summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig13
-rw-r--r--arch/x86/include/asm/agp.h4
-rw-r--r--arch/x86/include/asm/bootparam.h3
-rw-r--r--arch/x86/include/asm/cacheflush.h54
-rw-r--r--arch/x86/include/asm/fixmap.h3
-rw-r--r--arch/x86/include/asm/iomap.h9
-rw-r--r--arch/x86/include/asm/mtrr.h6
-rw-r--r--arch/x86/include/asm/pat.h5
-rw-r--r--arch/x86/include/asm/pci.h1
-rw-r--r--arch/x86/include/asm/percpu.h9
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--arch/x86/kernel/cpu/cpu_debug.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c8
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c2
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c46
-rw-r--r--arch/x86/kernel/cpu/perf_counter.c14
-rw-r--r--arch/x86/kernel/pci-dma.c4
-rw-r--r--arch/x86/kernel/quirks.c2
-rw-r--r--arch/x86/kernel/reboot.c7
-rw-r--r--arch/x86/kernel/setup.c23
-rw-r--r--arch/x86/kernel/setup_percpu.c364
-rw-r--r--arch/x86/kernel/smpboot.c16
-rw-r--r--arch/x86/kernel/tboot.c447
-rw-r--r--arch/x86/kernel/vmlinux.lds.S11
-rw-r--r--arch/x86/mm/iomap_32.c27
-rw-r--r--arch/x86/mm/ioremap.c18
-rw-r--r--arch/x86/mm/pageattr.c29
-rw-r--r--arch/x86/mm/pat.c353
-rw-r--r--arch/x86/pci/amd_bus.c64
-rw-r--r--arch/x86/pci/common.c69
-rw-r--r--arch/x86/power/cpu.c2
31 files changed, 1050 insertions, 568 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fc20fdc0f7f..e98e81a0497 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -150,7 +150,10 @@ config ARCH_HAS_CACHE_LINE_SIZE
config HAVE_SETUP_PER_CPU_AREA
def_bool y
-config HAVE_DYNAMIC_PER_CPU_AREA
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+ def_bool y
+
+config NEED_PER_CPU_PAGE_FIRST_CHUNK
def_bool y
config HAVE_CPUMASK_OF_CPU_MAP
@@ -179,6 +182,10 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
+config HAVE_INTEL_TXT
+ def_bool y
+ depends on EXPERIMENTAL && DMAR && ACPI
+
# Use the generic interrupt handling code in kernel/irq/:
config GENERIC_HARDIRQS
bool
@@ -1413,6 +1420,10 @@ config X86_PAT
If unsure, say Y.
+config ARCH_USES_PG_UNCACHED
+ def_bool y
+ depends on X86_PAT
+
config EFI
bool "EFI runtime service support"
depends on ACPI
diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h
index 9825cd64c9b..eec2a70d437 100644
--- a/arch/x86/include/asm/agp.h
+++ b/arch/x86/include/asm/agp.h
@@ -22,10 +22,6 @@
*/
#define flush_agp_cache() wbinvd()
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
/* GATT allocation. Returns/accepts GATT kernel virtual address. */
#define alloc_gatt_pages(order) \
((char *)__get_free_pages(GFP_KERNEL, (order)))
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 1724e8de317..6ca20218dd7 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -85,7 +85,8 @@ struct efi_info {
struct boot_params {
struct screen_info screen_info; /* 0x000 */
struct apm_bios_info apm_bios_info; /* 0x040 */
- __u8 _pad2[12]; /* 0x054 */
+ __u8 _pad2[4]; /* 0x054 */
+ __u64 tboot_addr; /* 0x058 */
struct ist_info ist_info; /* 0x060 */
__u8 _pad3[16]; /* 0x070 */
__u8 hd0_info[16]; /* obsolete! */ /* 0x080 */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index e55dfc1ad45..b54f6afe7ec 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -43,8 +43,58 @@ static inline void copy_from_user_page(struct vm_area_struct *vma,
memcpy(dst, src, len);
}
-#define PG_non_WB PG_arch_1
-PAGEFLAG(NonWB, non_WB)
+#define PG_WC PG_arch_1
+PAGEFLAG(WC, WC)
+
+#ifdef CONFIG_X86_PAT
+/*
+ * X86 PAT uses page flags WC and Uncached together to keep track of
+ * memory type of pages that have backing page struct. X86 PAT supports 3
+ * different memory types, _PAGE_CACHE_WB, _PAGE_CACHE_WC and
+ * _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not
+ * been changed from its default (value of -1 used to denote this).
+ * Note we do not support _PAGE_CACHE_UC here.
+ *
+ * Caller must hold memtype_lock for atomicity.
+ */
+static inline unsigned long get_page_memtype(struct page *pg)
+{
+ if (!PageUncached(pg) && !PageWC(pg))
+ return -1;
+ else if (!PageUncached(pg) && PageWC(pg))
+ return _PAGE_CACHE_WC;
+ else if (PageUncached(pg) && !PageWC(pg))
+ return _PAGE_CACHE_UC_MINUS;
+ else
+ return _PAGE_CACHE_WB;
+}
+
+static inline void set_page_memtype(struct page *pg, unsigned long memtype)
+{
+ switch (memtype) {
+ case _PAGE_CACHE_WC:
+ ClearPageUncached(pg);
+ SetPageWC(pg);
+ break;
+ case _PAGE_CACHE_UC_MINUS:
+ SetPageUncached(pg);
+ ClearPageWC(pg);
+ break;
+ case _PAGE_CACHE_WB:
+ SetPageUncached(pg);
+ SetPageWC(pg);
+ break;
+ default:
+ case -1:
+ ClearPageUncached(pg);
+ ClearPageWC(pg);
+ break;
+ }
+}
+#else
+static inline unsigned long get_page_memtype(struct page *pg) { return -1; }
+static inline void set_page_memtype(struct page *pg, unsigned long memtype) { }
+#endif
/*
* The set_memory_* API can be used to change various attributes of a virtual
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 7b2d71df39a..14f9890eb49 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -132,6 +132,9 @@ enum fixed_addresses {
#ifdef CONFIG_X86_32
FIX_WP_TEST,
#endif
+#ifdef CONFIG_INTEL_TXT
+ FIX_TBOOT_BASE,
+#endif
__end_of_fixed_addresses
};
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index 0e9fe1d9d97..f35eb45d657 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -26,13 +26,16 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
-int
-is_io_mapping_possible(resource_size_t base, unsigned long size);
-
void *
iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
void
iounmap_atomic(void *kvaddr, enum km_type type);
+int
+iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
+
+void
+iomap_free(resource_size_t base, unsigned long size);
+
#endif /* _ASM_X86_IOMAP_H */
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index a51ada8467d..4365ffdb461 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -121,6 +121,9 @@ extern int mtrr_del_page(int reg, unsigned long base, unsigned long size);
extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
extern void mtrr_ap_init(void);
extern void mtrr_bp_init(void);
+extern void set_mtrr_aps_delayed_init(void);
+extern void mtrr_aps_init(void);
+extern void mtrr_bp_restore(void);
extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
extern int amd_special_default_mtrr(void);
# else
@@ -161,6 +164,9 @@ static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
#define mtrr_ap_init() do {} while (0)
#define mtrr_bp_init() do {} while (0)
+#define set_mtrr_aps_delayed_init() do {} while (0)
+#define mtrr_aps_init() do {} while (0)
+#define mtrr_bp_restore() do {} while (0)
# endif
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 7af14e512f9..e2c1668dde7 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -19,4 +19,9 @@ extern int free_memtype(u64 start, u64 end);
extern int kernel_map_sync_memtype(u64 base, unsigned long size,
unsigned long flag);
+int io_reserve_memtype(resource_size_t start, resource_size_t end,
+ unsigned long *type);
+
+void io_free_memtype(resource_size_t start, resource_size_t end);
+
#endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 1ff685ca221..f76a162c082 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -48,7 +48,6 @@ extern unsigned int pcibios_assign_all_busses(void);
#else
#define pcibios_assign_all_busses() 0
#endif
-#define pcibios_scan_all_fns(a, b) 0
extern unsigned long pci_mem_start;
#define PCIBIOS_MIN_IO 0x1000
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 04eacefcfd2..b65a36defeb 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -168,15 +168,6 @@ do { \
/* We can use this directly for local CPU (faster). */
DECLARE_PER_CPU(unsigned long, this_cpu_off);
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-void *pcpu_lpage_remapped(void *kaddr);
-#else
-static inline void *pcpu_lpage_remapped(void *kaddr)
-{
- return NULL;
-}
-#endif
-
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 430d5b24af7..832cb838cb4 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_X86_DS_SELFTEST) += ds_selftest.o
obj-$(CONFIG_X86_32) += tls.o
obj-$(CONFIG_IA32_EMULATION) += tls.o
obj-y += step.o
+obj-$(CONFIG_INTEL_TXT) += tboot.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += cpu/
obj-y += acpi/
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index 6b2a52dd040..dca325c0399 100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
@@ -30,8 +30,8 @@
#include <asm/apic.h>
#include <asm/desc.h>
-static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
-static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
+static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
+static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
static DEFINE_PER_CPU(int, cpu_priv_count);
static DEFINE_MUTEX(cpu_debug_lock);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9bfe9d2ea61..fdd51b55435 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1101,7 +1101,7 @@ void mce_log_therm_throt_event(__u64 status)
*/
static int check_interval = 5 * 60; /* 5 minutes */
-static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
+static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);
static void mcheck_timer(unsigned long data)
@@ -1120,7 +1120,7 @@ static void mcheck_timer(unsigned long data)
* Alert userspace if needed. If we logged an MCE, reduce the
* polling interval, otherwise increase the polling interval.
