x86/mm for v2.6.33
Subsystems (7)
Linus,
Please pull the latest x86-mm-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86-mm-for-linus
out-of-topic modifications in x86-mm-for-linus:
-----------------------------------------------drivers/acpi/numa.c # 8716273: x86: Export srat physical topolog
Thanks,
Ingo
------------------>
Alexander Potashev (1):
x86, boot: Simplify setting of the PAE bit
Cliff Wickman (1):
x86: SGI UV: Fix BAU initialization
David Rientjes (4):
x86: Clean up and add missing log levels for k8
x86: Export k8 physical topology
x86: Export srat physical topology
x86: Interleave emulated nodes over physical nodes
H. Peter Anvin (10):
x86-32: Use symbolic constants, safer CPUID when enabling EFER.NX x86, sleep: Always save the value of EFER
x86, pageattr: Make set_memory_(x|nx) aware of NX support x86, mm: Clean up and simplify NX enablement
x86: remove "extern" from function prototypes in <asm/proto.h> x86, mm: Call is_untracked_pat_range() rather than is_ISA_range() x86, mm: is_untracked_pat_range() takes a normal semiclosed range
x86: Change is_ISA_range() into an inline function
x86, platform: Change is_untracked_pat_range() to bool; cleanup init x86, mm: Correct the implementation of is_untracked_pat_range()
Jack Steiner (1):
x86: UV SGI: Don't track GRU space in PAT
Jan Beulich (1):
x86: Eliminate redundant/contradicting cache line size config options
Kees Cook (1):
x86, mm: Report state of NX protections during boot
Minchan Kim (1):
x86: Remove pfn in add_one_highpage_init()
Randy Dunlap (1):
x86: k8.h: Add struct bootnode
Steven Rostedt (1):
tracing: allow to change permissions for text with dynamic ftrace enabled
Suresh Siddha (6):
x86-64: preserve large page mapping for 1st 2MB kernel txt with CONFIG_DEBUG_RODATA
x86-64: align RODATA kernel section to 2MB with CONFIG_DEBUG_RODATA
x86-64: add comment for RODATA large page retainment
x86, cpa: Fix kernel text RO checks in static_protection()
x86_64, ftrace: Make ftrace use kernel identity mapping to modify code x86_64, cpa: Use only text section in set_kernel_text_rw/ro
Xiaotian Feng (1):
x86/pat: Trivial: don't create debugfs for memtype if pat is disabled
Yinghai Lu (7):
x86: Make sure wakeup trampoline code is below 1MB
x86: When cleaning MTRRs, do not fold WP into UC
x86: Change crash kernel to reserve via reserve_early() x86, numa, bootmem: Only free bootmem on NUMA failure path x86, numa: Use near(er) online node instead of roundrobin for NUMA
x86: Move find_smp_config() earlier and avoid bootmem usage x86, mtrr: Fix sorting of mtrr after subtracting
arch/x86/Kconfig.cpu | 14 +- arch/x86/boot/compressed/head_64.S | 3 +- arch/x86/boot/compressed/vmlinux.lds.S | 3 +- arch/x86/include/asm/acpi.h | 3 +- arch/x86/include/asm/cache.h | 7 +- arch/x86/include/asm/cacheflush.h | 1 + arch/x86/include/asm/e820.h | 23 ++- arch/x86/include/asm/k8.h | 5 +- arch/x86/include/asm/mpspec.h | 11 +- arch/x86/include/asm/page_types.h | 3 +- arch/x86/include/asm/pgtable.h | 6 +- arch/x86/include/asm/proto.h | 17 +- arch/x86/include/asm/sections.h | 6 + arch/x86/include/asm/x86_init.h | 4 +- arch/x86/kernel/acpi/sleep.c | 24 ++-- arch/x86/kernel/apic/numaq_32.c | 5 - arch/x86/kernel/apic/x2apic_uv_x.c | 19 +++- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/cpu/intel.c | 6 +- arch/x86/kernel/cpu/mtrr/cleanup.c | 51 +++++-- arch/x86/kernel/ftrace.c | 17 ++ arch/x86/kernel/head_32.S | 18 ++- arch/x86/kernel/head_64.S | 3 +- arch/x86/kernel/machine_kexec_32.c | 6 +- arch/x86/kernel/mpparse.c | 44 ++---- arch/x86/kernel/setup.c | 106 ++++++-------- arch/x86/kernel/tlb_uv.c | 4 +- arch/x86/kernel/visws_quirks.c | 2 +- arch/x86/kernel/vmlinux.lds.S | 38 ++++- arch/x86/kernel/x86_init.c | 2 + arch/x86/mm/init.c | 4 - arch/x86/mm/init_32.c | 10 +- arch/x86/mm/init_64.c | 35 ++++- arch/x86/mm/k8topology_64.c | 101 +++++++------ arch/x86/mm/numa_32.c | 4 +- arch/x86/mm/numa_64.c | 252 +++++++++++++++++++++++++++----- arch/x86/mm/pageattr.c | 22 +++ arch/x86/mm/pat.c | 13 +- arch/x86/mm/setup_nx.c | 59 +++----- arch/x86/mm/srat_64.c | 29 +++- arch/x86/mm/tlb.c | 3 +- arch/x86/xen/enlighten.c | 4 +- drivers/acpi/numa.c | 10 +- 43 files changed, 656 insertions(+), 343 deletions(-)
arch/x86/Kconfig.cpu +5 -9
@@ -301,15 +301,11 @@ config X86_CPU # # Define implied options from the CPU selection here -config X86_L1_CACHE_BYTES +config X86_INTERNODE_CACHE_SHIFT int - default "128" if MPSC - default "64" if GENERIC_CPU || MK8 || MCORE2 || MATOM || X86_32 - -config X86_INTERNODE_CACHE_BYTES - int - default "4096" if X86_VSMP - default X86_L1_CACHE_BYTES if !X86_VSMP + default "12" if X86_VSMP + default "7" if NUMA + default X86_L1_CACHE_SHIFT config X86_CMPXCHG def_bool X86_64 || (X86_32 && !M386)
@@ -317,9 +313,9 @@ config X86_CMPXCHG config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || MPSC + default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU default "4" if X86_ELAN || M486 || M386 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX - default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU config X86_XADD def_bool y
arch/x86/boot/compressed/head_64.S +1 -2
@@ -107,8 +107,7 @@ ENTRY(startup_32) lgdt gdt(%ebp) /* Enable PAE mode */ - xorl %eax, %eax - orl $(X86_CR4_PAE), %eax + movl $(X86_CR4_PAE), %eax movl %eax, %cr4 /*
arch/x86/boot/compressed/vmlinux.lds.S +2 -1
@@ -4,6 +4,7 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) #undef i386 +#include <asm/cache.h> #include <asm/page_types.h> #ifdef CONFIG_X86_64
@@ -46,7 +47,7 @@ SECTIONS *(.data.*) _edata = . ; } - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .bss : { _bss = . ; *(.bss)
arch/x86/include/asm/acpi.h +2 -1
@@ -118,7 +118,7 @@ extern void acpi_restore_state_mem(void);extern unsigned long acpi_wakeup_address;/* early initialization routine */ -extern void acpi_reserve_bootmem (void ); +extern void acpi_reserve_wakeup_memory (void );/* * Check if the CPU can handle C2 and deeper
@@ -158,6 +158,7 @@ struct bootnode;#ifdef CONFIG_ACPI_NUMA extern int acpi_numa; +extern int acpi_get_nodes (struct bootnode *physnodes);extern int acpi_scan_nodes (unsigned long start,unsigned long end);#define NR_NODE_MEMBLKS (MAX_NUMNODES*2) extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
arch/x86/include/asm/cache.h +4 -3
@@ -9,12 +9,13 @@#define __read_mostly __attribute__((__section__(".data.read_mostly"))) +#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT +#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT) +#ifdef CONFIG_X86_VSMP -/* vSMP Internode cacheline shift */ -#define INTERNODE_CACHE_SHIFT (12)#ifdef CONFIG_SMP #define __cacheline_aligned_in_smp \ - __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT)))) \ + __attribute__((__aligned__(INTERNODE_CACHE_BYTES))) \ __page_aligned_data#endif #endif
arch/x86/include/asm/cacheflush.h +1 -0
