[PATCH] trim memory not covered by WB MTRRs

[Jesse Barnes <jesse.barnes@intel.com>]

On some machines, buggy BIOSes don't properly setup WB MTRRs to
cover all available RAM, meaning the last few megs (or even gigs)
of memory will be marked uncached.  Since Linux tends to allocate
from high memory addresses first, this causes the machine to be
unusably slow as soon as the kernel starts really using memory
(i.e. right around init time).

This patch works around the problem by scanning the MTRRs at
boot and figuring out whether the current end_pfn value (setup
by early e820 code) goes beyond the highest WB MTRR range, and
if so, trimming it to match.  A fairly obnoxious KERN_WARNING
is printed too, letting the user know that not all of their
memory is available due to a likely BIOS bug.

Something similar could be done on i386 if needed, but the boot
ordering would be slightly different, since the MTRR code on i386
depends on the boot_cpu_data structure being setup.

This patch fixes a bug in the last patch that caused the code to
run on non-Intel machines (AMD machines apparently don't need it
and it's untested on other non-Intel machines, so best keep it
off).

akpm -- this one should replace all the mtrr patches currently
in your tree.

Yinghai, maybe you can test this on one of your AMD machines to
make sure I got the CPU code right?

Signed-off-by:  Jesse Barnes <jesse.barnes@intel.com>

Thanks,
Jesse

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 5d0283c..642db9b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -553,6 +553,12 @@ 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]
+			By default the kernel will trim any uncacheable
+			memory out of your available memory pool based on
+			MTRR settings.  This parameter disables that behavior,
+			possibly causing your machine to run very slowly.
+
 	dmascc=		[HW,AX25,SERIAL] AX.25 Z80SCC driver with DMA
 			support available.
 			Format: <io_dev0>[,<io_dev1>[,..<io_dev32>]]
diff --git a/arch/i386/kernel/cpu/mtrr/generic.c b/arch/i386/kernel/cpu/mtrr/generic.c
index 6d59378..bf70d2d 100644
--- a/arch/i386/kernel/cpu/mtrr/generic.c
+++ b/arch/i386/kernel/cpu/mtrr/generic.c
@@ -13,7 +13,7 @@
 #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;
@@ -84,12 +84,6 @@ void 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);
diff --git a/arch/i386/kernel/cpu/mtrr/if.c b/arch/i386/kernel/cpu/mtrr/if.c
index c7d8f17..1b3a09c 100644
--- a/arch/i386/kernel/cpu/mtrr/if.c
+++ b/arch/i386/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] =
@@ -396,7 +392,7 @@ 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 +406,7 @@ 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/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c
index 55b0051..0e4be8b 100644
--- a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/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 {
@@ -381,7 +376,7 @@ 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;
 	}
@@ -390,12 +385,13 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	if (i >= 0) {
 		set_mtrr(i, base, size, type);
 		if (likely(replace < 0))
-			usage_table[i] = 1;
+			mtrr_usage_table[i] = 1;
 		else {
-			usage_table[i] = usage_table[replace] + !!increment;
+			mtrr_usage_table[i] = mtrr_usage_table[replace] +
+				!!increment;
 			if (unlikely(replace != i)) {
 				set_mtrr(replace, 0, 0, 0);
-				usage_table[replace] = 0;
+				mtrr_usage_table[replace] = 0;
 			}
 		}
 	} else
@@ -525,11 +521,11 @@ 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:
@@ -589,16 +585,11 @@ 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,
@@ -620,7 +611,6 @@ static int mtrr_restore(struct sys_device * sysdev)
 				 mtrr_state[i].lsize,
 				 mtrr_state[i].ltype);
 	}
-	kfree(mtrr_state);
 	return 0;
 }
 
@@ -631,6 +621,59 @@ 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);
+
+#ifdef CONFIG_X86_64
+/**
+ * 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 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.
+ */
+void __init mtrr_trim_uncached_memory(void)
+{
+	unsigned long i, base, size, highest_addr = 0, def, dummy;
+	mtrr_type type;
+
+	/* Make sure we only trim uncachable memory on Intel machines */
+	rdmsr(MTRRdefType_MSR, def, dummy);
+	def &= 0xff;
+	if (!is_cpu(INTEL) || disable_mtrr_trim || def != MTRR_TYPE_UNCACHABLE)
+		return;
+
+	/* 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;
+	}
+
+	if ((highest_addr >> PAGE_SHIFT) != end_pfn) {
+		printk(KERN_WARNING "***************\n");
+		printk(KERN_WARNING "**** WARNING: likely BIOS bug\n");
+		printk(KERN_WARNING "**** MTRRs don't cover all of "
+		       "memory, trimmed %ld pages\n", end_pfn -
+		       (highest_addr >> PAGE_SHIFT));
+		printk(KERN_WARNING "***************\n");
+		end_pfn = highest_addr >> PAGE_SHIFT;
+	}
+}
+#endif
 
 /**
  * mtrr_bp_init - initialize mtrrs on the boot CPU
diff --git a/arch/i386/kernel/cpu/mtrr/mtrr.h b/arch/i386/kernel/cpu/mtrr/mtrr.h
index 289dfe6..14fb88b 100644
--- a/arch/i386/kernel/cpu/mtrr/mtrr.h
+++ b/arch/i386/kernel/cpu/mtrr/mtrr.h
@@ -14,6 +14,7 @@
 #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 +35,8 @@
    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_64/kernel/bugs.c b/arch/x86_64/kernel/bugs.c
index c3c6b91..c138eac 100644
--- a/arch/x86_64/kernel/bugs.c
+++ b/arch/x86_64/kernel/bugs.c
@@ -14,7 +14,6 @@
 void __init check_bugs(void)
 {
 	identify_cpu(&boot_cpu_data);
-	mtrr_bp_init();
 #if !defined(CONFIG_SMP)
 	printk("CPU: ");
 	print_cpu_info(&boot_cpu_data);
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index eb6524f..409b63c 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -266,6 +266,10 @@ void __init setup_arch(char **cmdline_p)
 	 * we are rounding upwards:
 	 */
 	end_pfn = e820_end_of_ram();
+	/* Trim memory not covered by WB MTRRs */
+	mtrr_bp_init();
+	mtrr_trim_uncached_memory();
+
 	num_physpages = end_pfn;
 
 	check_efer();
diff --git a/include/asm-x86_64/mtrr.h b/include/asm-x86_64/mtrr.h
index b557c48..51ad788 100644
--- a/include/asm-x86_64/mtrr.h
+++ b/include/asm-x86_64/mtrr.h
@@ -78,6 +78,7 @@ extern int mtrr_add_page (unsigned long base, unsigned long size,
 		     unsigned int type, char increment);
 extern int mtrr_del (int reg, unsigned long base, unsigned long size);
 extern int mtrr_del_page (int reg, unsigned long base, unsigned long size);
+extern void mtrr_trim_uncached_memory(void);
 #  else
 static __inline__ int mtrr_add (unsigned long base, unsigned long size,
 				unsigned int type, char increment)
@@ -99,7 +100,9 @@ static __inline__ int mtrr_del_page (int reg, unsigned long base,
 {
     return -ENODEV;
 }
-
+static __inline__ void mtrr_trim_uncached_memory(void)
+{
+}
 #endif /* CONFIG_MTRR */
 
 #ifdef CONFIG_COMPAT
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/