[PATCH] smp: Replace QEMU SMP init assembler code with C; run only in 32bit mode.

[Kevin O'Connor]

Change the multi-processor init code to trampoline into 32bit mode on
each of the additional processors.  Implement an atomic lock so that
each processor performs its initialization serially.

Signed-off-by: Kevin O'Connor <kevin(a)koconnor.net>
---
 Makefile        |   3 +-
 src/config.h    |   1 +
 src/fw/smp.c    | 101 ++++++++++++++++++++++++++++----------------------------
 src/romlayout.S |  23 +++++++++++++
 src/util.h      |   1 -
 5 files changed, 75 insertions(+), 54 deletions(-)

diff --git a/Makefile b/Makefile
index 78b598e..fb4e683 100644
--- a/Makefile
+++ b/Makefile
@@ -29,7 +29,6 @@ LD32BIT_FLAG:=-melf_i386
 # Source files
 SRCBOTH=misc.c stacks.c output.c string.c x86.c block.c cdrom.c mouse.c kbd.c \
     serial.c clock.c resume.c pnpbios.c vgahooks.c pcibios.c apm.c \
-    fw/smp.c \
     hw/pci.c hw/timer.c hw/rtc.c hw/dma.c hw/pic.c hw/ps2port.c hw/serialio.c \
     hw/usb.c hw/usb-uhci.c hw/usb-ohci.c hw/usb-ehci.c \
     hw/usb-hid.c hw/usb-msc.c hw/usb-uas.c \
@@ -41,7 +40,7 @@ SRC32FLAT=$(SRCBOTH) post.c memmap.c malloc.c pmm.c romfile.c
optionroms.c \
     boot.c bootsplash.c jpeg.c bmp.c \
     hw/ahci.c hw/pvscsi.c hw/usb-xhci.c hw/usb-hub.c \
     fw/coreboot.c fw/lzmadecode.c fw/csm.c fw/biostables.c \
-    fw/paravirt.c fw/shadow.c fw/pciinit.c fw/smm.c fw/mtrr.c fw/xen.c \
+    fw/paravirt.c fw/shadow.c fw/pciinit.c fw/smm.c fw/smp.c fw/mtrr.c fw/xen.c \
     fw/acpi.c fw/mptable.c fw/pirtable.c fw/smbios.c fw/romfile_loader.c
 SRC32SEG=string.c output.c pcibios.c apm.c stacks.c hw/pci.c hw/serialio.c
 DIRS=src src/hw src/fw vgasrc
diff --git a/src/config.h b/src/config.h
index 6f1a5b9..6da067d 100644
--- a/src/config.h
+++ b/src/config.h
@@ -95,6 +95,7 @@
 #define DEBUG_ISR_hwpic1 5
 #define DEBUG_ISR_hwpic2 5
 #define DEBUG_HDL_smi 9
+#define DEBUG_HDL_smp 1
 #define DEBUG_HDL_pnp 1
 #define DEBUG_HDL_pmm 1
 #define DEBUG_HDL_pcibios 9
diff --git a/src/fw/smp.c b/src/fw/smp.c
index 38fe383..c8b48b6 100644
--- a/src/fw/smp.c
+++ b/src/fw/smp.c
@@ -1,4 +1,4 @@
-// CPU count detection
+// QEMU multi-CPU initialization code
 //
 // Copyright (C) 2008  Kevin O'Connor <kevin(a)koconnor.net>
 // Copyright (C) 2006 Fabrice Bellard
@@ -20,8 +20,8 @@
 
 #define APIC_ENABLED 0x0100
 
-struct { u32 ecx, eax, edx; } smp_mtrr[32] VARFSEG;
-u32 smp_mtrr_count VARFSEG;
+static struct { u32 index; u64 val; } smp_mtrr[32];
+static u32 smp_mtrr_count;
 
 void
 wrmsr_smp(u32 index, u64 val)
@@ -31,52 +31,36 @@ wrmsr_smp(u32 index, u64 val)
         warn_noalloc();
         return;
     }
-    smp_mtrr[smp_mtrr_count].ecx = index;
-    smp_mtrr[smp_mtrr_count].eax = val;
-    smp_mtrr[smp_mtrr_count].edx = val >> 32;
+    smp_mtrr[smp_mtrr_count].index = index;
+    smp_mtrr[smp_mtrr_count].val = val;
     smp_mtrr_count++;
 }
 
-u32 CountCPUs VARFSEG;
 u32 MaxCountCPUs;
+static u32 CountCPUs;
+u32 SMPLock __VISIBLE;
+u32 SMPStack __VISIBLE;
 // 256 bits for the found APIC IDs
-u32 FoundAPICIDs[256/32] VARFSEG;
-extern void smp_ap_boot_code(void);
-ASM16(
-    "  .global smp_ap_boot_code\n"
-    "smp_ap_boot_code:\n"
+static u32 FoundAPICIDs[256/32];
 
-    // Setup data segment
-    "  movw $" __stringify(SEG_BIOS) ", %ax\n"
-    "  movw %ax, %ds\n"
+void VISIBLE32FLAT
+handle_smp(void)
+{
+    dprintf(DEBUG_HDL_smp, "handle_smp\n");
 