@@ -176,6 +176,7 @@ void clflush_cache_range(void *addr, unsigned int size);#ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro (void );extern const int rodata_test_data; +extern int kernel_set_to_readonly;void set_kernel_text_rw (void );void set_kernel_text_ro (void );#else
arch/x86/include/asm/e820.h +16 -7
@@ -61,6 +61,12 @@ struct e820map {struct e820entry map[E820_X_MAX ]; }; +#define ISA_START_ADDRESS 0xa0000 +#define ISA_END_ADDRESS 0x100000 + +#define BIOS_BEGIN 0x000a0000 +#define BIOS_END 0x00100000 +#ifdef __KERNEL__/* see comment in arch/x86/kernel/e820.c */ extern struct e820map e820;
@@ -126,15 +132,18 @@ extern void e820_reserve_resources(void);extern void e820_reserve_resources_late (void );extern void setup_memory_map (void );extern char *default_machine_specific_memory_setup (void ); -#endif /* __KERNEL__ */ -#endif /* __ASSEMBLY__ */ -#define ISA_START_ADDRESS 0xa0000 -#define ISA_END_ADDRESS 0x100000 -#define is_ISA_range (s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS) +/* +* Returns true iff the specified range [s,e) is completely contained inside +* the ISA region. +*/ +static inline bool is_ISA_range (u64 s,u64 e) +{ +return s >=ISA_START_ADDRESS && e <=ISA_END_ADDRESS ; +} -#define BIOS_BEGIN 0x000a0000 -#define BIOS_END 0x00100000 +#endif /* __KERNEL__ */ +#endif /* __ASSEMBLY__ */ #ifdef __KERNEL__#include <linux/ioport.h>
arch/x86/include/asm/k8.h +4 -1
@@ -4,13 +4,16 @@#include <linux/pci.h> extern struct pci_device_id k8_nb_ids[]; +struct bootnode ;extern int early_is_k8_nb (u32 value);extern struct pci_dev **k8_northbridges;extern int num_k8_northbridges;extern int cache_k8_northbridges (void );extern void k8_flush_garts (void ); -extern int k8_scan_nodes (unsigned long start,unsigned long end); +extern int k8_get_nodes (struct bootnode *nodes); +extern int k8_numa_init (unsigned long start_pfn,unsigned long end_pfn); +extern int k8_scan_nodes (void );#ifdef CONFIG_K8_NB static inline struct pci_dev *node_to_k8_nb_misc (int node)
arch/x86/include/asm/mpspec.h +3 -8
@@ -71,12 +71,7 @@ static inline void early_get_smp_config(void)static inline void find_smp_config (void ) { - x86_init.mpparse.find_smp_config (1 ); -} - -static inline void early_find_smp_config (void ) -{ - x86_init.mpparse.find_smp_config (0 ); + x86_init.mpparse.find_smp_config (); }#ifdef CONFIG_X86_MPPARSE
@@ -89,7 +84,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);# else # define default_mpc_oem_bus_info NULL# endif -extern void default_find_smp_config (unsigned int reserve); +extern void default_find_smp_config (void );extern void default_get_smp_config (unsigned int early);#else static inline void early_reserve_e820_mpc_new (void ) { }
@@ -97,7 +92,7 @@ static inline void early_reserve_e820_mpc_new(void) { }#define default_mpc_apic_id NULL#define default_smp_read_mpc_oem NULL#define default_mpc_oem_bus_info NULL -#define default_find_smp_config x86_init_uint_noop +#define default_find_smp_config x86_init_noop#define default_get_smp_config x86_init_uint_noop#endif
arch/x86/include/asm/page_types.h +2 -1
@@ -49,7 +49,8 @@ extern unsigned long max_pfn_mapped;extern unsigned long init_memory_mapping (unsigned long start,unsigned long end); -extern void initmem_init (unsigned long start_pfn,unsigned long end_pfn); +extern void initmem_init (unsigned long start_pfn,unsigned long end_pfn, +int acpi,int k8);extern void free_initmem (void );#endif /* !__ASSEMBLY__ */
arch/x86/include/asm/pgtable.h +4 -2
@@ -16,6 +16,8 @@#ifndef __ASSEMBLY__ +#include <asm/x86_init.h> +/* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc..
