Merge branch 'linux-2.6'

7 files changed, 155 insertions, 67 deletions

diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c
index 0949cdbf848a..ee2331b0e58f 100644
--- a/arch/x86/kernel/cpu/mtrr/amd.c
+++ b/arch/x86/kernel/cpu/mtrr/amd.c
@@ -53,8 +53,6 @@ static void amd_set_mtrr(unsigned int reg, unsigned long base,
     <base> The base address of the region.
     <size> The size of the region. If this is 0 the region is disabled.
     <type> The type of the region.
-    <do_safe> If TRUE, do the change safely. If FALSE, safety measures should
-    be done externally.
     [RETURNS] Nothing.
 */
 {
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 9964be3de2b7..8e139c70f888 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -4,6 +4,7 @@
 #include <asm/msr.h>
 #include <asm/io.h>
 #include <asm/processor-cyrix.h>
+#include <asm/processor-flags.h>
 #include "mtrr.h"
 
 int arr3_protected;
@@ -142,7 +143,7 @@ static void prepare_set(void)
 
         /*  Disable and flush caches. Note that wbinvd flushes the TLBs as
             a side-effect  */
-        cr0 = read_cr0() | 0x40000000;
+        cr0 = read_cr0() | X86_CR0_CD;
         wbinvd();
         write_cr0(cr0);
         wbinvd();
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 992f08dfbb6c..103d61a59b19 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -9,11 +9,12 @@
 #include <asm/msr.h>
 #include <asm/system.h>
 #include <asm/cpufeature.h>
+#include <asm/processor-flags.h>
 #include <asm/tlbflush.h>
 #include "mtrr.h"
 
 struct mtrr_state {
-        struct mtrr_var_range *var_ranges;
+        struct mtrr_var_range var_ranges[MAX_VAR_RANGES];
         mtrr_type fixed_ranges[NUM_FIXED_RANGES];
         unsigned char enabled;
         unsigned char have_fixed;
@@ -85,12 +86,6 @@ void __init get_mtrr_state(void)
         struct mtrr_var_range *vrs;
         unsigned lo, dummy;
 
-        if (!mtrr_state.var_ranges) {
-                mtrr_state.var_ranges = kmalloc(num_var_ranges * sizeof (struct mtrr_var_range), 
-                                                GFP_KERNEL);
-                if (!mtrr_state.var_ranges)
-                        return;
-        } 
         vrs = mtrr_state.var_ranges;
 
         rdmsr(MTRRcap_MSR, lo, dummy);
@@ -188,7 +183,7 @@ static inline void k8_enable_fixed_iorrs(void)
  * \param changed pointer which indicates whether the MTRR needed to be changed
  * \param msrwords pointer to the MSR values which the MSR should have
  */
-static void set_fixed_range(int msr, int * changed, unsigned int * msrwords)
+static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
 {
         unsigned lo, hi;
 
@@ -200,7 +195,7 @@ static void set_fixed_range(int msr, int * changed, unsigned int * msrwords)
                     ((msrwords[0] | msrwords[1]) & K8_MTRR_RDMEM_WRMEM_MASK))
                         k8_enable_fixed_iorrs();
                 mtrr_wrmsr(msr, msrwords[0], msrwords[1]);
-                *changed = TRUE;
+                *changed = true;
         }
 }
 
@@ -260,7 +255,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 static int set_fixed_ranges(mtrr_type * frs)
 {
         unsigned long long *saved = (unsigned long long *) frs;
-        int changed = FALSE;
+        bool changed = false;
         int block=-1, range;
 
         while (fixed_range_blocks[++block].ranges)
@@ -273,17 +268,17 @@ static int set_fixed_ranges(mtrr_type * frs)
 