*/
- n = &__get_cpu_var(next_interval);
+ n = &__get_cpu_var(mce_next_interval);
if (mce_notify_irq())
*n = max(*n/2, HZ/100);
else
@@ -1335,7 +1335,7 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
static void mce_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- int *n = &__get_cpu_var(next_interval);
+ int *n = &__get_cpu_var(mce_next_interval);
if (mce_ignore_ce)
return;
@@ -1935,7 +1935,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
t->expires = round_jiffies(jiffies +
- __get_cpu_var(next_interval));
+ __get_cpu_var(mce_next_interval));
add_timer_on(t, cpu);
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 1fecba404fd..8cd5224943b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -69,7 +69,7 @@ struct threshold_bank {
struct threshold_block *blocks;
cpumask_var_t cpus;
};
-static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
+static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
#ifdef CONFIG_SMP
static unsigned char shared_bank[NR_BANKS] = {
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 7af0f88a416..84e83de5457 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -58,6 +58,7 @@ unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
static DEFINE_MUTEX(mtrr_mutex);
u64 size_or_mask, size_and_mask;
+static bool mtrr_aps_delayed_init;
static struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM];
@@ -163,7 +164,10 @@ static void ipi_handler(void *info)
if (data->smp_reg != ~0U) {
mtrr_if->set(data->smp_reg, data->smp_base,
data->smp_size, data->smp_type);
- } else {
+ } else if (mtrr_aps_delayed_init) {
+ /*
+ * Initialize the MTRRs inaddition to the synchronisation.
+ */
mtrr_if->set_all();
}
@@ -265,6 +269,8 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
*/
if (reg != ~0U)
mtrr_if->set(reg, base, size, type);
+ else if (!mtrr_aps_delayed_init)
+ mtrr_if->set_all();
/* Wait for the others */
while (atomic_read(&data.count))
@@ -721,9 +727,7 @@ void __init mtrr_bp_init(void)
void mtrr_ap_init(void)
{
- unsigned long flags;
-
- if (!mtrr_if || !use_intel())
+ if (!use_intel() || mtrr_aps_delayed_init)
return;
/*
* Ideally we should hold mtrr_mutex here to avoid mtrr entries
@@ -738,11 +742,7 @@ void mtrr_ap_init(void)
* 2. cpu hotadd time. We let mtrr_add/del_page hold cpuhotplug
* lock to prevent mtrr entry changes
*/
- local_irq_save(flags);
-
- mtrr_if->set_all();
-
- local_irq_restore(flags);
+ set_mtrr(~0U, 0, 0, 0);
}
/**
@@ -753,6 +753,34 @@ void mtrr_save_state(void)
smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1);
}
+void set_mtrr_aps_delayed_init(void)
+{
+ if (!use_intel())
+ return;
+
+ mtrr_aps_delayed_init = true;
+}
+
+/*
+ * MTRR initialization for all AP's
+ */
+void mtrr_aps_init(void)
+{
+ if (!use_intel())
+ return;
+
+ set_mtrr(~0U, 0, 0, 0);
+ mtrr_aps_delayed_init = false;
+}
+
+void mtrr_bp_restore(void)
+{
+ if (!use_intel())
+ return;
+
+ mtrr_if->set_all();
+}
+
static int __init mtrr_init_finialize(void)
{
if (!mtrr_if)
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index f9cd0849bd4..2732e2c1e4d 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -1211,7 +1211,7 @@ amd_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
x86_pmu_disable_counter(hwc, idx);
}
-static DEFINE_PER_CPU(u64, prev_left[X86_PMC_IDX_MAX]);
+static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
/*
* Set the next IRQ period, based on the hwc->period_left value.
@@ -1253,7 +1253,7 @@ x86_perf_counter_set_period(struct perf_counter *counter,
if (left > x86_pmu.max_period)
left = x86_pmu.max_period;
- per_cpu(prev_left[idx], smp_processor_id()) = left;
+ per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
/*
* The hw counter starts counting from this counter offset,
@@ -1470,7 +1470,7 @@ void perf_counter_print_debug(void)
rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
rdmsrl(x86_pmu.perfctr + idx, pmc_count);
- prev_left = per_cpu(prev_left[idx], cpu);
+ prev_left = per_cpu(pmc_prev_left[idx], cpu);
pr_info("CPU#%d: gen-PMC%d ctrl: %016llx\n",
cpu, idx, pmc_ctrl);
@@ -2110,8 +2110,8 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
entry->ip[entry->nr++] = ip;
}
-static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
+static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
static DEFINE_PER_CPU(int, in_nmi_frame);
@@ -2264,9 +2264,9 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
struct perf_callchain_entry *entry;
if (in_nmi())
- entry = &__get_cpu_var(nmi_entry);
+ entry = &__get_cpu_var(pmc_nmi_entry);
else
- entry = &__get_cpu_var(irq_entry);
+ entry = &__get_cpu_var(pmc_irq_entry);
entry->nr = 0;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index d71c8655905..64b838eac18 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -225,10 +225,8 @@ static __init int iommu_setup(char *p)
if (!strncmp(p, "soft", 4))
swiotlb = 1;
#endif
- if (!strncmp(p, "pt", 2)) {
+ if (!strncmp(p, "pt", 2))
iommu_pass_through = 1;
- return 1;
- }
gart_parse_options(p);
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index af71d06624b..6c3b2c6fd77 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -508,7 +508,7 @@ static void __init quirk_amd_nb_node(struct pci_dev *dev)
pci_read_config_dword(nb_ht, 0x60, &val);
set_dev_node(&dev->dev, val & 7);
- pci_dev_put(dev);
+ pci_dev_put(nb_ht);
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB,
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index a06e8d10184..27349f92a6d 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -4,6 +4,7 @@
#include <linux/pm.h>
#include <linux/efi.h>
#include <linux/dmi.h>
+#include <linux/tboot.h>
#include <acpi/reboot.h>
#include <asm/io.h>
#include <asm/apic.h>
@@ -508,6 +509,8 @@ static void native_machine_emergency_restart(void)
if (reboot_emergency)
emergency_vmx_disable_all();
+ tboot_shutdown(TB_SHUTDOWN_REBOOT);
+
/* Tell the BIOS if we want cold or warm reboot */
*((unsigned short *)__va(0x472)) = reboot_mode;
@@ -634,6 +637,8 @@ static void native_machine_halt(void)
/* stop other cpus and apics */
machine_shutdown();
+ tboot_shutdown(TB_SHUTDOWN_HALT);
+
/* stop this cpu */
stop_this_cpu(NULL);
}
@@ -645,6 +650,8 @@ static void native_machine_power_off(void)
machine_shutdown();
pm_power_off();
}
+ /* a fallback in case there is no PM info available */
+ tboot_shutdown(TB_SHUTDOWN_HALT);
}
struct machine_ops machine_ops = {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 63f32d220ef..19f15c4076f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -66,6 +66,7 @@
#include <linux/percpu.h>
#include <linux/crash_dump.h>
+#include <linux/tboot.h>
#include <video/edid.h>
@@ -711,6 +712,21 @@ void __init setup_arch(char **cmdline_p)
printk(KERN_INFO "Command line: %s\n", boot_command_line);
#endif
+ strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+ *cmdline_p = command_line;
+
+#ifdef CONFIG_X86_64
+ /*
+ * Must call this twice: Once just to detect whether hardware doesn't
+ * support NX (so that the early EHCI debug console setup can safely
+ * call set_fixmap(), and then again after parsing early parameters to
+ * honor the respective command line option.
+ */
+ check_efer();
+#endif
+
+ parse_early_param();
+
/* VMI may relocate the fixmap; do this before touching ioremap area */
vmi_init();
@@ -793,11 +809,6 @@ void __init setup_arch(char **cmdline_p)
#endif
#endif
- strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
- *cmdline_p = command_line;
-
- parse_early_param();
-
#ifdef CONFIG_X86_64
check_efer();
#endif
@@ -977,6 +988,8 @@ void __init setup_arch(char **cmdline_p)
paravirt_pagetable_setup_done(swapper_pg_dir);
paravirt_post_allocator_init();
+ tboot_probe();
+
#ifdef CONFIG_X86_64
map_vsyscall();
#endif
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 07d81916f21..d559af913e1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -55,6 +55,7 @@ EXPORT_SYMBOL(__per_cpu_offset);
#define PERCPU_FIRST_CHUNK_RESERVE 0
#endif
+#ifdef CONFIG_X86_32
/**
* pcpu_need_numa - determine percpu allocation needs to consider NUMA
*
@@ -83,6 +84,7 @@ static bool __init pcpu_need_numa(void)
#endif
return false;
}
+#endif
/**
* pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
@@ -124,308 +126,35 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
}
/*
- * Large page remap allocator
- *
- * This allocator uses PMD page as unit. A PMD page is allocated for
- * each cpu and each is remapped into vmalloc area using PMD mapping.