@@ -270,9 +272,9 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, unsigned long new_flags) {/* -* PAT type is always WB for ISA. So no need to check. +* PAT type is always WB for untracked ranges, so no need to check. */ -if (is_ISA_range (paddr, paddr + size -1 )) +if (x86_platform.is_untracked_pat_range (paddr, paddr + size))return 1 ;/*
arch/x86/include/asm/proto.h +9 -8
@@ -5,18 +5,19 @@/* misc architecture specific prototypes */ -extern void early_idt_handler (void ); +void early_idt_handler (void ); -extern void system_call (void ); -extern void syscall_init (void ); +void system_call (void ); +void syscall_init (void ); -extern void ia32_syscall (void ); -extern void ia32_cstar_target (void ); -extern void ia32_sysenter_target (void ); +void ia32_syscall (void ); +void ia32_cstar_target (void ); +void ia32_sysenter_target (void ); -extern void syscall32_cpu_init (void ); +void syscall32_cpu_init (void ); -extern void check_efer (void ); +void x86_configure_nx (void ); +void x86_report_nx (void );extern int reboot_force;
arch/x86/include/asm/sections.h +6 -0
@@ -2,7 +2,13 @@#define _ASM_X86_SECTIONS_H#include <asm-generic/sections.h> +#include <asm/uaccess.h> extern char __brk_base[], __brk_limit[]; +extern struct exception_table_entry __stop___ex_table[]; + +#if defined(CONFIG_X86_64 ) && defined(CONFIG_DEBUG_RODATA ) +extern char __end_rodata_hpage_align[]; +#endif #endif /* _ASM_X86_SECTIONS_H */
arch/x86/include/asm/x86_init.h +3 -1
@@ -26,7 +26,7 @@ struct x86_init_mpparse {void (*smp_read_mpc_oem)(struct mpc_table *mpc);void (*mpc_oem_pci_bus)(struct mpc_bus *m);void (*mpc_oem_bus_info)(struct mpc_bus *m,char *name); -void (*find_smp_config)(unsigned int reserve); +void (*find_smp_config)(void );void (*get_smp_config)(unsigned int early); };
@@ -116,11 +116,13 @@ struct x86_cpuinit_ops {* @calibrate_tsc: calibrate TSC * @get_wallclock: get time from HW clock like RTC etc. * @set_wallclock: set time back to HW clock +* @is_untracked_pat_range exclude from PAT logic */ struct x86_platform_ops {unsigned long (*calibrate_tsc)(void );unsigned long (*get_wallclock)(void );int (*set_wallclock)(unsigned long nowtime); +bool (*is_untracked_pat_range)(u64 start,u64 end); };extern struct x86_init_ops x86_init;
arch/x86/kernel/acpi/sleep.c +12 -12
@@ -78,12 +78,9 @@ int acpi_save_state_mem(void)#ifndef CONFIG_64BIT store_gdt ((struct desc_ptr *)&header->pmode_gdt); - header->pmode_efer_low = nx_enabled; -if (header->pmode_efer_low &1 ) { -/* This is strange, why not save efer, always? */ -rdmsr (MSR_EFER , header->pmode_efer_low, - header->pmode_efer_high); - } +if (rdmsr_safe (MSR_EFER , &header->pmode_efer_low, + &header->pmode_efer_high)) + header->pmode_efer_low = header->pmode_efer_high =0 ;#endif /* !CONFIG_64BIT */ header->pmode_cr0 =read_cr0 ();