 /*  Set the MSR pair relating to a var range. Returns TRUE if
     changes are made  */
-static int set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
+static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
 {
         unsigned int lo, hi;
-        int changed = FALSE;
+        bool changed = false;
 
         rdmsr(MTRRphysBase_MSR(index), lo, hi);
         if ((vr->base_lo & 0xfffff0ffUL) != (lo & 0xfffff0ffUL)
             || (vr->base_hi & (size_and_mask >> (32 - PAGE_SHIFT))) !=
                 (hi & (size_and_mask >> (32 - PAGE_SHIFT)))) {
                 mtrr_wrmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi);
-                changed = TRUE;
+                changed = true;
         }
 
         rdmsr(MTRRphysMask_MSR(index), lo, hi);
@@ -292,7 +287,7 @@ static int set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
             || (vr->mask_hi & (size_and_mask >> (32 - PAGE_SHIFT))) !=
                 (hi & (size_and_mask >> (32 - PAGE_SHIFT)))) {
                 mtrr_wrmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
-                changed = TRUE;
+                changed = true;
         }
         return changed;
 }
@@ -350,7 +345,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
         spin_lock(&set_atomicity_lock);
 
         /*  Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
-        cr0 = read_cr0() | 0x40000000;  /* set CD flag */
+        cr0 = read_cr0() | X86_CR0_CD;
         write_cr0(cr0);
         wbinvd();
 
@@ -417,8 +412,6 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base,
     <base> The base address of the region.
     <size> The size of the region. If this is 0 the region is disabled.
     <type> The type of the region.
-    <do_safe> If TRUE, do the change safely. If FALSE, safety measures should
-    be done externally.
     [RETURNS] Nothing.
 */
 {
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index c7d8f1756745..91e150acb46c 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -11,10 +11,6 @@
 #include <asm/mtrr.h>
 #include "mtrr.h"
 
-/* RED-PEN: this is accessed without any locking */
-extern unsigned int *usage_table;
-
-
 #define FILE_FCOUNT(f) (((struct seq_file *)((f)->private_data))->private)
 
 static const char *const mtrr_strings[MTRR_NUM_TYPES] =
@@ -37,7 +33,7 @@ const char *mtrr_attrib_to_str(int x)
 
 static int
 mtrr_file_add(unsigned long base, unsigned long size,
-              unsigned int type, char increment, struct file *file, int page)
+              unsigned int type, bool increment, struct file *file, int page)
 {
         int reg, max;
         unsigned int *fcount = FILE_FCOUNT(file); 
@@ -55,7 +51,7 @@ mtrr_file_add(unsigned long base, unsigned long size,
                 base >>= PAGE_SHIFT;
                 size >>= PAGE_SHIFT;
         }
-        reg = mtrr_add_page(base, size, type, 1);
+        reg = mtrr_add_page(base, size, type, true);
         if (reg >= 0)
                 ++fcount[reg];
         return reg;
@@ -141,7 +137,7 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
                 size >>= PAGE_SHIFT;
                 err =
                     mtrr_add_page((unsigned long) base, (unsigned long) size, i,
-                                  1);
+                                  true);
                 if (err < 0)
                         return err;
                 return len;
@@ -217,7 +213,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
                 if (!capable(CAP_SYS_ADMIN))
                         return -EPERM;
                 err =
-                    mtrr_file_add(sentry.base, sentry.size, sentry.type, 1,
+                    mtrr_file_add(sentry.base, sentry.size, sentry.type, true,
                                   file, 0);
                 break;
         case MTRRIOC_SET_ENTRY:
@@ -226,7 +222,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 #endif
                 if (!capable(CAP_SYS_ADMIN))
                         return -EPERM;
-                err = mtrr_add(sentry.base, sentry.size, sentry.type, 0);
+                err = mtrr_add(sentry.base, sentry.size, sentry.type, false);
                 break;
         case MTRRIOC_DEL_ENTRY:
 #ifdef CONFIG_COMPAT
@@ -270,7 +266,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
                 if (!capable(CAP_SYS_ADMIN))
                         return -EPERM;
                 err =
-                    mtrr_file_add(sentry.base, sentry.size, sentry.type, 1,
+                    mtrr_file_add(sentry.base, sentry.size, sentry.type, true,
                                   file, 1);
                 break;
         case MTRRIOC_SET_PAGE_ENTRY:
@@ -279,7 +275,8 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 #endif
                 if (!capable(CAP_SYS_ADMIN))
                         return -EPERM;
-                err = mtrr_add_page(sentry.base, sentry.size, sentry.type, 0);
+                err =
+                    mtrr_add_page(sentry.base, sentry.size, sentry.type, false);
                 break;
         case MTRRIOC_DEL_PAGE_ENTRY:
 #ifdef CONFIG_COMPAT
@@ -396,7 +393,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
         for (i = 0; i < max; i++) {
                 mtrr_if->get(i, &base, &size, &type);
                 if (size == 0)
-                        usage_table[i] = 0;
+                        mtrr_usage_table[i] = 0;
                 else {
                         if (size < (0x100000 >> PAGE_SHIFT)) {
                                 /* less than 1MB */
@@ -410,7 +407,7 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset)
                         len += seq_printf(seq, 
                                    "reg%02i: base=0x%05lx000 (%4luMB), size=%4lu%cB: %s, count=%d\n",
                              i, base, base >> (20 - PAGE_SHIFT), size, factor,
-                             mtrr_attrib_to_str(type), usage_table[i]);
+                             mtrr_attrib_to_str(type), mtrr_usage_table[i]);
                 }
         }
         return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 3b20613325dc..715919582657 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -38,8 +38,8 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 
+#include <asm/e820.h>
 #include <asm/mtrr.h>
-
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
@@ -47,7 +47,7 @@
 