- * As PMD page is quite large, only part of it is used for the first
- * chunk. Unused part is returned to the bootmem allocator.
- *
- * So, the PMD pages are mapped twice - once to the physical mapping
- * and to the vmalloc area for the first percpu chunk. The double
- * mapping does add one more PMD TLB entry pressure but still is much
- * better than only using 4k mappings while still being NUMA friendly.
+ * Helpers for first chunk memory allocation
*/
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-struct pcpul_ent {
- unsigned int cpu;
- void *ptr;
-};
-
-static size_t pcpul_size;
-static struct pcpul_ent *pcpul_map;
-static struct vm_struct pcpul_vm;
-
-static struct page * __init pcpul_get_page(unsigned int cpu, int pageno)
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
{
- size_t off = (size_t)pageno << PAGE_SHIFT;
-
- if (off >= pcpul_size)
- return NULL;
-
- return virt_to_page(pcpul_map[cpu].ptr + off);
+ return pcpu_alloc_bootmem(cpu, size, align);
}
-static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
+static void __init pcpu_fc_free(void *ptr, size_t size)
{
- size_t map_size, dyn_size;
- unsigned int cpu;
- int i, j;
- ssize_t ret;
-
- if (!chosen) {
- size_t vm_size = VMALLOC_END - VMALLOC_START;
- size_t tot_size = nr_cpu_ids * PMD_SIZE;
-
- /* on non-NUMA, embedding is better */
- if (!pcpu_need_numa())
- return -EINVAL;
-
- /* don't consume more than 20% of vmalloc area */
- if (tot_size > vm_size / 5) {
- pr_info("PERCPU: too large chunk size %zuMB for "
- "large page remap\n", tot_size >> 20);
- return -EINVAL;
- }
- }
-
- /* need PSE */
- if (!cpu_has_pse) {
- pr_warning("PERCPU: lpage allocator requires PSE\n");
- return -EINVAL;
- }
-
- /*
- * Currently supports only single page. Supporting multiple
- * pages won't be too difficult if it ever becomes necessary.
- */
- pcpul_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
- PERCPU_DYNAMIC_RESERVE);
- if (pcpul_size > PMD_SIZE) {
- pr_warning("PERCPU: static data is larger than large page, "
- "can't use large page\n");
- return -EINVAL;
- }
- dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
-
- /* allocate pointer array and alloc large pages */
- map_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpul_map[0]));
- pcpul_map = alloc_bootmem(map_size);
-
- for_each_possible_cpu(cpu) {
- pcpul_map[cpu].cpu = cpu;
- pcpul_map[cpu].ptr = pcpu_alloc_bootmem(cpu, PMD_SIZE,
- PMD_SIZE);
- if (!pcpul_map[cpu].ptr) {
- pr_warning("PERCPU: failed to allocate large page "
- "for cpu%u\n", cpu);
- goto enomem;
- }
-
- /*
- * Only use pcpul_size bytes and give back the rest.
- *
- * Ingo: The 2MB up-rounding bootmem is needed to make
- * sure the partial 2MB page is still fully RAM - it's
- * not well-specified to have a PAT-incompatible area
- * (unmapped RAM, device memory, etc.) in that hole.
- */
- free_bootmem(__pa(pcpul_map[cpu].ptr + pcpul_size),
- PMD_SIZE - pcpul_size);
-
- memcpy(pcpul_map[cpu].ptr, __per_cpu_load, static_size);
- }
-
- /* allocate address and map */
- pcpul_vm.flags = VM_ALLOC;
- pcpul_vm.size = nr_cpu_ids * PMD_SIZE;
- vm_area_register_early(&pcpul_vm, PMD_SIZE);
-
- for_each_possible_cpu(cpu) {
- pmd_t *pmd, pmd_v;
-
- pmd = populate_extra_pmd((unsigned long)pcpul_vm.addr +
- cpu * PMD_SIZE);
- pmd_v = pfn_pmd(page_to_pfn(virt_to_page(pcpul_map[cpu].ptr)),
- PAGE_KERNEL_LARGE);
- set_pmd(pmd, pmd_v);
- }
-
- /* we're ready, commit */
- pr_info("PERCPU: Remapped at %p with large pages, static data "
- "%zu bytes\n", pcpul_vm.addr, static_size);
-
- ret = pcpu_setup_first_chunk(pcpul_get_page, static_size,
- PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
- PMD_SIZE, pcpul_vm.addr, NULL);
-
- /* sort pcpul_map array for pcpu_lpage_remapped() */
- for (i = 0; i < nr_cpu_ids - 1; i++)
- for (j = i + 1; j < nr_cpu_ids; j++)
- if (pcpul_map[i].ptr > pcpul_map[j].ptr) {
- struct pcpul_ent tmp = pcpul_map[i];
- pcpul_map[i] = pcpul_map[j];
- pcpul_map[j] = tmp;
- }
-
- return ret;
-
-enomem:
- for_each_possible_cpu(cpu)
- if (pcpul_map[cpu].ptr)
- free_bootmem(__pa(pcpul_map[cpu].ptr), pcpul_size);
- free_bootmem(__pa(pcpul_map), map_size);
- return -ENOMEM;
+ free_bootmem(__pa(ptr), size);
}
-/**
- * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area
- * @kaddr: the kernel address in question
- *
- * Determine whether @kaddr falls in the pcpul recycled area. This is
- * used by pageattr to detect VM aliases and break up the pcpu PMD
- * mapping such that the same physical page is not mapped under
- * different attributes.
- *
- * The recycled area is always at the tail of a partially used PMD
- * page.
- *
- * RETURNS:
- * Address of corresponding remapped pcpu address if match is found;
- * otherwise, NULL.
- */
-void *pcpu_lpage_remapped(void *kaddr)
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
{
- void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK);
- unsigned long offset = (unsigned long)kaddr & ~PMD_MASK;
- int left = 0, right = nr_cpu_ids - 1;
- int pos;
-
- /* pcpul in use at all? */
- if (!pcpul_map)
- return NULL;
-
- /* okay, perform binary search */
- while (left <= right) {
- pos = (left + right) / 2;
-
- if (pcpul_map[pos].ptr < pmd_addr)
- left = pos + 1;
- else if (pcpul_map[pos].ptr > pmd_addr)
- right = pos - 1;
- else {
- /* it shouldn't be in the area for the first chunk */
- WARN_ON(offset < pcpul_size);
-
- return pcpul_vm.addr +
- pcpul_map[pos].cpu * PMD_SIZE + offset;
- }
- }
-
- return NULL;
-}
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ if (early_cpu_to_node(from) == early_cpu_to_node(to))
+ return LOCAL_DISTANCE;
+ else
+ return REMOTE_DISTANCE;
#else
-static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
-{
- return -EINVAL;
-}
+ return LOCAL_DISTANCE;
#endif
-
-/*
- * Embedding allocator
- *
- * The first chunk is sized to just contain the static area plus
- * module and dynamic reserves and embedded into linear physical
- * mapping so that it can use PMD mapping without additional TLB
- * pressure.
- */
-static ssize_t __init setup_pcpu_embed(size_t static_size, bool chosen)
-{
- size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
-
- /*
- * If large page isn't supported, there's no benefit in doing
- * this. Also, embedding allocation doesn't play well with
- * NUMA.
- */
- if (!chosen && (!cpu_has_pse || pcpu_need_numa()))
- return -EINVAL;
-
- return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
- reserve - PERCPU_FIRST_CHUNK_RESERVE, -1);
}
-/*
- * 4k page allocator
- *
- * This is the basic allocator. Static percpu area is allocated
- * page-by-page and most of initialization is done by the generic
- * setup function.
