@ -334,22 +334,6 @@ static always_inline void stac(void)
 
 #endif
 
-#ifdef CONFIG_PERF_COUNTERS
-#define PERFC_INCR(_name,_idx,_cur)             \
-        pushq _cur;                             \
-        movslq VCPU_processor(_cur),_cur;       \
-        pushq %rdx;                             \
-        leaq __per_cpu_offset(%rip),%rdx;       \
-        movq (%rdx,_cur,8),_cur;                \
-        leaq per_cpu__perfcounters(%rip),%rdx;  \
-        addq %rdx,_cur;                         \
-        popq %rdx;                              \
-        incl ASM_PERFC_##_name*4(_cur,_idx,4);  \
-        popq _cur
-#else
-#define PERFC_INCR(_name,_idx,_cur)
-#endif
-
 /* Work around AMD erratum #88 */
 #define safe_swapgs                             \
         "mfence; swapgs;"