 u32 num_var_ranges = 0;
 
-unsigned int *usage_table;
+unsigned int mtrr_usage_table[MAX_VAR_RANGES];
 static DEFINE_MUTEX(mtrr_mutex);
 
 u64 size_or_mask, size_and_mask;
@@ -121,13 +121,8 @@ static void __init init_table(void)
         int i, max;
 
         max = num_var_ranges;
-        if ((usage_table = kmalloc(max * sizeof *usage_table, GFP_KERNEL))
-            == NULL) {
-                printk(KERN_ERR "mtrr: could not allocate\n");
-                return;
-        }
         for (i = 0; i < max; i++)
-                usage_table[i] = 1;
+                mtrr_usage_table[i] = 1;
 }
 
 struct set_mtrr_data {
@@ -311,7 +306,7 @@ static void set_mtrr(unsigned int reg, unsigned long base,
  */
 
 int mtrr_add_page(unsigned long base, unsigned long size, 
-                  unsigned int type, char increment)
+                  unsigned int type, bool increment)
 {
         int i, replace, error;
         mtrr_type ltype;
@@ -349,7 +344,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
         replace = -1;
 
         /* No CPU hotplug when we change MTRR entries */
-        lock_cpu_hotplug();
+        get_online_cpus();
         /*  Search for existing MTRR  */
         mutex_lock(&mtrr_mutex);
         for (i = 0; i < num_var_ranges; ++i) {
@@ -383,7 +378,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
                         goto out;
                 }
                 if (increment)
-                        ++usage_table[i];
+                        ++mtrr_usage_table[i];
                 error = i;
                 goto out;
         }
@@ -391,13 +386,15 @@ int mtrr_add_page(unsigned long base, unsigned long size,
         i = mtrr_if->get_free_region(base, size, replace);
         if (i >= 0) {
                 set_mtrr(i, base, size, type);
-                if (likely(replace < 0))
-                        usage_table[i] = 1;
-                else {
-                        usage_table[i] = usage_table[replace] + !!increment;
+                if (likely(replace < 0)) {
+                        mtrr_usage_table[i] = 1;
+                } else {
+                        mtrr_usage_table[i] = mtrr_usage_table[replace];
+                        if (increment)
+                                mtrr_usage_table[i]++;
                         if (unlikely(replace != i)) {
                                 set_mtrr(replace, 0, 0, 0);
-                                usage_table[replace] = 0;
+                                mtrr_usage_table[replace] = 0;
                         }
                 }
         } else
@@ -405,7 +402,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
         error = i;
  out:
         mutex_unlock(&mtrr_mutex);
-        unlock_cpu_hotplug();
+        put_online_cpus();
         return error;
 }
 