- */
-static struct page **pcpu4k_pages __initdata;
-static int pcpu4k_nr_static_pages __initdata;
-
-static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno)
-{
- if (pageno < pcpu4k_nr_static_pages)
- return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno];
- return NULL;
-}
-
-static void __init pcpu4k_populate_pte(unsigned long addr)
+static void __init pcpup_populate_pte(unsigned long addr)
{
populate_extra_pte(addr);
}
-static ssize_t __init setup_pcpu_4k(size_t static_size)
-{
- size_t pages_size;
- unsigned int cpu;
- int i, j;
- ssize_t ret;
-
- pcpu4k_nr_static_pages = PFN_UP(static_size);
-
- /* unaligned allocations can't be freed, round up to page size */
- pages_size = PFN_ALIGN(pcpu4k_nr_static_pages * nr_cpu_ids
- * sizeof(pcpu4k_pages[0]));
- pcpu4k_pages = alloc_bootmem(pages_size);
-
- /* allocate and copy */
- j = 0;
- for_each_possible_cpu(cpu)
- for (i = 0; i < pcpu4k_nr_static_pages; i++) {
- void *ptr;
-
- ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE);
- if (!ptr) {
- pr_warning("PERCPU: failed to allocate "
- "4k page for cpu%u\n", cpu);
- goto enomem;
- }
-
- memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE);
- pcpu4k_pages[j++] = virt_to_page(ptr);
- }
-
- /* we're ready, commit */
- pr_info("PERCPU: Allocated %d 4k pages, static data %zu bytes\n",
- pcpu4k_nr_static_pages, static_size);
-
- ret = pcpu_setup_first_chunk(pcpu4k_get_page, static_size,
- PERCPU_FIRST_CHUNK_RESERVE, -1,
- -1, NULL, pcpu4k_populate_pte);
- goto out_free_ar;
-
-enomem:
- while (--j >= 0)
- free_bootmem(__pa(page_address(pcpu4k_pages[j])), PAGE_SIZE);
- ret = -ENOMEM;
-out_free_ar:
- free_bootmem(__pa(pcpu4k_pages), pages_size);
- return ret;
-}
-
-/* for explicit first chunk allocator selection */
-static char pcpu_chosen_alloc[16] __initdata;
-
-static int __init percpu_alloc_setup(char *str)
-{
- strncpy(pcpu_chosen_alloc, str, sizeof(pcpu_chosen_alloc) - 1);
- return 0;
-}
-early_param("percpu_alloc", percpu_alloc_setup);
-
static inline void setup_percpu_segment(int cpu)
{
#ifdef CONFIG_X86_32
@@ -441,52 +170,49 @@ static inline void setup_percpu_segment(int cpu)
void __init setup_per_cpu_areas(void)
{
- size_t static_size = __per_cpu_end - __per_cpu_start;
unsigned int cpu;
unsigned long delta;
- size_t pcpu_unit_size;
- ssize_t ret;
+ int rc;
pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
/*
- * Allocate percpu area. If PSE is supported, try to make use
- * of large page mappings. Please read comments on top of
- * each allocator for details.
+ * Allocate percpu area. Embedding allocator is our favorite;
+ * however, on NUMA configurations, it can result in very
+ * sparse unit mapping and vmalloc area isn't spacious enough
+ * on 32bit. Use page in that case.
*/
- ret = -EINVAL;
- if (strlen(pcpu_chosen_alloc)) {
- if (strcmp(pcpu_chosen_alloc, "4k")) {
- if (!strcmp(pcpu_chosen_alloc, "lpage"))
- ret = setup_pcpu_lpage(static_size, true);
- else if (!strcmp(pcpu_chosen_alloc, "embed"))
- ret = setup_pcpu_embed(static_size, true);
- else
- pr_warning("PERCPU: unknown allocator %s "
- "specified\n", pcpu_chosen_alloc);
- if (ret < 0)
- pr_warning("PERCPU: %s allocator failed (%zd), "
- "falling back to 4k\n",
- pcpu_chosen_alloc, ret);
- }
- } else {
- ret = setup_pcpu_lpage(static_size, false);
- if (ret < 0)
- ret = setup_pcpu_embed(static_size, false);
+#ifdef CONFIG_X86_32
+ if (pcpu_chosen_fc == PCPU_FC_AUTO && pcpu_need_numa())
+ pcpu_chosen_fc = PCPU_FC_PAGE;
+#endif
+ rc = -EINVAL;
+ if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+ const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
+ const size_t dyn_size = PERCPU_MODULE_RESERVE +
+ PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+
+ rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+ dyn_size, atom_size,
+ pcpu_cpu_distance,
+ pcpu_fc_alloc, pcpu_fc_free);
+ if (rc < 0)
+ pr_warning("PERCPU: %s allocator failed (%d), "
+ "falling back to page size\n",
+ pcpu_fc_names[pcpu_chosen_fc], rc);
}
- if (ret < 0)
- ret = setup_pcpu_4k(static_size);
- if (ret < 0)
- panic("cannot allocate static percpu area (%zu bytes, err=%zd)",
- static_size, ret);
-
- pcpu_unit_size = ret;
+ if (rc < 0)
+ rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+ pcpu_fc_alloc, pcpu_fc_free,
+ pcpup_populate_pte);
+ if (rc < 0)
+ panic("cannot initialize percpu area (err=%d)", rc);
/* alrighty, percpu areas up and running */
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu) {
- per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size;
+ per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
per_cpu(cpu_number, cpu) = cpu;
setup_percpu_segment(cpu);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c36cc1452cd..a25eeec0008 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -47,6 +47,7 @@
#include <linux/bootmem.h>
#include <linux/err.h>
#include <linux/nmi.h>
+#include <linux/tboot.h>
#include <asm/acpi.h>
#include <asm/desc.h>
@@ -1117,9 +1118,22 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
if (is_uv_system())
uv_system_init();
+
+ set_mtrr_aps_delayed_init();
out:
preempt_enable();
}
+
+void arch_enable_nonboot_cpus_begin(void)
+{
+ set_mtrr_aps_delayed_init();
+}
+
+void arch_enable_nonboot_cpus_end(void)
+{
+ mtrr_aps_init();
+}
+
/*
* Early setup to make printk work.
*/
@@ -1141,6 +1155,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
setup_ioapic_dest();
#endif
check_nmi_watchdog();
+ mtrr_aps_init();
}
static int __initdata setup_possible_cpus = -1;
@@ -1318,6 +1333,7 @@ void play_dead_common(void)
void native_play_dead(void)
{
play_dead_common();
+ tboot_shutdown(TB_SHUTDOWN_WFS);
wbinvd_halt();
}
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
new file mode 100644
index 00000000000..86c9f91b48a
--- /dev/null
+++ b/arch/x86/kernel/tboot.c
@@ -0,0 +1,447 @@
+/*
+ * tboot.c: main implementation of helper functions used by kernel for
+ * runtime support of Intel(R) Trusted Execution Technology
+ *
+ * Copyright (c) 2006-2009, Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+
+#include <linux/dma_remapping.h>
+#include <linux/init_task.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/dmar.h>
+#include <linux/cpu.h>
+#include <linux/pfn.h>
+#include <linux/mm.h>
+#include <linux/tboot.h>
+
+#include <asm/trampoline.h>
+#include <asm/processor.h>
+#include <asm/bootparam.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/fixmap.h>
+#include <asm/proto.h>
+#include <asm/setup.h>
+#include <asm/e820.h>
+#include <asm/io.h>
+
+#include "acpi/realmode/wakeup.h"
+
+/* Global pointer to shared data; NULL means no measured launch. */
+struct tboot *tboot __read_mostly;
+
+/* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */
+#define AP_WAIT_TIMEOUT 1
+
+#undef pr_fmt
+#define pr_fmt(fmt) "tboot: " fmt
+
+static u8 tboot_uuid[16] __initdata = TBOOT_UUID;
+
+void __init tboot_probe(void)
+{
+ /* Look for valid page-aligned address for shared page. */
+ if (!boot_params.tboot_addr)
+ return;
+ /*
+ * also verify that it is mapped as we expect it before calling
+ * set_fixmap(), to reduce chance of garbage value causing crash
+ */
+ if (!e820_any_mapped(boot_params.tboot_addr,
+ boot_params.tboot_addr, E820_RESERVED)) {
+ pr_warning("non-0 tboot_addr but it is not of type E820_RESERVED\n");
+ return;
+ }
+
+ /* only a natively booted kernel should be using TXT */
+ if (paravirt_enabled()) {
+ pr_warning("non-0 tboot_addr but pv_ops is enabled\n");
+ return;
+ }
+
+ /* Map and check for tboot UUID. */
+ set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr);
+ tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE);
+ if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) {
+ pr_warning("tboot at 0x%llx is invalid\n",
+ boot_params.tboot_addr);
+ tboot = NULL;
+ return;
+ }
+ if (tboot->version < 5) {
