Re: [PATCH] x86: not overmap than end in init_memory_mapping - 64bit

[Yinghai Lu]

On Wed, Jul 9, 2008 at 1:34 AM, Ingo Molnar <mingo@xxxxxxx> wrote:
>
> * Ingo Molnar <mingo@xxxxxxx> wrote:
>
>> > handle head and tail that can not aligned to big pages.
>> >
>> > with this patch, on system that support gbpages
>> > change
>> > last_map_addr: 1080000000 end: 1078000000
>> > to
>> > last_map_addr: 1078000000 end: 1078000000
>> >
>> > Signed-off-by: Yinghai Lu <yhlu.kernel@xxxxxxxxx>
>>
>> applied to tip/x86/core, thanks Yinghai.
>
> found an early boot crash on a testbox:
>
> [    0.000000] last_pfn = 0x3fff0 max_arch_pfn = 0x3ffffffff
> [    0.000000] x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106
> [    0.000000] init_memory_mapping
> [    0.000000] kernel direct mapping tables up to 3fff0000 @ 8000-b000
> [    0.000000] last_map_addr: 40000000 end: 3fff0000
> [    0.000000] ACPI: RSDP 000F76F0, 0014 (r0 Nvidia)
> PANIC: early exception 0e rip 10:ffffffff803d3b8a error 0 cr2 ffff88003fff3040
> [    0.000000] Pid: 0, comm: swapper Not tainted 2.6.26-rc9-tip-00118-g95f03c7-dirty #16954
> [    0.000000]
> [    0.000000] Call Trace:
> [    0.000000]  [<ffffffff80c05196>] early_idt_handler+0x56/0x6a
> [    0.000000]  [<ffffffff803d3b8a>] ? acpi_tb_print_table_header+0xe/0xd5
> [    0.000000]  [<ffffffff803d3bfc>] ? acpi_tb_print_table_header+0x80/0xd5
> [    0.000000]  [<ffffffff803d42f4>] ? acpi_tb_scan_memory_for_rsdp+0xc8/0xd3
>
> i bisected it down to:
>
> |  a1007454854803f6fc63f0a881518cea87df6d9a is first bad commit
> |  commit a1007454854803f6fc63f0a881518cea87df6d9a
> |  Author: Yinghai Lu <yhlu.kernel@xxxxxxxxx>
> |  Date:   Tue Jul 8 01:43:27 2008 -0700
> |
> |      x86: not overmap more than the end of RAM in init_memory_mapping - 64bit
>
> with this config:
>
>  http://redhat.com/~mingo/misc/config-Wed_Jul__9_09_43_06_CEST_2008.bad
>
> crashlog:
>
>  http://redhat.com/~mingo/misc/crashlog-Wed_Jul__9_09_43_06_CEST_2008.bad
>
> i've pushed the failing tree out to tip/tmp.x86.Jul__9_09_43
>
> reverting the commit solves the crash. The crash seems to be because
> ACPI is unable to access that memory range. (perhaps early_ioremap
> fails?)

system with less than 4g?

please test attached patch
[PATCH] x86: make max_pfn cover acpi table below 4g

YH
[PATCH] x86: make max_pfn cover acpi table below 4g

when system have 4g less ram installed, and acpi table sit
near end of ram. make max_pfn cover them too.
so 64bit kernel don't need to mess up fixmap.

Signed-off-by: Yinghai Lu <yhlu.kernel@xxxxxxxxx>

---
 arch/x86/kernel/e820.c  |   18 ++++++++++++------
 arch/x86/kernel/setup.c |   13 +++----------
 include/asm-x86/e820.h  |    2 +-
 3 files changed, 16 insertions(+), 17 deletions(-)

Index: linux-2.6/arch/x86/kernel/e820.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/e820.c
+++ linux-2.6/arch/x86/kernel/e820.c
@@ -1056,12 +1056,20 @@ unsigned long __initdata end_user_pfn =
 /*
  * Find the highest page frame number we have available
  */
-unsigned long __init e820_end_of_ram(void)
+unsigned long __init e820_end(void)
 {
-	unsigned long last_pfn;
+	int i;
+	unsigned long last_pfn = 0;
 	unsigned long max_arch_pfn = MAX_ARCH_PFN;
 
-	last_pfn = find_max_pfn_with_active_regions();
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		unsigned long end_pfn;
+
+		end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
+		if (end_pfn > last_pfn)
+			last_pfn = end_pfn;
+	}
 
 	if (last_pfn > max_arch_pfn)
 		last_pfn = max_arch_pfn;
@@ -1192,9 +1200,7 @@ static int __init parse_memmap_opt(char
 		 * the real mem size before original memory map is
 		 * reset.
 		 */
-		e820_register_active_regions(0, 0, -1UL);
-		saved_max_pfn = e820_end_of_ram();
-		remove_all_active_ranges();
+		saved_max_pfn = e820_end();
 #endif
 		e820.nr_map = 0;
 		userdef = 1;
Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -714,22 +714,18 @@ void __init setup_arch(char **cmdline_p)
 	early_gart_iommu_check();
 #endif
 
-	e820_register_active_regions(0, 0, -1UL);
 	/*
 	 * partially used pages are not usable - thus
 	 * we are rounding upwards:
 	 */
-	max_pfn = e820_end_of_ram();
+	max_pfn = e820_end();
 
 	/* preallocate 4k for mptable mpc */
 	early_reserve_e820_mpc_new();
 	/* update e820 for memory not covered by WB MTRRs */
 	mtrr_bp_init();
-	if (mtrr_trim_uncached_memory(max_pfn)) {
-		remove_all_active_ranges();
-		e820_register_active_regions(0, 0, -1UL);
-		max_pfn = e820_end_of_ram();
-	}
+	if (mtrr_trim_uncached_memory(max_pfn))
+		max_pfn = e820_end();
 
 #ifdef CONFIG_X86_32
 	/* max_low_pfn get updated here */
@@ -772,9 +768,6 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	acpi_boot_table_init();
 
-	/* Remove active ranges so rediscovery with NUMA-awareness happens */
-	remove_all_active_ranges();
-
 #ifdef CONFIG_ACPI_NUMA
 	/*
 	 * Parse SRAT to discover nodes.
Index: linux-2.6/include/asm-x86/e820.h
===================================================================
--- linux-2.6.orig/include/asm-x86/e820.h
+++ linux-2.6/include/asm-x86/e820.h
@@ -99,7 +99,7 @@ extern void free_early(u64 start, u64 en
 extern void early_res_to_bootmem(u64 start, u64 end);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 
-extern unsigned long e820_end_of_ram(void);
+extern unsigned long e820_end(void);
 extern int e820_find_active_region(const struct e820entry *ei,
 				  unsigned long start_pfn,
 				  unsigned long last_pfn,