| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <200804272337.40130.yhlu.kernel@gmail.com>
Date: Sun, 27 Apr 2008 23:37:39 -0700
From: Yinghai Lu <yhlu.kernel.send@...il.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
Ingo Molnar <mingo@...e.hu>
Cc: "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: [PATCH] x86: mtrr cleanup for converting continuous to discrete layout
some BIOS like to use continus MTRR layout, and X driver can not add
WB entries for graphical cards when 4g or more RAM installed.
the patch will change MTRR to discrete.
mtrr_chunk_size= could be used to have smaller continuous block to hold holes.
default is 256m, could be set according to size of graphics card memory.
Signed-off-by: Yinghai Lu <yhlu.kernel@...il.com>
Index: linux-2.6/arch/x86/kernel/cpu/mtrr/generic.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/mtrr/generic.c
+++ linux-2.6/arch/x86/kernel/cpu/mtrr/generic.c
@@ -158,6 +158,20 @@ get_mtrr_var_range(unsigned int index, s
rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi);
}
+/* fill the MSR pair relating to a var range */
+void fill_mtrr_var_range(unsigned int index,
+ u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi)
+{
+ struct mtrr_var_range *vr;
+
+ vr = mtrr_state.var_ranges;
+
+ vr[index].base_lo = base_lo;
+ vr[index].base_hi = base_hi;
+ vr[index].mask_lo = mask_lo;
+ vr[index].mask_hi = mask_hi;
+}
+
static void
get_fixed_ranges(mtrr_type * frs)
{
Index: linux-2.6/arch/x86/kernel/cpu/mtrr/main.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/mtrr/main.c
+++ linux-2.6/arch/x86/kernel/cpu/mtrr/main.c
@@ -37,6 +37,7 @@
#include <linux/smp.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
+#include <linux/sort.h>
#include <asm/e820.h>
#include <asm/mtrr.h>
@@ -609,6 +610,348 @@ static struct sysdev_driver mtrr_sysdev_
.resume = mtrr_restore,
};
+static int disable_mtrr_cleanup;
+
+static int __init disable_mtrr_cleanup_setup(char *str)
+{
+ disable_mtrr_cleanup = 1;
+ return 0;
+}
+early_param("disable_mtrr_cleanup", disable_mtrr_cleanup_setup);
+
+#define RANGE_NUM 256
+
+struct res_range {
+ size_t start;
+ size_t end;
+};
+
+static void __init subtract_range(struct res_range *range, size_t start,
+ size_t end)
+{
+ int i;
+ int j;
+
+ for (j = 0; j < RANGE_NUM; j++) {
+ if (!range[j].end)
+ continue;
+
+ if (start <= range[j].start && end >= range[j].end) {
+ range[j].start = 0;
+ range[j].end = 0;
+ continue;
+ }
+
+ if (start <= range[j].start && end < range[j].end && range[j].start < end + 1) {
+ range[j].start = end + 1;
+ continue;
+ }
+
+
+ if (start > range[j].start && end >= range[j].end && range[j].end > start - 1) {
+ range[j].end = start - 1;
+ continue;
+ }
+
+ if (start > range[j].start && end < range[j].end) {
+ /* find the new spare */
+ for (i = 0; i < RANGE_NUM; i++) {
+ if (range[i].end == 0)
+ break;
+ }
+ if (i < RANGE_NUM) {
+ range[i].end = range[j].end;
+ range[i].start = end + 1;
+ } else {
+ printk(KERN_ERR "run of slot in ranges\n");
+ }
+ range[j].end = start - 1;
+ continue;
+ }
+ }
+}
+
+static int __cpuinit cmp_range(const void *x1, const void *x2)
+{
+ const struct res_range *r1 = x1;
+ const struct res_range *r2 = x2;
+ s64 start1, start2;
+
+ start1 = r1->start;