+ pr_warning("tboot version is invalid: %u\n", tboot->version);
+ tboot = NULL;
+ return;
+ }
+
+ pr_info("found shared page at phys addr 0x%llx:\n",
+ boot_params.tboot_addr);
+ pr_debug("version: %d\n", tboot->version);
+ pr_debug("log_addr: 0x%08x\n", tboot->log_addr);
+ pr_debug("shutdown_entry: 0x%x\n", tboot->shutdown_entry);
+ pr_debug("tboot_base: 0x%08x\n", tboot->tboot_base);
+ pr_debug("tboot_size: 0x%x\n", tboot->tboot_size);
+}
+
+static pgd_t *tboot_pg_dir;
+static struct mm_struct tboot_mm = {
+ .mm_rb = RB_ROOT,
+ .pgd = swapper_pg_dir,
+ .mm_users = ATOMIC_INIT(2),
+ .mm_count = ATOMIC_INIT(1),
+ .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem),
+ .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+ .mmlist = LIST_HEAD_INIT(init_mm.mmlist),
+ .cpu_vm_mask = CPU_MASK_ALL,
+};
+
+static inline void switch_to_tboot_pt(void)
+{
+ write_cr3(virt_to_phys(tboot_pg_dir));
+}
+
+static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
+ pgprot_t prot)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = pgd_offset(&tboot_mm, vaddr);
+ pud = pud_alloc(&tboot_mm, pgd, vaddr);
+ if (!pud)
+ return -1;
+ pmd = pmd_alloc(&tboot_mm, pud, vaddr);
+ if (!pmd)
+ return -1;
+ pte = pte_alloc_map(&tboot_mm, pmd, vaddr);
+ if (!pte)
+ return -1;
+ set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
+ pte_unmap(pte);
+ return 0;
+}
+
+static int map_tboot_pages(unsigned long vaddr, unsigned long start_pfn,
+ unsigned long nr)
+{
+ /* Reuse the original kernel mapping */
+ tboot_pg_dir = pgd_alloc(&tboot_mm);
+ if (!tboot_pg_dir)
+ return -1;
+
+ for (; nr > 0; nr--, vaddr += PAGE_SIZE, start_pfn++) {
+ if (map_tboot_page(vaddr, start_pfn, PAGE_KERNEL_EXEC))
+ return -1;
+ }
+
+ return 0;
+}
+
+static void tboot_create_trampoline(void)
+{
+ u32 map_base, map_size;
+
+ /* Create identity map for tboot shutdown code. */
+ map_base = PFN_DOWN(tboot->tboot_base);
+ map_size = PFN_UP(tboot->tboot_size);
+ if (map_tboot_pages(map_base << PAGE_SHIFT, map_base, map_size))
+ panic("tboot: Error mapping tboot pages (mfns) @ 0x%x, 0x%x\n",
+ map_base, map_size);
+}
+
+#ifdef CONFIG_ACPI_SLEEP
+
+static void add_mac_region(phys_addr_t start, unsigned long size)
+{
+ struct tboot_mac_region *mr;
+ phys_addr_t end = start + size;
+
+ if (start && size) {
+ mr = &tboot->mac_regions[tboot->num_mac_regions++];
+ mr->start = round_down(start, PAGE_SIZE);
+ mr->size = round_up(end, PAGE_SIZE) - mr->start;
+ }
+}
+
+static int tboot_setup_sleep(void)
+{
+ tboot->num_mac_regions = 0;
+
+ /* S3 resume code */
+ add_mac_region(acpi_wakeup_address, WAKEUP_SIZE);
+
+#ifdef CONFIG_X86_TRAMPOLINE
+ /* AP trampoline code */
+ add_mac_region(virt_to_phys(trampoline_base), TRAMPOLINE_SIZE);
+#endif
+
+ /* kernel code + data + bss */
+ add_mac_region(virt_to_phys(_text), _end - _text);
+
+ tboot->acpi_sinfo.kernel_s3_resume_vector = acpi_wakeup_address;
+
+ return 0;
+}
+
+#else /* no CONFIG_ACPI_SLEEP */
+
+static int tboot_setup_sleep(void)
+{
+ /* S3 shutdown requested, but S3 not supported by the kernel... */
+ BUG();
+ return -1;
+}
+
+#endif
+
+void tboot_shutdown(u32 shutdown_type)
+{
+ void (*shutdown)(void);
+
+ if (!tboot_enabled())
+ return;
+
+ /*
+ * if we're being called before the 1:1 mapping is set up then just
+ * return and let the normal shutdown happen; this should only be
+ * due to very early panic()
+ */
+ if (!tboot_pg_dir)
+ return;
+
+ /* if this is S3 then set regions to MAC */
+ if (shutdown_type == TB_SHUTDOWN_S3)
+ if (tboot_setup_sleep())
+ return;
+
+ tboot->shutdown_type = shutdown_type;
+
+ switch_to_tboot_pt();
+
+ shutdown = (void(*)(void))(unsigned long)tboot->shutdown_entry;
+ shutdown();
+
+ /* should not reach here */
+ while (1)
+ halt();
+}
+
+static void tboot_copy_fadt(const struct acpi_table_fadt *fadt)
+{
+#define TB_COPY_GAS(tbg, g) \
+ tbg.space_id = g.space_id; \
+ tbg.bit_width = g.bit_width; \
+ tbg.bit_offset = g.bit_offset; \
+ tbg.access_width = g.access_width; \
+ tbg.address = g.address;
+
+ TB_COPY_GAS(tboot->acpi_sinfo.pm1a_cnt_blk, fadt->xpm1a_control_block);
+ TB_COPY_GAS(tboot->acpi_sinfo.pm1b_cnt_blk, fadt->xpm1b_control_block);
+ TB_COPY_GAS(tboot->acpi_sinfo.pm1a_evt_blk, fadt->xpm1a_event_block);
+ TB_COPY_GAS(tboot->acpi_sinfo.pm1b_evt_blk, fadt->xpm1b_event_block);
+
+ /*
+ * We need phys addr of waking vector, but can't use virt_to_phys() on
+ * &acpi_gbl_FACS because it is ioremap'ed, so calc from FACS phys
+ * addr.
+ */
+ tboot->acpi_sinfo.wakeup_vector = fadt->facs +
+ offsetof(struct acpi_table_facs, firmware_waking_vector);
+}
+
+void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
+{
+ static u32 acpi_shutdown_map[ACPI_S_STATE_COUNT] = {
+ /* S0,1,2: */ -1, -1, -1,
+ /* S3: */ TB_SHUTDOWN_S3,
+ /* S4: */ TB_SHUTDOWN_S4,
+ /* S5: */ TB_SHUTDOWN_S5 };
+
+ if (!tboot_enabled())
+ return;
+
+ tboot_copy_fadt(&acpi_gbl_FADT);
+ tboot->acpi_sinfo.pm1a_cnt_val = pm1a_control;
+ tboot->acpi_sinfo.pm1b_cnt_val = pm1b_control;
+ /* we always use the 32b wakeup vector */
+ tboot->acpi_sinfo.vector_width = 32;
+
+ if (sleep_state >= ACPI_S_STATE_COUNT ||
+ acpi_shutdown_map[sleep_state] == -1) {
+ pr_warning("unsupported sleep state 0x%x\n", sleep_state);
+ return;
+ }
+
+ tboot_shutdown(acpi_shutdown_map[sleep_state]);
+}
+
+static atomic_t ap_wfs_count;
+
+static int tboot_wait_for_aps(int num_aps)
+{
+ unsigned long timeout;
+
+ timeout = AP_WAIT_TIMEOUT*HZ;
+ while (atomic_read((atomic_t *)&tboot->num_in_wfs) != num_aps &&
+ timeout) {
+ mdelay(1);
+ timeout--;
+ }
+
+ if (timeout)
+ pr_warning("tboot wait for APs timeout\n");
+
+ return !(atomic_read((atomic_t *)&tboot->num_in_wfs) == num_aps);
+}
+
+static int __cpuinit tboot_cpu_callback(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ switch (action) {
+ case CPU_DYING:
+ atomic_inc(&ap_wfs_count);
+ if (num_online_cpus() == 1)
+ if (tboot_wait_for_aps(atomic_read(&ap_wfs_count)))
+ return NOTIFY_BAD;
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block tboot_cpu_notifier __cpuinitdata =
+{
+ .notifier_call = tboot_cpu_callback,
+};
+
+static __init int tboot_late_init(void)
+{
+ if (!tboot_enabled())
+ return 0;
+
+ tboot_create_trampoline();
+
+ atomic_set(&ap_wfs_count, 0);
+ register_hotcpu_notifier(&tboot_cpu_notifier);
+ return 0;
+}
+
+late_initcall(tboot_late_init);
+
+/*
+ * TXT configuration registers (offsets from TXT_{PUB, PRIV}_CONFIG_REGS_BASE)
+ */
+
+#define TXT_PUB_CONFIG_REGS_BASE 0xfed30000
+#define TXT_PRIV_CONFIG_REGS_BASE 0xfed20000
+
+/* # pages for each config regs space - used by fixmap */
+#define NR_TXT_CONFIG_PAGES ((TXT_PUB_CONFIG_REGS_BASE - \
+ TXT_PRIV_CONFIG_REGS_BASE) >> PAGE_SHIFT)
+
+/* offsets from pub/priv config space */
+#define TXTCR_HEAP_BASE 0x0300
+#define TXTCR_HEAP_SIZE 0x0308
+
+#define SHA1_SIZE 20
+
+struct sha1_hash {
+ u8 hash[SHA1_SIZE];
+};
+
+struct sinit_mle_data {
+ u32 version; /* currently 6 */
+ struct sha1_hash bios_acm_id;
+ u32 edx_senter_flags;
+ u64 mseg_valid;
+ struct sha1_hash sinit_hash;
+ struct sha1_hash mle_hash;
+ struct sha1_hash stm_hash;
+ struct sha1_hash lcp_policy_hash;
+ u32 lcp_policy_control;
+ u32 rlp_wakeup_addr;
+ u32 reserved;
+ u32 num_mdrs;
+ u32 mdrs_off;
+ u32 num_vtd_dmars;
+ u32 vtd_dmars_off;
+} __packed;
+
+struct acpi_table_header *tboot_get_dmar_table(struct acpi_table_header *dmar_tbl)
+{
+ void *heap_base, *heap_ptr, *config;
+
+ if (!tboot_enabled())
+ return dmar_tbl;
+
+ /*
+ * ACPI tables may not be DMA protected by tboot, so use DMAR copy
+ * SINIT saved in SinitMleData in TXT heap (which is DMA protected)
+ */
+
+ /* map config space in order to get heap addr */
+ config = ioremap(TXT_PUB_CONFIG_REGS_BASE, NR_TXT_CONFIG_PAGES *
+ PAGE_SIZE);
+ if (!config)
+ return NULL;
+
+ /* now map TXT heap */
+ heap_base = ioremap(*(u64 *)(config + TXTCR_HEAP_BASE),
