x86: Use find_e820() instead of hard coded trampoline address

Jens found the following crash/regression:

[    0.000000] found SMP MP-table at [ffff8800000fdd80] fdd80
[    0.000000] Kernel panic - not syncing: Overlapping early reservations 12-f011 MP-table mpc to 0-fff BIOS data page

and

[    0.000000] Kernel panic - not syncing: Overlapping early reservations 12-f011 MP-table mpc to 6000-7fff TRAMPOLINE

and bisected it to b24c2a9 ("x86: Move find_smp_config()
earlier and avoid bootmem usage").

It turns out the BIOS is using the first 64k for mptable,
without reserving it.

So try to find good range for the real-mode trampoline instead of
hard coding it, in case some bios tries to use that range for sth.

Reported-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Tested-by: Jens Axboe <jens.axboe@oracle.com>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
LKML-Reference: <4B21630A.6000308@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

6 files changed, 27 insertions, 24 deletions

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d17d482a04f4..f50447d961c0 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -732,7 +732,16 @@ struct early_res {
         char overlap_ok;
 };
 static struct early_res early_res[MAX_EARLY_RES] __initdata = {
-        { 0, PAGE_SIZE, "BIOS data page" },     /* BIOS data page */
+        { 0, PAGE_SIZE, "BIOS data page", 1 },  /* BIOS data page */
+#ifdef CONFIG_X86_32
+        /*
+         * But first pinch a few for the stack/trampoline stuff
+         * FIXME: Don't need the extra page at 4K, but need to fix
+         * trampoline before removing it. (see the GDT stuff)
+         */
+        { PAGE_SIZE, PAGE_SIZE, "EX TRAMPOLINE", 1 },
+#endif
+
         {}
 };
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 4f8e2507e8f3..5051b94c9069 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,8 +29,6 @@ static void __init i386_default_early_setup(void)
 
 void __init i386_start_kernel(void)
 {
-        reserve_trampoline_memory();
-
         reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 0b06cd778fd9..b5a9896ca1e7 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -98,8 +98,6 @@ void __init x86_64_start_reservations(char *real_mode_data)
 {
         copy_bootdata(__va(real_mode_data));
 
-        reserve_trampoline_memory();
-
         reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 35a57c963df9..40b54ceb68b5 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -945,9 +945,6 @@ void __init early_reserve_e820_mpc_new(void)
 {
         if (enable_update_mptable && alloc_mptable) {
                 u64 startt = 0;
-#ifdef CONFIG_X86_TRAMPOLINE
-                startt = TRAMPOLINE_BASE;
-#endif
                 mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4);
         }
 }
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 946a311a25c9..f7b8b9894b22 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -73,6 +73,7 @@
 
 #include <asm/mtrr.h>
 #include <asm/apic.h>
+#include <asm/trampoline.h>
 #include <asm/e820.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
@@ -875,6 +876,13 @@ void __init setup_arch(char **cmdline_p)
 
         reserve_brk();
 
+        /*
+         * Find and reserve possible boot-time SMP configuration:
+         */
+        find_smp_config();
+
+        reserve_trampoline_memory();
+
 #ifdef CONFIG_ACPI_SLEEP
         /*
          * Reserve low memory region for sleep support.
@@ -921,11 +929,6 @@ void __init setup_arch(char **cmdline_p)
 
         early_acpi_boot_init();
 
-        /*
-         * Find and reserve possible boot-time SMP configuration:
-         */
-        find_smp_config();
-
 #ifdef CONFIG_ACPI_NUMA
         /*
          * Parse SRAT to discover nodes.
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index cd022121cab6..c652ef62742d 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -12,21 +12,19 @@
 #endif
 
 /* ready for x86_64 and x86 */
-unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE);
+unsigned char *__trampinitdata trampoline_base;
 
 void __init reserve_trampoline_memory(void)
 {
-#ifdef CONFIG_X86_32
-        /*
-         * But first pinch a few for the stack/trampoline stuff
-         * FIXME: Don't need the extra page at 4K, but need to fix
-         * trampoline before removing it. (see the GDT stuff)
-         */
-        reserve_early(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE");
-#endif
+        unsigned long mem;
+
         /* Has to be in very low memory so we can execute real-mode AP code. */
-        reserve_early(TRAMPOLINE_BASE, TRAMPOLINE_BASE + TRAMPOLINE_SIZE,
-                        "TRAMPOLINE");
+        mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE);
+        if (mem == -1L)
+                panic("Cannot allocate trampoline\n");
+
+        trampoline_base = __va(mem);
+        reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE");
 }
 
 /*