+ start2 = r2->start;
+
+ return start1 - start2;
+}
+
+struct var_mtrr_state {
+ unsigned long range_startk, range_sizek;
+ unsigned long chunk_sizek;
+ unsigned int reg;
+ unsigned address_bits;
+};
+
+static void __init set_var_mtrr(
+ unsigned int reg, unsigned long basek, unsigned long sizek,
+ unsigned char type, unsigned address_bits)
+{
+ u32 base_lo, base_hi, mask_lo, mask_hi;
+ unsigned address_mask_high;
+
+ if (!sizek) {
+ fill_mtrr_var_range(reg, 0, 0, 0, 0);
+ return;
+ }
+
+ address_mask_high = ((1u << (address_bits - 32u)) - 1u);
+
+ base_hi = basek >> 22;
+ base_lo = basek << 10;
+
+ if (sizek < 4*1024*1024) {
+ mask_hi = address_mask_high;
+ mask_lo = ~((sizek << 10) - 1);
+ } else {
+ mask_hi = address_mask_high & (~((sizek >> 22) - 1));
+ mask_lo = 0;
+ }
+
+ base_lo |= type;
+ mask_lo |= 0x800;
+ fill_mtrr_var_range(reg, base_lo, base_hi, mask_lo, mask_hi);
+}
+
+static unsigned int __init range_to_mtrr(unsigned int reg,
+ unsigned long range_startk, unsigned long range_sizek,
+ unsigned long next_range_startk, unsigned char type, unsigned address_bits)
+{
+ if (!range_sizek || (reg >= num_var_ranges))
+ return reg;
+
+ while (range_sizek) {
+ unsigned long max_align, align;
+ unsigned long sizek;
+ /* Compute the maximum size I can make a range */
+ if (range_startk)
+ max_align = ffs(range_startk) - 1;
+ else
+ max_align = 32;
+ align = fls(range_sizek) - 1;
+ if (align > max_align)
+ align = max_align;
+
+ sizek = 1 << align;
+ printk(KERN_INFO "Setting variable MTRR %d, base: %ldMB, range: %ldMB, type %s\n",
+ reg, range_startk >> 10, sizek >> 10,
+ (type == MTRR_TYPE_UNCACHABLE)?"UC":
+ ((type == MTRR_TYPE_WRBACK)?"WB":"Other")
+ );
+ set_var_mtrr(reg++, range_startk, sizek, type, address_bits);
+ range_startk += sizek;
+ range_sizek -= sizek;
+ if (reg >= num_var_ranges)
+ break;
+ }
+ return reg;
+}
+
+static void __init range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek)
+{
+ unsigned long hole_basek, hole_sizek;
+ unsigned long range0_basek, range0_sizek;
+ unsigned long range_basek, range_sizek;
+ unsigned long next_basek;
+ unsigned long chunk_sizek;
+
+ hole_basek = 0;
+ hole_sizek = 0;
+ chunk_sizek = state->chunk_sizek;
+ range0_basek = state->range_startk;
+ next_basek = basek;
+
+ /* try to append some small hole */
+ range0_sizek = ALIGN(state->range_sizek, chunk_sizek);
+ if ((range0_sizek == state->range_sizek) ||
+ ((range0_basek + range0_sizek > basek) && basek)) {
+ printk(KERN_INFO "rangeX: %016lx - %016lx\n", range0_basek<<10, (range0_basek + range0_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, range0_basek,
+ range0_sizek, next_basek, MTRR_TYPE_WRBACK, state->address_bits);
+ return;
+ }
+
+ range0_sizek -= chunk_sizek;
+ range_basek = range0_basek + range0_sizek;
+ printk(KERN_INFO "range0: %016lx - %016lx\n", range0_basek<<10, (range0_basek + range0_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, range0_basek,
+ range0_sizek, range_basek, MTRR_TYPE_WRBACK, state->address_bits);
+
+ range_sizek = chunk_sizek;
+ if (range_sizek - (state->range_sizek - range0_sizek) < (chunk_sizek >> 1)) {
+ hole_sizek = range_sizek - (state->range_sizek - range0_sizek);
+ next_basek = hole_basek = range_basek + range_sizek - hole_sizek;