+ *(u64 *)(config + TXTCR_HEAP_SIZE));
+ iounmap(config);
+ if (!heap_base)
+ return NULL;
+
+ /* walk heap to SinitMleData */
+ /* skip BiosData */
+ heap_ptr = heap_base + *(u64 *)heap_base;
+ /* skip OsMleData */
+ heap_ptr += *(u64 *)heap_ptr;
+ /* skip OsSinitData */
+ heap_ptr += *(u64 *)heap_ptr;
+ /* now points to SinitMleDataSize; set to SinitMleData */
+ heap_ptr += sizeof(u64);
+ /* get addr of DMAR table */
+ dmar_tbl = (struct acpi_table_header *)(heap_ptr +
+ ((struct sinit_mle_data *)heap_ptr)->vtd_dmars_off -
+ sizeof(u64));
+
+ /* don't unmap heap because dmar.c needs access to this */
+
+ return dmar_tbl;
+}
+
+int tboot_force_iommu(void)
+{
+ if (!tboot_enabled())
+ return 0;
+
+ if (no_iommu || swiotlb || dmar_disabled)
+ pr_warning("Forcing Intel-IOMMU to enabled\n");
+
+ dmar_disabled = 0;
+#ifdef CONFIG_SWIOTLB
+ swiotlb = 0;
+#endif
+ no_iommu = 0;
+
+ return 1;
+}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9fc178255c0..0ccb57d5ee3 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -348,15 +348,12 @@ SECTIONS
_end = .;
}
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.exitcall.exit)
- *(.eh_frame)
- *(.discard)
- }
-
STABS_DEBUG
DWARF_DEBUG
+
+ /* Sections to be discarded */
+ DISCARDS
+ /DISCARD/ : { *(.eh_frame) }
}
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index fe6f84ca121..84e236ce76b 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -21,7 +21,7 @@
#include <linux/module.h>
#include <linux/highmem.h>
-int is_io_mapping_possible(resource_size_t base, unsigned long size)
+static int is_io_mapping_possible(resource_size_t base, unsigned long size)
{
#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT)
/* There is no way to map greater than 1 << 32 address without PAE */
@@ -30,7 +30,30 @@ int is_io_mapping_possible(resource_size_t base, unsigned long size)
#endif
return 1;
}
-EXPORT_SYMBOL_GPL(is_io_mapping_possible);
+
+int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot)
+{
+ unsigned long flag = _PAGE_CACHE_WC;
+ int ret;
+
+ if (!is_io_mapping_possible(base, size))
+ return -EINVAL;
+
+ ret = io_reserve_memtype(base, base + size, &flag);
+ if (ret)
+ return ret;
+
+ *prot = __pgprot(__PAGE_KERNEL | flag);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_create_wc);
+
+void
+iomap_free(resource_size_t base, unsigned long size)
+{
+ io_free_memtype(base, base + size);
+}
+EXPORT_SYMBOL_GPL(iomap_free);
void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
{
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 04e1ad60c63..334e63ca7b2 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -158,24 +158,14 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
prot_val, &new_prot_val);
if (retval) {
- pr_debug("Warning: reserve_memtype returned %d\n", retval);
+ printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval);
return NULL;
}
if (prot_val != new_prot_val) {
- /*
- * Do not fallback to certain memory types with certain
- * requested type:
- * - request is uc-, return cannot be write-back
- * - request is uc-, return cannot be write-combine
- * - request is write-combine, return cannot be write-back
- */
- if ((prot_val == _PAGE_CACHE_UC_MINUS &&
- (new_prot_val == _PAGE_CACHE_WB ||
- new_prot_val == _PAGE_CACHE_WC)) ||
- (prot_val == _PAGE_CACHE_WC &&
- new_prot_val == _PAGE_CACHE_WB)) {
- pr_debug(
+ if (!is_new_memtype_allowed(phys_addr, size,
+ prot_val, new_prot_val)) {
+ printk(KERN_ERR
"ioremap error for 0x%llx-0x%llx, requested 0x%lx, got 0x%lx\n",
(unsigned long long)phys_addr,
(unsigned long long)(phys_addr + size),
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 7e600c1962d..24952fdc7e4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -12,6 +12,7 @@
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/pfn.h>
+#include <linux/percpu.h>
#include <asm/e820.h>
#include <asm/processor.h>
@@ -686,7 +687,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
{
struct cpa_data alias_cpa;
unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
- unsigned long vaddr, remapped;
+ unsigned long vaddr;
int ret;
if (cpa->pfn >= max_pfn_mapped)
@@ -744,24 +745,6 @@ static int cpa_process_alias(struct cpa_data *cpa)
}
#endif
- /*
- * If the PMD page was partially used for per-cpu remapping,
- * the recycled area needs to be split and modified. Because
- * the area is always proper subset of a PMD page
- * cpa->numpages is guaranteed to be 1 for these areas, so
- * there's no need to loop over and check for further remaps.
- */
- remapped = (unsigned long)pcpu_lpage_remapped((void *)laddr);
- if (remapped) {
- WARN_ON(cpa->numpages > 1);
- alias_cpa = *cpa;
- alias_cpa.vaddr = &remapped;
- alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
- ret = __change_page_attr_set_clr(&alias_cpa, 0);
- if (ret)
- return ret;
- }
-
return 0;
}
@@ -822,6 +805,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
{
struct cpa_data cpa;
int ret, cache, checkalias;
+ unsigned long baddr = 0;
/*
* Check, if we are requested to change a not supported
@@ -853,6 +837,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
*/
WARN_ON_ONCE(1);
}
+ /*
+ * Save address for cache flush. *addr is modified in the call
+ * to __change_page_attr_set_clr() below.
+ */
+ baddr = *addr;
}
/* Must avoid aliasing mappings in the highmem code */
@@ -900,7 +889,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
cpa_flush_array(addr, numpages, cache,
cpa.flags, pages);
} else
- cpa_flush_range(*addr, numpages, cache);
+ cpa_flush_range(baddr, numpages, cache);
} else
cpa_flush_all(cache);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index b2f7d3e59b8..d7ebc3a10f2 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -15,6 +15,7 @@
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/fs.h>
+#include <linux/rbtree.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
@@ -148,11 +149,10 @@ static char *cattr_name(unsigned long flags)
* areas). All the aliases have the same cache attributes of course.
* Zero attributes are represented as holes.
*
- * Currently the data structure is a list because the number of mappings
- * are expected to be relatively small. If this should be a problem
- * it could be changed to a rbtree or similar.
+ * The data structure is a list that is also organized as an rbtree
+ * sorted on the start address of memtype range.
*
- * memtype_lock protects the whole list.
+ * memtype_lock protects both the linear list and rbtree.
*/
struct memtype {
@@ -160,11 +160,53 @@ struct memtype {
u64 end;
unsigned long type;
struct list_head nd;
+ struct rb_node rb;
};
+static struct rb_root memtype_rbroot = RB_ROOT;
static LIST_HEAD(memtype_list);
static DEFINE_SPINLOCK(memtype_lock); /* protects memtype list */
+static struct memtype *memtype_rb_search(struct rb_root *root, u64 start)
+{
+ struct rb_node *node = root->rb_node;
+ struct memtype *last_lower = NULL;
+
+ while (node) {
+ struct memtype *data = container_of(node, struct memtype, rb);
+
+ if (data->start < start) {
+ last_lower = data;
+ node = node->rb_right;
+ } else if (data->start > start) {
+ node = node->rb_left;
+ } else
+ return data;
+ }
+
+ /* Will return NULL if there is no entry with its start <= start */
+ return last_lower;
+}
+
+static void memtype_rb_insert(struct rb_root *root, struct memtype *data)
+{
+ struct rb_node **new = &(root->rb_node);
+ struct rb_node *parent = NULL;
+
+ while (*new) {
+ struct memtype *this = container_of(*new, struct memtype, rb);
+
+ parent = *new;
+ if (data->start <= this->start)
+ new = &((*new)->rb_left);
+ else if (data->start > this->start)
+ new = &((*new)->rb_right);
+ }
+
+ rb_link_node(&data->rb, parent, new);
+ rb_insert_color(&data->rb, root);
+}
+
/*
* Does intersection of PAT memory type and MTRR memory type and returns
* the resulting memory type as PAT understands it.
