3 files changed, 137 insertions, 35 deletions

diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index c5f59d071425..ac140c7be396 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -827,7 +827,7 @@ int __init amd_special_default_mtrr(void)
 
         if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
                 return 0;
-        if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
+        if (boot_cpu_data.x86 < 0xf)
                 return 0;
         /* In case some hypervisor doesn't pass SYSCFG through: */
         if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d28d7d03885..a71efcdbb092 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -1,6 +1,6 @@
 /*
  * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong
- * because MTRRs can span upto 40 bits (36bits on most modern x86)
+ * because MTRRs can span up to 40 bits (36bits on most modern x86)
  */
 #define DEBUG
 
@@ -64,18 +64,59 @@ static inline void k8_check_syscfg_dram_mod_en(void)
         }
 }
 
+/* Get the size of contiguous MTRR range */
+static u64 get_mtrr_size(u64 mask)
+{
+        u64 size;
+
+        mask >>= PAGE_SHIFT;
+        mask |= size_or_mask;
+        size = -mask;
+        size <<= PAGE_SHIFT;
+        return size;
+}
+
 /*
- * Returns the effective MTRR type for the region
- * Error returns:
- * - 0xFE - when the range is "not entirely covered" by _any_ var range MTRR
- * - 0xFF - when MTRR is not enabled
+ * Check and return the effective type for MTRR-MTRR type overlap.
+ * Returns 1 if the effective type is UNCACHEABLE, else returns 0
  */
-u8 mtrr_type_lookup(u64 start, u64 end)
+static int check_type_overlap(u8 *prev, u8 *curr)
+{
+        if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) {
+                *prev = MTRR_TYPE_UNCACHABLE;
+                *curr = MTRR_TYPE_UNCACHABLE;
+                return 1;
+        }
+
+        if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) ||
+            (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) {
+                *prev = MTRR_TYPE_WRTHROUGH;
+                *curr = MTRR_TYPE_WRTHROUGH;
+        }
+
+        if (*prev != *curr) {
+                *prev = MTRR_TYPE_UNCACHABLE;
+                *curr = MTRR_TYPE_UNCACHABLE;
+                return 1;
+        }
+
+        return 0;
+}
+
+/*
+ * Error/Semi-error returns:
+ * 0xFF - when MTRR is not enabled
+ * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
+ *              corresponds only to [start:*partial_end].
+ *              Caller has to lookup again for [*partial_end:end].
+ */
+static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 {
         int i;
         u64 base, mask;
         u8 prev_match, curr_match;
 
+        *repeat = 0;
         if (!mtrr_state_set)
                 return 0xFF;
 
@@ -126,8 +167,34 @@ u8 mtrr_type_lookup(u64 start, u64 end)
 
                 start_state = ((start & mask) == (base & mask));
                 end_state = ((end & mask) == (base & mask));
-                if (start_state != end_state)
-                        return 0xFE;
+
+                if (start_state != end_state) {
+                        /*
+                         * We have start:end spanning across an MTRR.
+                         * We split the region into
+                         * either
+                         * (start:mtrr_end) (mtrr_end:end)
+                         * or
+                         * (start:mtrr_start) (mtrr_start:end)
+                         * depending on kind of overlap.
+                         * Return the type for first region and a pointer to
+                         * the start of second region so that caller will
+                         * lookup again on the second region.
+                         * Note: This way we handle multiple overlaps as well.
+                         */
+                        if (start_state)
+                                *partial_end = base + get_mtrr_size(mask);
+                        else
+                                *partial_end = base;
+
+                        if (unlikely(*partial_end <= start)) {
+                                WARN_ON(1);
+                                *partial_end = start + PAGE_SIZE;
+                        }
+
+                        end = *partial_end - 1; /* end is inclusive */
+                        *repeat = 1;
+                }
 
                 if ((start & mask) != (base & mask))
                         continue;
@@ -138,21 +205,8 @@ u8 mtrr_type_lookup(u64 start, u64 end)
                         continue;
                 }
 
-                if (prev_match == MTRR_TYPE_UNCACHABLE ||
-                    curr_match == MTRR_TYPE_UNCACHABLE) {
-                        return MTRR_TYPE_UNCACHABLE;
-                }
-
-                if ((prev_match == MTRR_TYPE_WRBACK &&
-                     curr_match == MTRR_TYPE_WRTHROUGH) ||
-                    (prev_match == MTRR_TYPE_WRTHROUGH &&
-                     curr_match == MTRR_TYPE_WRBACK)) {
-                        prev_match = MTRR_TYPE_WRTHROUGH;
-                        curr_match = MTRR_TYPE_WRTHROUGH;
-                }
-
-                if (prev_match != curr_match)
-                        return MTRR_TYPE_UNCACHABLE;
+                if (check_type_overlap(&prev_match, &curr_match))
+                        return curr_match;
         }
 
         if (mtrr_tom2) {
@@ -166,6 +220,36 @@ u8 mtrr_type_lookup(u64 start, u64 end)
         return mtrr_state.def_type;
 }
 
+/*
+ * Returns the effective MTRR type for the region
+ * Error return:
+ * 0xFF - when MTRR is not enabled
+ */
+u8 mtrr_type_lookup(u64 start, u64 end)
+{
+        u8 type, prev_type;
+        int repeat;
+        u64 partial_end;
+
+        type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+        /*
+         * Common path is with repeat = 0.
+         * However, we can have cases where [start:end] spans across some
+         * MTRR range. Do repeated lookups for that case here.
+         */
+        while (repeat) {
+                prev_type = type;
+                start = partial_end;
+                type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+                if (check_type_overlap(&prev_type, &type))
+                        return type;
+        }
+
+        return type;
+}
+
 /* Get the MSR pair relating to a var range */
 static void
 get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 01c0f3ee6cc3..929739a653d1 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -45,6 +45,7 @@
 #include <linux/cpu.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/processor.h>
 #include <asm/e820.h>
@@ -292,14 +293,24 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 
         /*
          * HACK!
-         * We use this same function to initialize the mtrrs on boot.
-         * The state of the boot cpu's mtrrs has been saved, and we want
-         * to replicate across all the APs.
-         * If we're doing that @reg is set to something special...
+         *
+         * We use this same function to initialize the mtrrs during boot,
+         * resume, runtime cpu online and on an explicit request to set a
+         * specific MTRR.
+         *
+         * During boot or suspend, the state of the boot cpu's mtrrs has been
+         * saved, and we want to replicate that across all the cpus that come
+         * online (either at the end of boot or resume or during a runtime cpu
+         * online). If we're doing that, @reg is set to something special and on
+         * this cpu we still do mtrr_if->set_all(). During boot/resume, this
+         * is unnecessary if at this point we are still on the cpu that started
+         * the boot/resume sequence. But there is no guarantee that we are still
+         * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be
+         * sure that we are in sync with everyone else.
          */
         if (reg != ~0U)
                 mtrr_if->set(reg, base, size, type);
-        else if (!mtrr_aps_delayed_init)
+        else
                 mtrr_if->set_all();
 
         /* Wait for the others */
@@ -630,7 +641,7 @@ struct mtrr_value {
 
 static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES];
 
-static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
+static int mtrr_save(void)
 {
         int i;
 
@@ -642,7 +653,7 @@ static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
         return 0;
 }
 
-static int mtrr_restore(struct sys_device *sysdev)
+static void mtrr_restore(void)
 {
         int i;
 
@@ -653,12 +664,11 @@ static int mtrr_restore(struct sys_device *sysdev)
                                     mtrr_value[i].ltype);
                 }
         }
-        return 0;
 }
 
 
 
-static struct sysdev_driver mtrr_sysdev_driver = {
+static struct syscore_ops mtrr_syscore_ops = {
         .suspend        = mtrr_save,
         .resume         = mtrr_restore,
 };
@@ -793,13 +803,21 @@ void set_mtrr_aps_delayed_init(void)
 }
 
 /*
- * MTRR initialization for all AP's
+ * Delayed MTRR initialization for all AP's
  */
 void mtrr_aps_init(void)
 {
         if (!use_intel())
                 return;
 
+        /*
+         * Check if someone has requested the delay of AP MTRR initialization,
+         * by doing set_mtrr_aps_delayed_init(), prior to this point. If not,
+         * then we are done.
+         */
+        if (!mtrr_aps_delayed_init)
+                return;
+
         set_mtrr(~0U, 0, 0, 0);
         mtrr_aps_delayed_init = false;
 }
@@ -831,7 +849,7 @@ static int __init mtrr_init_finialize(void)
          * TBD: is there any system with such CPU which supports
          * suspend/resume? If no, we should remove the code.
          */
-        sysdev_driver_register(&cpu_sysdev_class, &mtrr_sysdev_driver);
+        register_syscore_ops(&mtrr_syscore_ops);
 
         return 0;
 }