+ } else {
+ range_sizek = state->range_sizek - range0_sizek;
+ }
+ printk(KERN_INFO "range: %016lx - %016lx\n", range_basek<<10, (range_basek + range_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, range_basek,
+ range_sizek, next_basek, MTRR_TYPE_WRBACK, state->address_bits);
+ if (hole_sizek) {
+ printk(KERN_INFO "hole: %016lx - %016lx\n", hole_basek<<10, (hole_basek + hole_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, hole_basek,
+ hole_sizek, basek, MTRR_TYPE_UNCACHABLE, state->address_bits);
+ }
+}
+
+static void __init set_var_mtrr_range(struct var_mtrr_state *state, size_t base_pfn, size_t size_pfn)
+{
+ unsigned long basek, sizek;
+
+ if (state->reg >= num_var_ranges)
+ return;
+
+ basek = base_pfn << (PAGE_SHIFT - 10);
+ sizek = size_pfn << (PAGE_SHIFT - 10);
+
+ /* See if I can merge with the last range */
+ if ((basek <= 1024) || (state->range_startk + state->range_sizek == basek)) {
+ unsigned long endk = basek + sizek;
+ state->range_sizek = endk - state->range_startk;
+ return;
+ }
+ /* Write the range mtrrs */
+ if (state->range_sizek != 0) {
+ range_to_mtrr_with_hole(state, basek);
+
+ state->range_startk = 0;
+ state->range_sizek = 0;
+ }
+ /* Allocate an msr */
+ state->range_startk = basek;
+ state->range_sizek = sizek;
+}
+
+static u64 mtrr_chunk_size __initdata = (256ULL<<20);
+
+static int __init parse_mtrr_chunk_size_opt(char *p)
+{
+ if (!p)
+ return -EINVAL;
+ mtrr_chunk_size = memparse(p, &p);
+ return 0;
+}
+early_param("mtrr_chunk_size", parse_mtrr_chunk_size_opt);
+
+static void __init x86_setup_var_mtrrs(struct res_range *range, int nr_range, unsigned address_bits)
+{
+ struct var_mtrr_state var_state;
+ int i;
+
+ var_state.range_startk = 0;
+ var_state.range_sizek = 0;
+ var_state.reg = 0;
+ var_state.address_bits = address_bits;
+ var_state.chunk_sizek = mtrr_chunk_size >> 10;
+
+ /* Write the range etc */
+ for (i = 0; i < nr_range; i++)
+ set_var_mtrr_range(&var_state, range[i].start, range[i].end - range[i].start + 1);
+
+ /* Write the last range */
+ range_to_mtrr_with_hole(&var_state, 0);
+ printk(KERN_INFO "DONE variable MTRRs\n");
+ /* Clear out the extra MTRR's */
+ while (var_state.reg < num_var_ranges)
+ set_var_mtrr(var_state.reg++, 0, 0, 0, var_state.address_bits);
+}
+
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+ unsigned long i, base, size, def, dummy;
+ mtrr_type type;
+ struct res_range range[RANGE_NUM];
+ int nr_range;
+
+ /* extra one for all 0 */
+ int num[MTRR_NUM_TYPES + 1];
+
+ if (!is_cpu(INTEL) || disable_mtrr_cleanup)
+ return 0;
+ rdmsr(MTRRdefType_MSR, def, dummy);
+ def &= 0xff;
+ if (def != MTRR_TYPE_UNCACHABLE)
+ return 0;
+
+ /* check entries number */
+ memset(num, 0, sizeof(num));
+ for (i = 0; i < num_var_ranges; i++) {
+ mtrr_if->get(i, &base, &size, &type);
+ if (type >= MTRR_NUM_TYPES)
+ continue;
+ if (!size)
+ type = MTRR_NUM_TYPES;
+ num[type]++;
+ }
+
+ /* check if we got UC entries */
+ if (!num[MTRR_TYPE_UNCACHABLE])
+ return 0;
+
+ /* check if we only had WB and UC */
+ if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] !=
+ num_var_ranges - num[MTRR_NUM_TYPES])
+ return 0;
+
+ /*
+ * get WB ranges at first
+ * assume BIOS don't give us overlapping WB entries
+ * or add add_range?