@@ -218,9 +260,6 @@ chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type)
return -EBUSY;
}
-static struct memtype *cached_entry;
-static u64 cached_start;
-
static int pat_pagerange_is_ram(unsigned long start, unsigned long end)
{
int ram_page = 0, not_rampage = 0;
@@ -249,63 +288,61 @@ static int pat_pagerange_is_ram(unsigned long start, unsigned long end)
}
/*
- * For RAM pages, mark the pages as non WB memory type using
- * PageNonWB (PG_arch_1). We allow only one set_memory_uc() or
- * set_memory_wc() on a RAM page at a time before marking it as WB again.
- * This is ok, because only one driver will be owning the page and
- * doing set_memory_*() calls.
+ * For RAM pages, we use page flags to mark the pages with appropriate type.
+ * Here we do two pass:
+ * - Find the memtype of all the pages in the range, look for any conflicts
+ * - In case of no conflicts, set the new memtype for pages in the range
*
- * For now, we use PageNonWB to track that the RAM page is being mapped
- * as non WB. In future, we will have to use one more flag
- * (or some other mechanism in page_struct) to distinguish between
- * UC and WC mapping.
+ * Caller must hold memtype_lock for atomicity.
*/
static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
unsigned long *new_type)
{
struct page *page;
- u64 pfn, end_pfn;
+ u64 pfn;
+
+ if (req_type == _PAGE_CACHE_UC) {
+ /* We do not support strong UC */
+ WARN_ON_ONCE(1);
+ req_type = _PAGE_CACHE_UC_MINUS;
+ }
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
- page = pfn_to_page(pfn);
- if (page_mapped(page) || PageNonWB(page))
- goto out;
+ unsigned long type;
- SetPageNonWB(page);
+ page = pfn_to_page(pfn);
+ type = get_page_memtype(page);
+ if (type != -1) {
+ printk(KERN_INFO "reserve_ram_pages_type failed "
+ "0x%Lx-0x%Lx, track 0x%lx, req 0x%lx\n",
+ start, end, type, req_type);
+ if (new_type)
+ *new_type = type;
+
+ return -EBUSY;
+ }
}
- return 0;
-out:
- end_pfn = pfn;
- for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
+ if (new_type)
+ *new_type = req_type;
+
+ for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
page = pfn_to_page(pfn);
- ClearPageNonWB(page);
+ set_page_memtype(page, req_type);
}
-
- return -EINVAL;
+ return 0;
}
static int free_ram_pages_type(u64 start, u64 end)
{
struct page *page;
- u64 pfn, end_pfn;
+ u64 pfn;
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
page = pfn_to_page(pfn);
- if (page_mapped(page) || !PageNonWB(page))
- goto out;
-
- ClearPageNonWB(page);
+ set_page_memtype(page, -1);
}
return 0;
-
-out:
- end_pfn = pfn;
- for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
- page = pfn_to_page(pfn);
- SetPageNonWB(page);
- }
- return -EINVAL;
}
/*
@@ -339,6 +376,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
if (new_type) {
if (req_type == -1)
*new_type = _PAGE_CACHE_WB;
+ else if (req_type == _PAGE_CACHE_WC)
+ *new_type = _PAGE_CACHE_UC_MINUS;
else
*new_type = req_type & _PAGE_CACHE_MASK;
}
@@ -364,11 +403,16 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
*new_type = actual_type;
is_range_ram = pat_pagerange_is_ram(start, end);
- if (is_range_ram == 1)
- return reserve_ram_pages_type(start, end, req_type,
- new_type);
- else if (is_range_ram < 0)
+ if (is_range_ram == 1) {
+
+ spin_lock(&memtype_lock);
+ err = reserve_ram_pages_type(start, end, req_type, new_type);
+ spin_unlock(&memtype_lock);
+
+ return err;
+ } else if (is_range_ram < 0) {
return -EINVAL;
+ }
new = kmalloc(sizeof(struct memtype), GFP_KERNEL);
if (!new)
@@ -380,17 +424,19 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
spin_lock(&memtype_lock);
- if (cached_entry && start >= cached_start)
- entry = cached_entry;
- else
+ entry = memtype_rb_search(&memtype_rbroot, new->start);
+ if (likely(entry != NULL)) {
+ /* To work correctly with list_for_each_entry_continue */
+ entry = list_entry(entry->nd.prev, struct memtype, nd);
+ } else {
entry = list_entry(&memtype_list, struct memtype, nd);
+ }
/* Search for existing mapping that overlaps the current range */
where = NULL;
list_for_each_entry_continue(entry, &memtype_list, nd) {
if (end <= entry->start) {
where = entry->nd.prev;
- cached_entry = list_entry(where, struct memtype, nd);
break;
} else if (start <= entry->start) { /* end > entry->start */
err = chk_conflict(new, entry, new_type);
@@ -398,8 +444,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
dprintk("Overlap at 0x%Lx-0x%Lx\n",
entry->start, entry->end);
where = entry->nd.prev;
- cached_entry = list_entry(where,
- struct memtype, nd);
}
break;
} else if (start < entry->end) { /* start > entry->start */
@@ -407,8 +451,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
if (!err) {
dprintk("Overlap at 0x%Lx-0x%Lx\n",
entry->start, entry->end);
- cached_entry = list_entry(entry->nd.prev,
- struct memtype, nd);
/*
* Move to right position in the linked
@@ -436,13 +478,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
return err;
}
- cached_start = start;
-
if (where)
list_add(&new->nd, where);
else
list_add_tail(&new->nd, &memtype_list);
+ memtype_rb_insert(&memtype_rbroot, new);
+
spin_unlock(&memtype_lock);
dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
@@ -454,7 +496,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
int free_memtype(u64 start, u64 end)
{
- struct memtype *entry;
+ struct memtype *entry, *saved_entry;
int err = -EINVAL;
int is_range_ram;
@@ -466,23 +508,58 @@ int free_memtype(u64 start, u64 end)
return 0;
is_range_ram = pat_pagerange_is_ram(start, end);
- if (is_range_ram == 1)
- return free_ram_pages_type(start, end);
- else if (is_range_ram < 0)
+ if (is_range_ram == 1) {
+
+ spin_lock(&memtype_lock);
+ err = free_ram_pages_type(start, end);
+ spin_unlock(&memtype_lock);
+
+ return err;
+ } else if (is_range_ram < 0) {
return -EINVAL;
+ }
spin_lock(&memtype_lock);
+
+ entry = memtype_rb_search(&memtype_rbroot, start);
+ if (unlikely(entry == NULL))
+ goto unlock_ret;
+
+ /*
+ * Saved entry points to an entry with start same or less than what
+ * we searched for. Now go through the list in both directions to look
+ * for the entry that matches with both start and end, with list stored
+ * in sorted start address
+ */
+ saved_entry = entry;
list_for_each_entry(entry, &memtype_list, nd) {
if (entry->start == start && entry->end == end) {
- if (cached_entry == entry || cached_start == start)
- cached_entry = NULL;
+ rb_erase(&entry->rb, &memtype_rbroot);
+ list_del(&entry->nd);
+ kfree(entry);
+ err = 0;
+ break;
+ } else if (entry->start > start) {
+ break;
+ }
+ }
+
+ if (!err)
+ goto unlock_ret;
+ entry = saved_entry;
+ list_for_each_entry_reverse(entry, &memtype_list, nd) {
+ if (entry->start == start && entry->end == end) {
+ rb_erase(&entry->rb, &memtype_rbroot);
list_del(&entry->nd);
kfree(entry);
err = 0;
break;
+ } else if (entry->start < start) {
+ break;
}
}
+unlock_ret:
spin_unlock(&memtype_lock);
if (err) {
@@ -496,6 +573,101 @@ int free_memtype(u64 start, u64 end)
}
+/**
+ * lookup_memtype - Looksup the memory type for a physical address
+ * @paddr: physical address of which memory type needs to be looked up
+ *
+ * Only to be called when PAT is enabled
+ *
+ * Returns _PAGE_CACHE_WB, _PAGE_CACHE_WC, _PAGE_CACHE_UC_MINUS or
+ * _PAGE_CACHE_UC
+ */
+static unsigned long lookup_memtype(u64 paddr)
+{
+ int rettype = _PAGE_CACHE_WB;
+ struct memtype *entry;
+
+ if (is_ISA_range(paddr, paddr + PAGE_SIZE - 1))
+ return rettype;
+
+ if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
+ struct page *page;
+ spin_lock(&memtype_lock);
+ page = pfn_to_page(paddr >> PAGE_SHIFT);
+ rettype = get_page_memtype(page);
+ spin_unlock(&memtype_lock);
+ /*
+ * -1 from get_page_memtype() implies RAM page is in its
+ * default state and not reserved, and hence of type WB
+ */
+ if (rettype == -1)
+ rettype = _PAGE_CACHE_WB;
+
+ return rettype;
+ }
+
+ spin_lock(&memtype_lock);
+
+ entry = memtype_rb_search(&memtype_rbroot, paddr);
+ if (entry != NULL)
+ rettype = entry->type;
+ else
+ rettype = _PAGE_CACHE_UC_MINUS;
+
+ spin_unlock(&memtype_lock);
+ return rettype;
+}
+
+/**
+ * io_reserve_memtype - Request a memory type mapping for a region of memory
+ * @start: start (physical address) of the region
+ * @end: end (physical address) of the region
+ * @type: A pointer to memtype, with requested type. On success, requested
+ * or any other compatible type that was available for the region is returned
+ *
+ * On success, returns 0
+ * On failure, returns non-zero
+ */
+int io_reserve_memtype(resource_size_t start, resource_size_t end,
+ unsigned long *type)
+{
+ resource_size_t size = end - start;
+ unsigned long req_type = *type;
+ unsigned long new_type;
+ int ret;
+
+ WARN_ON_ONCE(iomem_map_sanity_check(start, size));
+
+ ret = reserve_memtype(start, end, req_type, &new_type);
+ if (ret)
+ goto out_err;
+
+ if (!is_new_memtype_allowed(start, size, req_type, new_type))
+ goto out_free;
+
+ if (kernel_map_sync_memtype(start, size, new_type) < 0)
+ goto out_free;
+
+ *type = new_type;
+ return 0;
+
+out_free:
+ free_memtype(start, end);
+ ret = -EBUSY;
+out_err:
+ return ret;
+}
+
+/**
+ * io_free_memtype - Release a memory type mapping for a region of memory
+ * @start: start (physical address) of the region
+ * @end: end (physical address) of the region
+ */
+void io_free_memtype(resource_size_t start, resource_size_t end)
+{
+ free_memtype(start, end);
+}
+
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
@@ -577,7 +749,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
{
unsigned long id_sz;
- if (!pat_enabled || base >= __pa(high_memory))
+ if (base >= __pa(high_memory))
return 0;
id_sz = (__pa(high_memory) < base + size) ?