     // MTRR setup
-    "  movl $smp_mtrr, %esi\n"
-    "  movl smp_mtrr_count, %ebx\n"
-    "1:testl %ebx, %ebx\n"
-    "  jz 2f\n"
-    "  movl 0(%esi), %ecx\n"
-    "  movl 4(%esi), %eax\n"
-    "  movl 8(%esi), %edx\n"
-    "  wrmsr\n"
-    "  addl $12, %esi\n"
-    "  decl %ebx\n"
-    "  jmp 1b\n"
-    "2:\n"
-
-    // get apic ID on EBX, set bit on FoundAPICIDs
-    "  movl $1, %eax\n"
-    "  cpuid\n"
-    "  shrl $24, %ebx\n"
-    "  lock btsl %ebx, FoundAPICIDs\n"
-
-    // Increment the cpu counter
-    "  lock incl CountCPUs\n"
-
-    // Halt the processor.
-    "1:hlt\n"
-    "  jmp 1b\n"
-    );
+    int i;
+    for (i=0; i<smp_mtrr_count; i++)
+        wrmsr(smp_mtrr[i].index, smp_mtrr[i].val);
+
+    // Set bit on FoundAPICIDs
+    u32 eax, ebx, ecx, cpuid_features;
+    cpuid(1, &eax, &ebx, &ecx, &cpuid_features);
+    u8 apic_id = ebx>>24;
+    FoundAPICIDs[apic_id/32] |= (1 << (apic_id % 32));
+
+    CountCPUs++;
+}
 
 int apic_id_is_present(u8 apic_id)
 {
@@ -104,15 +88,14 @@ smp_setup(void)
     // mark the BSP initial APIC ID as found, too:
     u8 apic_id = ebx>>24;
     FoundAPICIDs[apic_id/32] |= (1 << (apic_id % 32));
-
-    // Init the counter.
-    writel(&CountCPUs, 1);
+    CountCPUs = 1;
 
     // Setup jump trampoline to counter code.
     u64 old = *(u64*)BUILD_AP_BOOT_ADDR;
-    // ljmpw $SEG_BIOS, $(smp_ap_boot_code - BUILD_BIOS_ADDR)
+    // ljmpw $SEG_BIOS, $(entry_smp - BUILD_BIOS_ADDR)
+    extern void entry_smp(void);
     u64 new = (0xea | ((u64)SEG_BIOS<<24)
-               | (((u32)smp_ap_boot_code - BUILD_BIOS_ADDR) << 8));
+               | (((u32)entry_smp - BUILD_BIOS_ADDR) << 8));
     *(u64*)BUILD_AP_BOOT_ADDR = new;
 
     // enable local APIC
@@ -125,6 +108,9 @@ smp_setup(void)
     /* Set LINT1 as NMI, level triggered */
     writel(APIC_LINT1, 0x8400);
 
+    // Init the lock.
+    writel(&SMPLock, 1);
+
     // broadcast SIPI
     barrier();
     writel(APIC_ICR_LOW, 0x000C4500);
@@ -132,9 +118,22 @@ smp_setup(void)
     writel(APIC_ICR_LOW, 0x000C4600 | sipi_vector);
 
     // Wait for other CPUs to process the SIPI.
-    u8 cmos_smp_count = rtc_read(CMOS_BIOS_SMP_COUNT);
-    while (cmos_smp_count + 1 != readl(&CountCPUs))
-        yield();
+    u8 cmos_smp_count = rtc_read(CMOS_BIOS_SMP_COUNT) + 1;
+    u32 lockval = 1;
+    while (cmos_smp_count != CountCPUs)
+        asm volatile(
+            // Store %esp value and unlock.
+            "  movl %%esp, %1\n"
+            "  movl $0, %0\n"
+            // Reacquire lock.
+            "1:rep ; nop\n"
+            "  xorl %2, %2\n"
+            "  lock cmpxchgl %3, %0\n"
+            "  jnz 1b\n"
+            : "+m" (SMPLock), "+m" (SMPStack), "=&a"
(eax)
+            : "r" (lockval)
+            : "cc", "memory");
+    yield();
 
     // Restore memory.
     *(u64*)BUILD_AP_BOOT_ADDR = old;
@@ -143,6 +142,6 @@ smp_setup(void)
     if (!MaxCountCPUs || MaxCountCPUs < CountCPUs)
         MaxCountCPUs = CountCPUs;
 
-    dprintf(1, "Found %d cpu(s) max supported %d cpu(s)\n",
readl(&CountCPUs),
-        MaxCountCPUs);
+    dprintf(1, "Found %d cpu(s) max supported %d cpu(s)\n", CountCPUs,
+            MaxCountCPUs);
 }
diff --git a/src/romlayout.S b/src/romlayout.S
index 0d6af39..bee3943 100644
--- a/src/romlayout.S
+++ b/src/romlayout.S
@@ -274,6 +274,29 @@ entry_smi:
         rsm
         .code16gcc
 
+// Entry point for QEMU smp sipi interrupts.
+        DECLFUNC entry_smp
+entry_smp:
+        // Transition to 32bit mode.
+        movl $1f + BUILD_BIOS_ADDR, %edx
+        jmp transition32
+        .code32
+        // Acquire lock
+1:      movl $1, %ecx
+2:      xorl %eax, %eax
+        lock cmpxchgl %ecx, SMPLock
+        jz 3f
+        rep nop
+        jmp 2b
+        // Setup stack and call handle_smp
+3:      movl SMPStack, %esp
+        calll _cfunc32flat_handle_smp - BUILD_BIOS_ADDR
+        // Release lock and halt processor.
+        movl $0, SMPLock
+4:      hlt
+        jmp 4b
+        .code16gcc
+
 // Resume (and reboot) entry point - called from entry_post
         DECLFUNC entry_resume
 entry_resume:
diff --git a/src/util.h b/src/util.h
index b54271b..8c794c4 100644
--- a/src/util.h
+++ b/src/util.h
@@ -126,7 +126,6 @@ void smm_device_setup(void);
 void smm_setup(void);
 
 // fw/smp.c
-extern u32 CountCPUs;
 extern u32 MaxCountCPUs;
 void wrmsr_smp(u32 index, u64 val);
 void smp_setup(void);
-- 
1.9.3