@@ -460,7 +457,7 @@ static int mtrr_check(unsigned long base, unsigned long size)
 
 int
 mtrr_add(unsigned long base, unsigned long size, unsigned int type,
-         char increment)
+         bool increment)
 {
         if (mtrr_check(base, size))
                 return -EINVAL;
@@ -495,7 +492,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 
         max = num_var_ranges;
         /* No CPU hotplug when we change MTRR entries */
-        lock_cpu_hotplug();
+        get_online_cpus();
         mutex_lock(&mtrr_mutex);
         if (reg < 0) {
                 /*  Search for existing MTRR  */
@@ -527,16 +524,16 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
                 printk(KERN_WARNING "mtrr: MTRR %d not used\n", reg);
                 goto out;
         }
-        if (usage_table[reg] < 1) {
+        if (mtrr_usage_table[reg] < 1) {
                 printk(KERN_WARNING "mtrr: reg: %d has count=0\n", reg);
                 goto out;
         }
-        if (--usage_table[reg] < 1)
+        if (--mtrr_usage_table[reg] < 1)
                 set_mtrr(reg, 0, 0, 0);
         error = reg;
  out:
         mutex_unlock(&mtrr_mutex);
-        unlock_cpu_hotplug();
+        put_online_cpus();
         return error;
 }
 /**
@@ -591,16 +588,11 @@ struct mtrr_value {
         unsigned long   lsize;
 };
 
-static struct mtrr_value * mtrr_state;
+static struct mtrr_value mtrr_state[MAX_VAR_RANGES];
 
 static int mtrr_save(struct sys_device * sysdev, pm_message_t state)
 {
         int i;
-        int size = num_var_ranges * sizeof(struct mtrr_value);
-
-        mtrr_state = kzalloc(size,GFP_ATOMIC);
-        if (!mtrr_state)
-                return -ENOMEM;
 
         for (i = 0; i < num_var_ranges; i++) {
                 mtrr_if->get(i,
@@ -622,7 +614,6 @@ static int mtrr_restore(struct sys_device * sysdev)
                                  mtrr_state[i].lsize,
                                  mtrr_state[i].ltype);
         }
-        kfree(mtrr_state);
         return 0;
 }
 
@@ -633,6 +624,112 @@ static struct sysdev_driver mtrr_sysdev_driver = {
         .resume         = mtrr_restore,
 };
 
+static int disable_mtrr_trim;
+
+static int __init disable_mtrr_trim_setup(char *str)
+{
+        disable_mtrr_trim = 1;
+        return 0;
+}
+early_param("disable_mtrr_trim", disable_mtrr_trim_setup);
+
+/*
+ * Newer AMD K8s and later CPUs have a special magic MSR way to force WB
+ * for memory >4GB. Check for that here.
+ * Note this won't check if the MTRRs < 4GB where the magic bit doesn't
+ * apply to are wrong, but so far we don't know of any such case in the wild.
+ */
+#define Tom2Enabled (1U << 21)
+#define Tom2ForceMemTypeWB (1U << 22)
+
+static __init int amd_special_default_mtrr(void)
+{
+        u32 l, h;
+
+        if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+                return 0;
+        if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
+                return 0;
+        /* In case some hypervisor doesn't pass SYSCFG through */
+        if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
+                return 0;
+        /*
+         * Memory between 4GB and top of mem is forced WB by this magic bit.
+         * Reserved before K8RevF, but should be zero there.
+         */
+        if ((l & (Tom2Enabled | Tom2ForceMemTypeWB)) ==
+                 (Tom2Enabled | Tom2ForceMemTypeWB))
+                return 1;
+        return 0;
+}
+
+/**
+ * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs
+ *
+ * Some buggy BIOSes don't setup the MTRRs properly for systems with certain
+ * memory configurations.  This routine checks that the highest MTRR matches
+ * the end of memory, to make sure the MTRRs having a write back type cover
+ * all of the memory the kernel is intending to use. If not, it'll trim any
+ * memory off the end by adjusting end_pfn, removing it from the kernel's
+ * allocation pools, warning the user with an obnoxious message.
+ */
+int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
+{
+        unsigned long i, base, size, highest_addr = 0, def, dummy;
+        mtrr_type type;
+        u64 trim_start, trim_size;
+
+        /*
+         * 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 (def != MTRR_TYPE_UNCACHABLE)
+                return 0;
+
+        if (amd_special_default_mtrr())
+                return 0;
+
+        /* Find highest cached pfn */
+        for (i = 0; i < num_var_ranges; i++) {
+                mtrr_if->get(i, &base, &size, &type);
+                if (type != MTRR_TYPE_WRBACK)
+                        continue;
+                base <<= PAGE_SHIFT;
+                size <<= PAGE_SHIFT;
+                if (highest_addr < base + size)
+                        highest_addr = base + size;
+        }
+
+        /* kvm/qemu doesn't have mtrr set right, don't trim them all */
+        if (!highest_addr) {
+                printk(KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n");
+                WARN_ON(1);
+                return 0;
+        }
+
+        if ((highest_addr >> PAGE_SHIFT) < end_pfn) {
+                printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover"
+                        " all of memory, losing %LdMB of RAM.\n",
+                        (((u64)end_pfn << PAGE_SHIFT) - highest_addr) >> 20);
+
+                WARN_ON(1);
+
+                printk(KERN_INFO "update e820 for mtrr\n");
+                trim_start = highest_addr;
+                trim_size = end_pfn;
+                trim_size <<= PAGE_SHIFT;
+                trim_size -= trim_start;
+                add_memory_region(trim_start, trim_size, E820_RESERVED);
+                update_e820();
+                return 1;
+        }
+
+        return 0;
+}
 
 /**
  * mtrr_bp_init - initialize mtrrs on the boot CPU
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 289dfe6030e3..fb74a2c20814 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -2,10 +2,8 @@
  * local mtrr defines.
  */
 
-#ifndef TRUE
-#define TRUE  1
-#define FALSE 0
-#endif
+#include <linux/types.h>
+#include <linux/stddef.h>
 
 #define MTRRcap_MSR     0x0fe
 #define MTRRdefType_MSR 0x2ff
@@ -14,6 +12,7 @@
 #define MTRRphysMask_MSR(reg) (0x200 + 2 * (reg) + 1)
 
 #define NUM_FIXED_RANGES 88
+#define MAX_VAR_RANGES 256
 #define MTRRfix64K_00000_MSR 0x250
 #define MTRRfix16K_80000_MSR 0x258
 #define MTRRfix16K_A0000_MSR 0x259
@@ -34,6 +33,8 @@
    an 8 bit field: */
 typedef u8 mtrr_type;
 
+extern unsigned int mtrr_usage_table[MAX_VAR_RANGES];
+
 struct mtrr_ops {
         u32     vendor;
         u32     use_intel_if;
diff --git a/arch/x86/kernel/cpu/mtrr/state.c b/arch/x86/kernel/cpu/mtrr/state.c
index 49e20c2afcdf..9f8ba923d1c9 100644
--- a/arch/x86/kernel/cpu/mtrr/state.c
+++ b/arch/x86/kernel/cpu/mtrr/state.c
@@ -4,6 +4,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 #include <asm/processor-cyrix.h>
+#include <asm/processor-flags.h>
 #include "mtrr.h"
 
 
@@ -25,7 +26,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt)
 
                 /*  Disable and flush caches. Note that wbinvd flushes the TLBs as
                     a side-effect  */
-                cr0 = read_cr0() | 0x40000000;
+                cr0 = read_cr0() | X86_CR0_CD;
                 wbinvd();
                 write_cr0(cr0);
                 wbinvd();