+ */
+ memset(range, 0, sizeof(range));
+ nr_range = 0;
+ for (i = 0; i < num_var_ranges; i++) {
+ mtrr_if->get(i, &base, &size, &type);
+ if (type != MTRR_TYPE_WRBACK)
+ continue;
+ range[nr_range].start = base;
+ range[nr_range].end = base + size - 1;
+ nr_range++;
+ }
+ printk(KERN_INFO "After WB checking\n");
+ for (i = 0; i < nr_range; i++)
+ printk(KERN_INFO "MTRR MAP PFN: %016lx - %016lx\n", range[i].start, range[i].end + 1);
+
+ /* take out UC ranges */
+ for (i = 0; i < num_var_ranges; i++) {
+ mtrr_if->get(i, &base, &size, &type);
+ if (type != MTRR_TYPE_UNCACHABLE)
+ continue;
+ if (!size)
+ continue;
+ subtract_range(range, base, base + size);
+ }
+ /* get new range num */
+ nr_range = 0;
+ for (i = 0; i < RANGE_NUM; i++) {
+ if (!range[i].end)
+ continue;
+ nr_range++;
+ }
+ printk(KERN_INFO "After UC checking\n");
+ for (i = 0; i < nr_range; i++)
+ printk(KERN_INFO "MTRR MAP PFN: %016lx - %016lx\n", range[i].start, range[i].end + 1);
+
+ /* sort the ranges */
+ sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+ printk(KERN_INFO "After sorting\n");
+ for (i = 0; i < nr_range; i++)
+ printk(KERN_INFO "MTRR MAP PFN: %016lx - %016lx\n", range[i].start, range[i].end + 1);
+
+ /* convert ranges to var ranges state */
+ x86_setup_var_mtrrs(range, nr_range, address_bits);
+
+ return 1;
+
+}
+
static int disable_mtrr_trim;
static int __init disable_mtrr_trim_setup(char *str)
@@ -729,18 +1072,21 @@ int __init mtrr_trim_uncached_memory(uns
*/
void __init mtrr_bp_init(void)
{
+ u32 phys_addr;
init_ifs();
+ phys_addr = 32;
+
if (cpu_has_mtrr) {
mtrr_if = &generic_mtrr_ops;
size_or_mask = 0xff000000; /* 36 bits */
size_and_mask = 0x00f00000;
+ phys_addr = 36;
/* This is an AMD specific MSR, but we assume(hope?) that
Intel will implement it to when they extend the address
bus of the Xeon. */
if (cpuid_eax(0x80000000) >= 0x80000008) {
- u32 phys_addr;
phys_addr = cpuid_eax(0x80000008) & 0xff;
/* CPUID workaround for Intel 0F33/0F34 CPU */
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
@@ -758,6 +1104,7 @@ void __init mtrr_bp_init(void)
don't support PAE */
size_or_mask = 0xfff00000; /* 32 bits */
size_and_mask = 0;
+ phys_addr = 32;
}
} else {
switch (boot_cpu_data.x86_vendor) {
@@ -791,8 +1138,13 @@ void __init mtrr_bp_init(void)
if (mtrr_if) {
set_num_var_ranges();
init_table();
- if (use_intel())
+ if (use_intel()) {
get_mtrr_state();
+
+ if (mtrr_cleanup(phys_addr))
+ mtrr_if->set_all();
+
+ }
}
}
Index: linux-2.6/arch/x86/kernel/cpu/mtrr/mtrr.h
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ linux-2.6/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -81,6 +81,8 @@ void set_mtrr_done(struct set_mtrr_conte
void set_mtrr_cache_disable(struct set_mtrr_context *ctxt);
void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
+void fill_mtrr_var_range(unsigned int index,
+ u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
void get_mtrr_state(void);
extern void set_mtrr_ops(struct mtrr_ops * ops);
Index: linux-2.6/Documentation/kernel-parameters.txt
===================================================================
--- linux-2.6.orig/Documentation/kernel-parameters.txt
+++ linux-2.6/Documentation/kernel-parameters.txt
@@ -595,6 +595,16 @@ and is between 256 and 4096 characters.
See drivers/char/README.epca and
Documentation/digiepca.txt.
+ disable_mtrr_cleanup [X86]
+ By default the kernel will adjust mtrr from continuous
+ to discrete layout, to make x server driver could add
+ WB entry later. This parameter disables that behavior,
+ will not touch MTRRs.
+
+ mtrr_chunk_size=nn[KMG] [X86]
+ used for mtrr cleanup. It is largest continous chunk
+ that could hold holes aka. UC entries.
+
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
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists