[PATCH] x86: fix broken SMP boot sequence

Recent GDT changes broke the SMP boot sequence if the booting CPU is
numbered anything other than zero.  There's also a subtle source of error
in that the boot time CPU now uses cpu_gdt_table (which is actually the GDT
for booting CPUs in head.S).  This patch fixes both problems by making GDT
descriptors themselves allocated from a per_cpu area and switching to them
in cpu_init(), which now means that cpu_gdt_table is exclusively used for
booting CPUs again.

Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Matt Tolentino <metolent@snoqualmie.dp.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

6 files changed, 39 insertions, 21 deletions

diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 7eb9213..4ecd4b3 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -4,6 +4,7 @@
 #include <linux/smp.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
+#include <linux/bootmem.h>
 #include <asm/semaphore.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
@@ -18,6 +19,9 @@
 
 #include "cpu.h"
 
+DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
+EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr);
+
 DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]);
 EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack);
 
@@ -571,8 +575,9 @@ void __devinit cpu_init(void)
 	int cpu = smp_processor_id();
 	struct tss_struct * t = &per_cpu(init_tss, cpu);
 	struct thread_struct *thread = &current->thread;
-	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+	struct desc_struct *gdt;
 	__u32 stk16_off = (__u32)&per_cpu(cpu_16bit_stack, cpu);
+	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
 
 	if (cpu_test_and_set(cpu, cpu_initialized)) {
 		printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
@@ -590,6 +595,25 @@ void __devinit cpu_init(void)
 	}
 
 	/*
+	 * This is a horrible hack to allocate the GDT.  The problem
+	 * is that cpu_init() is called really early for the boot CPU
+	 * (and hence needs bootmem) but much later for the secondary
+	 * CPUs, when bootmem will have gone away
+	 */
+	if (NODE_DATA(0)->bdata->node_bootmem_map) {
+		gdt = (struct desc_struct *)alloc_bootmem_pages(PAGE_SIZE);
+		/* alloc_bootmem_pages panics on failure, so no check */
+		memset(gdt, 0, PAGE_SIZE);
+	} else {
+		gdt = (struct desc_struct *)get_zeroed_page(GFP_KERNEL);
+		if (unlikely(!gdt)) {
+			printk(KERN_CRIT "CPU%d failed to allocate GDT\n", cpu);
+			for (;;)
+				local_irq_enable();
+		}
+	}
+
+	/*
 	 * Initialize the per-CPU GDT with the boot GDT,
 	 * and set up the GDT descriptor:
 	 */
@@ -601,10 +625,10 @@ void __devinit cpu_init(void)
 		((((__u64)stk16_off) << 32) & 0xff00000000000000ULL) |
 		(CPU_16BIT_STACK_SIZE - 1);
 
-	cpu_gdt_descr[cpu].size = GDT_SIZE - 1;
- 	cpu_gdt_descr[cpu].address = (unsigned long)gdt;
+	cpu_gdt_descr->size = GDT_SIZE - 1;
+ 	cpu_gdt_descr->address = (unsigned long)gdt;
 
-	load_gdt(&cpu_gdt_descr[cpu]);
+	load_gdt(cpu_gdt_descr);
 	load_idt(&idt_descr);
 
 	/*
diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c
index ecad519..e3e42fd 100644
--- a/arch/i386/kernel/efi.c
+++ b/arch/i386/kernel/efi.c
@@ -103,17 +103,19 @@ static void efi_call_phys_prelog(void)
 	 */
 	local_flush_tlb();
 
-	cpu_gdt_descr[0].address = __pa(cpu_gdt_descr[0].address);
-	load_gdt((struct Xgt_desc_struct *) __pa(&cpu_gdt_descr[0]));
+	per_cpu(cpu_gdt_descr, 0).address =
+				 __pa(per_cpu(cpu_gdt_descr, 0).address);
+	load_gdt((struct Xgt_desc_struct *)__pa(&per_cpu(cpu_gdt_descr, 0)));
 }
 
 static void efi_call_phys_epilog(void)
 {
 	unsigned long cr4;
 
-	cpu_gdt_descr[0].address =
-		(unsigned long) __va(cpu_gdt_descr[0].address);
-	load_gdt(&cpu_gdt_descr[0]);
+	per_cpu(cpu_gdt_descr, 0).address =
+			(unsigned long)__va(per_cpu(cpu_gdt_descr, 0).address);
+	load_gdt((struct Xgt_desc_struct *)__va(&per_cpu(cpu_gdt_descr, 0)));
+
 	cr4 = read_cr4();
 
 	if (cr4 & X86_CR4_PSE) {
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index 2bee649..e0b7c63 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -534,5 +534,3 @@ ENTRY(cpu_gdt_table)
 	.quad 0x0000000000000000	/* 0xf0 - unused */
 	.quad 0x0000000000000000	/* 0xf8 - GDT entry 31: double-fault TSS */
 
-	/* Be sure this is zeroed to avoid false validations in Xen */
-	.fill PAGE_SIZE_asm / 8 - GDT_ENTRIES,8,0
diff --git a/arch/i386/kernel/i386_ksyms.c b/arch/i386/kernel/i386_ksyms.c
index 3999bec..0553250 100644
--- a/arch/i386/kernel/i386_ksyms.c
+++ b/arch/i386/kernel/i386_ksyms.c
@@ -3,8 +3,6 @@
 #include <asm/checksum.h>
 #include <asm/desc.h>
 
-EXPORT_SYMBOL_GPL(cpu_gdt_descr);
-
 EXPORT_SYMBOL(__down_failed);
 EXPORT_SYMBOL(__down_failed_interruptible);
 EXPORT_SYMBOL(__down_failed_trylock);
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index fb00ab7..eba7f53 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -898,12 +898,6 @@ static int __devinit do_boot_cpu(int apicid, int cpu)
 	unsigned long start_eip;
 	unsigned short nmi_high = 0, nmi_low = 0;
 
-	if (!cpu_gdt_descr[cpu].address &&
-	    !(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) {
-		printk("Failed to allocate GDT for CPU %d\n", cpu);
-		return 1;
-	}
-
 	++cpucount;
 
 	/*
diff --git a/include/asm-i386/desc.h b/include/asm-i386/desc.h
index 494e73b..89b8b82 100644
--- a/include/asm-i386/desc.h
+++ b/include/asm-i386/desc.h
@@ -24,11 +24,13 @@ struct Xgt_desc_struct {
 	unsigned short pad;
 } __attribute__ ((packed));
 
-extern struct Xgt_desc_struct idt_descr, cpu_gdt_descr[NR_CPUS];
+extern struct Xgt_desc_struct idt_descr;
+DECLARE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
+
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 {
-	return ((struct desc_struct *)cpu_gdt_descr[cpu].address);
+	return (struct desc_struct *)per_cpu(cpu_gdt_descr, cpu).address;
 }
 
 #define load_TR_desc() __asm__ __volatile__("ltr %w0"::"q" (GDT_ENTRY_TSS*8))