@@ -612,11 +784,29 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
is_ram = pat_pagerange_is_ram(paddr, paddr + size);
/*
- * reserve_pfn_range() doesn't support RAM pages. Maintain the current
- * behavior with RAM pages by returning success.
+ * reserve_pfn_range() for RAM pages. We do not refcount to keep
+ * track of number of mappings of RAM pages. We can assert that
+ * the type requested matches the type of first page in the range.
*/
- if (is_ram != 0)
+ if (is_ram) {
+ if (!pat_enabled)
+ return 0;
+
+ flags = lookup_memtype(paddr);
+ if (want_flags != flags) {
+ printk(KERN_WARNING
+ "%s:%d map pfn RAM range req %s for %Lx-%Lx, got %s\n",
+ current->comm, current->pid,
+ cattr_name(want_flags),
+ (unsigned long long)paddr,
+ (unsigned long long)(paddr + size),
+ cattr_name(flags));
+ *vma_prot = __pgprot((pgprot_val(*vma_prot) &
+ (~_PAGE_CACHE_MASK)) |
+ flags);
+ }
return 0;
+ }
ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
if (ret)
@@ -678,14 +868,6 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;
- if (!pat_enabled)
- return 0;
-
- /*
- * For now, only handle remap_pfn_range() vmas where
- * is_linear_pfn_mapping() == TRUE. Handling of
- * vm_insert_pfn() is TBD.
- */
if (is_linear_pfn_mapping(vma)) {
/*
* reserve the whole chunk covered by vma. We need the
@@ -713,23 +895,24 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long size)
{
+ unsigned long flags;
resource_size_t paddr;
unsigned long vma_size = vma->vm_end - vma->vm_start;
- if (!pat_enabled)
- return 0;
-
- /*
- * For now, only handle remap_pfn_range() vmas where
- * is_linear_pfn_mapping() == TRUE. Handling of
- * vm_insert_pfn() is TBD.
- */
if (is_linear_pfn_mapping(vma)) {
/* reserve the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
return reserve_pfn_range(paddr, vma_size, prot, 0);
}
+ if (!pat_enabled)
+ return 0;
+
+ /* for vm_insert_pfn and friends, we set prot based on lookup */
+ flags = lookup_memtype(pfn << PAGE_SHIFT);
+ *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+ flags);
+
return 0;
}
@@ -744,14 +927,6 @@ void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
resource_size_t paddr;
unsigned long vma_size = vma->vm_end - vma->vm_start;
- if (!pat_enabled)
- return;
-
- /*
- * For now, only handle remap_pfn_range() vmas where
- * is_linear_pfn_mapping() == TRUE. Handling of
- * vm_insert_pfn() is TBD.
- */
if (is_linear_pfn_mapping(vma)) {
/* free the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 3ffa10df20b..572ee9782f2 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -15,63 +15,6 @@
* also get peer root bus resource for io,mmio
*/
-#ifdef CONFIG_NUMA
-
-#define BUS_NR 256
-
-#ifdef CONFIG_X86_64
-
-static int mp_bus_to_node[BUS_NR];
-
-void set_mp_bus_to_node(int busnum, int node)
-{
- if (busnum >= 0 && busnum < BUS_NR)
- mp_bus_to_node[busnum] = node;
-}
-
-int get_mp_bus_to_node(int busnum)
-{
- int node = -1;
-
- if (busnum < 0 || busnum > (BUS_NR - 1))
- return node;
-
- node = mp_bus_to_node[busnum];
-
- /*
- * let numa_node_id to decide it later in dma_alloc_pages
- * if there is no ram on that node
- */
- if (node != -1 && !node_online(node))
- node = -1;
-
- return node;
-}
-
-#else /* CONFIG_X86_32 */
-
-static unsigned char mp_bus_to_node[BUS_NR];
-
-void set_mp_bus_to_node(int busnum, int node)
-{
- if (busnum >= 0 && busnum < BUS_NR)
- mp_bus_to_node[busnum] = (unsigned char) node;
-}
-
-int get_mp_bus_to_node(int busnum)
-{
- int node;
-
- if (busnum < 0 || busnum > (BUS_NR - 1))
- return 0;
- node = mp_bus_to_node[busnum];
- return node;
-}
-
-#endif /* CONFIG_X86_32 */
-
-#endif /* CONFIG_NUMA */
-
#ifdef CONFIG_X86_64
/*
@@ -301,11 +244,6 @@ static int __init early_fill_mp_bus_info(void)
u64 val;
u32 address;
-#ifdef CONFIG_NUMA
- for (i = 0; i < BUS_NR; i++)
- mp_bus_to_node[i] = -1;
-#endif
-
if (!early_pci_allowed())
return -1;
@@ -346,7 +284,7 @@ static int __init early_fill_mp_bus_info(void)
node = (reg >> 4) & 0x07;
#ifdef CONFIG_NUMA
for (j = min_bus; j <= max_bus; j++)
- mp_bus_to_node[j] = (unsigned char) node;
+ set_mp_bus_to_node(j, node);
#endif
link = (reg >> 8) & 0x03;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 2202b6257b8..5db96d4304d 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -600,3 +600,72 @@ struct pci_bus * __devinit pci_scan_bus_with_sysdata(int busno)
{
return pci_scan_bus_on_node(busno, &pci_root_ops, -1);
}
+
+/*
+ * NUMA info for PCI busses
+ *
+ * Early arch code is responsible for filling in reasonable values here.
+ * A node id of "-1" means "use current node". In other words, if a bus
+ * has a -1 node id, it's not tightly coupled to any particular chunk
+ * of memory (as is the case on some Nehalem systems).
+ */
+#ifdef CONFIG_NUMA
+
+#define BUS_NR 256
+
+#ifdef CONFIG_X86_64
+
+static int mp_bus_to_node[BUS_NR] = {
+ [0 ... BUS_NR - 1] = -1
+};
+
+void set_mp_bus_to_node(int busnum, int node)
+{
+ if (busnum >= 0 && busnum < BUS_NR)
+ mp_bus_to_node[busnum] = node;
+}
+
+int get_mp_bus_to_node(int busnum)
+{
+ int node = -1;
+
+ if (busnum < 0 || busnum > (BUS_NR - 1))
+ return node;
+
+ node = mp_bus_to_node[busnum];
+
+ /*
+ * let numa_node_id to decide it later in dma_alloc_pages
+ * if there is no ram on that node
+ */
+ if (node != -1 && !node_online(node))
+ node = -1;
+
+ return node;
+}
+
+#else /* CONFIG_X86_32 */
+
+static unsigned char mp_bus_to_node[BUS_NR] = {
+ [0 ... BUS_NR - 1] = -1
+};
+
+void set_mp_bus_to_node(int busnum, int node)
+{
+ if (busnum >= 0 && busnum < BUS_NR)
+ mp_bus_to_node[busnum] = (unsigned char) node;
+}
+
+int get_mp_bus_to_node(int busnum)
+{
+ int node;
+
+ if (busnum < 0 || busnum > (BUS_NR - 1))
+ return 0;
+ node = mp_bus_to_node[busnum];
+ return node;
+}
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* CONFIG_NUMA */
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index b3d20b9cac6..417c9f5b4af 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -242,7 +242,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
fix_processor_context();
do_fpu_end();
- mtrr_ap_init();
+ mtrr_bp_restore();
#ifdef CONFIG_X86_OLD_MCE
mcheck_init(&boot_cpu_data);