x86_32: trim memory by updating e820

when MTRRs are not covering the whole e820 table, we need to trim the
RAM and need to update e820.

reuse some code on 64-bit as well.

here need to add early_get_cap and use it in early_cpu_detect, and move
mtrr_bp_init early.

The code successfully trimmed the memory map on Justin's system:

from:

 [    0.000000]  BIOS-e820: 0000000100000000 - 000000022c000000 (usable)

to:

 [    0.000000]   modified: 0000000100000000 - 0000000228000000 (usable)
 [    0.000000]   modified: 0000000228000000 - 000000022c000000 (reserved)

According to Justin it makes quite a difference:

|  When I boot the box without any trimming it acts like a 286 or 386,
|  takes about 10 minutes to boot (using raptor disks).

Signed-off-by: Yinghai Lu <yinghai.lu@sun.com>
Tested-by: Justin Piszcz <jpiszcz@lucidpixels.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

6 files changed, 64 insertions, 10 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 50d564dabb13..fe3031d56431 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -583,7 +583,7 @@ and is between 256 and 4096 characters. It is defined in the file
                         See drivers/char/README.epca and
                         Documentation/digiepca.txt.
 
-        disable_mtrr_trim [X86-64, Intel only]
+        disable_mtrr_trim [X86, Intel and AMD only]
                         By default the kernel will trim any uncacheable
                         memory out of your available memory pool based on
                         MTRR settings.  This parameter disables that behavior,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 56cc341cc586..bba850b05d0e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -278,6 +278,33 @@ void __init cpu_detect(struct cpuinfo_x86 *c)
                         c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
         }
 }
+static void __cpuinit early_get_cap(struct cpuinfo_x86 *c)
+{
+        u32 tfms, xlvl;
+        int ebx;
+
+        memset(&c->x86_capability, 0, sizeof c->x86_capability);
+        if (have_cpuid_p()) {
+                /* Intel-defined flags: level 0x00000001 */
+                if (c->cpuid_level >= 0x00000001) {
+                        u32 capability, excap;
+                        cpuid(0x00000001, &tfms, &ebx, &excap, &capability);
+                        c->x86_capability[0] = capability;
+                        c->x86_capability[4] = excap;
+                }
+
+                /* AMD-defined flags: level 0x80000001 */
+                xlvl = cpuid_eax(0x80000000);
+                if ((xlvl & 0xffff0000) == 0x80000000) {
+                        if (xlvl >= 0x80000001) {
+                                c->x86_capability[1] = cpuid_edx(0x80000001);
+                                c->x86_capability[6] = cpuid_ecx(0x80000001);
+                        }
+                }
+
+        }
+
+}
 
 /* Do minimum CPU detection early.
    Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment.
@@ -306,6 +333,8 @@ static void __init early_cpu_detect(void)
                 early_init_intel(c);
                 break;
         }
+
+        early_get_cap(c);
 }
 
 static void __cpuinit generic_identify(struct cpuinfo_x86 * c)
@@ -485,7 +514,6 @@ void __init identify_boot_cpu(void)
         identify_cpu(&boot_cpu_data);
         sysenter_setup();
         enable_sep_cpu();
-        mtrr_bp_init();
 }
 
 void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index ccd36ed2187b..ac4b6338f3f4 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -624,7 +624,6 @@ static struct sysdev_driver mtrr_sysdev_driver = {
         .resume         = mtrr_restore,
 };
 
-#ifdef CONFIG_X86_64
 static int disable_mtrr_trim;
 
 static int __init disable_mtrr_trim_setup(char *str)
@@ -643,13 +642,10 @@ early_param("disable_mtrr_trim", disable_mtrr_trim_setup);
 #define Tom2Enabled (1U << 21)
 #define Tom2ForceMemTypeWB (1U << 22)
 
-static __init int amd_special_default_mtrr(unsigned long end_pfn)
+static __init int amd_special_default_mtrr(void)
 {
         u32 l, h;
 
-        /* Doesn't apply to memory < 4GB */
-        if (end_pfn <= (0xffffffff >> PAGE_SHIFT))
-                return 0;
         if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
                 return 0;
         if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
@@ -687,9 +683,14 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
          * Make sure we only trim uncachable memory on machines that
          * support the Intel MTRR architecture:
          */
+        if (!is_cpu(INTEL) || disable_mtrr_trim)
+                return 0;
         rdmsr(MTRRdefType_MSR, def, dummy);
         def &= 0xff;
-        if (!is_cpu(INTEL) || disable_mtrr_trim || def != MTRR_TYPE_UNCACHABLE)
+        if (def != MTRR_TYPE_UNCACHABLE)
+                return 0;
+
+        if (amd_special_default_mtrr())
                 return 0;
 
         /* Find highest cached pfn */
@@ -703,8 +704,14 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
                         highest_addr = base + size;
         }
 
-        if (amd_special_default_mtrr(end_pfn))
+        /* kvm/qemu doesn't have mtrr set right, don't trim them all */
+        if (!highest_addr) {
+                printk(KERN_WARNING "***************\n");
+                printk(KERN_WARNING "**** WARNING: likely strange cpu\n");
+                printk(KERN_WARNING "**** MTRRs all blank, cpu in qemu?\n");
+                printk(KERN_WARNING "***************\n");
                 return 0;
+        }
 
         if ((highest_addr >> PAGE_SHIFT) < end_pfn) {
                 printk(KERN_WARNING "***************\n");
@@ -726,7 +733,6 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
         return 0;
 }
-#endif
 
 /**
  * mtrr_bp_init - initialize mtrrs on the boot CPU
diff --git a/arch/x86/kernel/e820_32.c b/arch/x86/kernel/e820_32.c
index 931934a7b353..4e16ef4a2659 100644
--- a/arch/x86/kernel/e820_32.c
+++ b/arch/x86/kernel/e820_32.c
@@ -749,3 +749,14 @@ static int __init parse_memmap(char *arg)
         return 0;
 }
 early_param("memmap", parse_memmap);
+void __init update_e820(void)
+{
+        u8 nr_map;
+
+        nr_map = e820.nr_map;
+        if (sanitize_e820_map(e820.map, &nr_map))
+                return;
+        e820.nr_map = nr_map;
+        printk(KERN_INFO "modified physical RAM map:\n");
+        print_memory_map("modified");
+}
diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index 26a56f714d34..83ba3ca5f431 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -48,6 +48,7 @@
 
 #include <video/edid.h>
 
+#include <asm/mtrr.h>
 #include <asm/apic.h>
 #include <asm/e820.h>
 #include <asm/mpspec.h>
@@ -758,6 +759,11 @@ void __init setup_arch(char **cmdline_p)
 
         max_low_pfn = setup_memory();
 
+        /* update e820 for memory not covered by WB MTRRs */
+        mtrr_bp_init();
+        if (mtrr_trim_uncached_memory(max_pfn))
+                max_low_pfn = setup_memory();
+
 #ifdef CONFIG_VMI
         /*
          * Must be after max_low_pfn is determined, and before kernel
diff --git a/include/asm-x86/e820_32.h b/include/asm-x86/e820_32.h
index e2faf5f3a0bb..f1da7ebd1905 100644
--- a/include/asm-x86/e820_32.h
+++ b/include/asm-x86/e820_32.h
@@ -19,12 +19,15 @@
 #ifndef __ASSEMBLY__
 
 extern struct e820map e820;
+extern void update_e820(void);
 
 extern int e820_all_mapped(unsigned long start, unsigned long end,
                            unsigned type);
 extern int e820_any_mapped(u64 start, u64 end, unsigned type);
 extern void find_max_pfn(void);
 extern void register_bootmem_low_pages(unsigned long max_low_pfn);
+extern void add_memory_region(unsigned long long start,
+                              unsigned long long size, int type);
 extern void e820_register_memory(void);
 extern void limit_regions(unsigned long long size);
 extern void print_memory_map(char *who);