@@ -119,29 +116,32 @@ void acpi_restore_state_mem(void)/** -* acpi_reserve_bootmem - do _very_ early ACPI initialisation +* acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation * * We allocate a page from the first 1MB of memory for the wakeup * routine for when we come back from a sleep state. The * runtime allocator allows specification of <16MB pages, but not * <1MB pages. */ -void __init acpi_reserve_bootmem (void ) +void __init acpi_reserve_wakeup_memory (void ) { +unsigned long mem; +if ((&wakeup_code_end - &wakeup_code_start) >WAKEUP_SIZE ) {printk (KERN_ERR "ACPI: Wakeup code way too big, S3 disabled.\n" );return ; } - acpi_realmode = (unsigned long )alloc_bootmem_low (WAKEUP_SIZE ); + mem =find_e820_area (0 ,1 <<20 ,WAKEUP_SIZE ,PAGE_SIZE ); -if (!acpi_realmode) { +if (mem ==-1L ) {printk (KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n" );return ; } - - acpi_wakeup_address =virt_to_phys ((void *)acpi_realmode); + acpi_realmode = (unsigned long )phys_to_virt (mem); + acpi_wakeup_address = mem; +reserve_early (mem, mem +WAKEUP_SIZE ,"ACPI WAKEUP" ); }
arch/x86/kernel/apic/numaq_32.c +0 -5
@@ -264,11 +264,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc)static __init void early_check_numaq (void ) {/* -* Find possible boot-time SMP configuration: -*/ -early_find_smp_config (); - -/* * get boot-time SMP configuration: */ if (smp_found_config)
arch/x86/kernel/apic/x2apic_uv_x.c +18 -1
@@ -30,10 +30,22 @@#include <asm/apic.h> #include <asm/ipi.h> #include <asm/smp.h> +#include <asm/x86_init.h> DEFINE_PER_CPU (int, x2apic_extra_bits);static enum uv_system_type uv_system_type; +static u64 gru_start_paddr, gru_end_paddr; + +static inline bool is_GRU_range (u64 start,u64 end) +{ +return start >= gru_start_paddr && end <= gru_end_paddr; +} + +static bool uv_is_untracked_pat_range (u64 start,u64 end) +{ +return is_ISA_range (start, end) ||is_GRU_range (start, end); +}static int early_get_nodeid (void ) {
@@ -49,6 +61,7 @@ static int early_get_nodeid(void)static int __init uv_acpi_madt_oem_check (char *oem_id,char *oem_table_id) {if (!strcmp (oem_id,"SGI" )) { + x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;if (!strcmp (oem_table_id,"UVL" )) uv_system_type =UV_LEGACY_APIC ;else if (!strcmp (oem_table_id,"UVX" ))
@@ -385,8 +398,12 @@ static __init void map_gru_high(int max_pnode)int shift =UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT ; gru.v =uv_read_local_mmr (UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR ); -if (gru.s.enable) +if (gru.s.enable) {map_high ("GRU" , gru.s.base, shift, max_pnode, map_wb); + gru_start_paddr = ((u64 )gru.s.base << shift); + gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode +1 ); + + } }static __init void map_mmr_high (int max_pnode)
arch/x86/kernel/cpu/common.c +1 -1
@@ -1136,7 +1136,7 @@ void __cpuinit cpu_init(void)wrmsrl (MSR_KERNEL_GS_BASE ,0 );barrier (); -check_efer (); +x86_configure_nx ();if (cpu !=0 )enable_x2apic ();
arch/x86/kernel/cpu/intel.c +5 -1
@@ -263,8 +263,12 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)/* Don't do the funky fallback heuristics the AMD version employs for now. */ node = apicid_to_node[apicid]; -if (node ==NUMA_NO_NODE || !node_online (node)) +if (node ==NUMA_NO_NODE ) node =first_node (node_online_map); +else if (!node_online (node)) { +/* reuse the value from init_cpu_to_node() */ + node =cpu_to_node (cpu); + }numa_set_node (cpu, node);printk (KERN_INFO "CPU %d/0x%x -> Node %d\n" , cpu, apicid, node);
arch/x86/kernel/cpu/mtrr/cleanup.c +40 -11
76 lines not on this page · raw message
arch/x86/kernel/ftrace.c +17 -0
@@ -187,9 +187,26 @@ static void wait_for_nmi(void) nmi_wait_count++; } +static inline int +within (unsigned long addr,unsigned long start,unsigned long end) +{ +return addr >= start && addr < end; +} +static int do_ftrace_mod_code (unsigned long ip,void *new_code) { +/* +* On x86_64, kernel text mappings are mapped read-only with +* CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead +* of the kernel text mapping to modify the kernel text. +* +* For 32bit kernels, these mappings are same and we can use +* kernel identity mapping to modify code. +*/ +if (within (ip, (unsigned long )_text, (unsigned long )_etext)) + ip = (unsigned long )__va (__pa (ip)); + mod_code_ip = (void *)ip; mod_code_newcode = new_code;
arch/x86/kernel/head_32.S +11 -7
@@ -18,6 +18,8 @@ #include <asm/asm-offsets.h> #include <asm/setup.h> #include <asm/processor-flags.h> +#include <asm/msr-index.h> +#include <asm/cpufeature.h> #include <asm/percpu.h> /* Physical address */
@@ -297,25 +299,27 @@ ENTRY(startup_32_smp) orl %edx,%eax movl %eax,%cr4 - btl $5, %eax # check if PAE is enabled - jnc 6f + testb $X86_CR4_PAE, %al # check if PAE is enabled + jz 6f /* Check if extended functions are implemented */ movl $0x80000000, %eax cpuid - cmpl $0x80000000, %eax - jbe 6f + /* Value must be in the range 0x80000001 to 0x8000ffff */ + subl $0x80000001, %eax + cmpl $(0x8000ffff-0x80000001), %eax + ja 6f mov $0x80000001, %eax cpuid /* Execute Disable bit supported? */ - btl $20, %edx + btl $(X86_FEATURE_NX & 31), %edx jnc 6f /* Setup EFER (Extended Feature Enable Register) */ - movl $0xc0000080, %ecx + movl $MSR_EFER, %ecx rdmsr - btsl $11, %eax + btsl $_EFER_NX, %eax /* Make changes effective */ wrmsr
arch/x86/kernel/head_64.S +2 -1
@@ -262,11 +262,11 @@ ENTRY(secondary_startup_64) .quad x86_64_start_kernel ENTRY(initial_gs) .quad INIT_PER_CPU_VAR(irq_stack_union) - __FINITDATA ENTRY(stack_start) .quad init_thread_union+THREAD_SIZE-8 .word 0 + __FINITDATA bad_address: jmp bad_address
@@ -340,6 +340,7 @@ ENTRY(name) i = i + 1 ; \ .endr + .data /* * This default setting generates an ident mapping at address 0x100000 * and a mapping for the kernel that precisely maps virtual address
arch/x86/kernel/machine_kexec_32.c +2 -4
@@ -157,8 +157,7 @@ int machine_kexec_prepare(struct kimage *image) {int error; -if (nx_enabled) -set_pages_x (image->control_code_page,1 ); +set_pages_x (image->control_code_page,1 ); error =machine_kexec_alloc_page_tables (image);if (error)return error;
@@ -172,8 +171,7 @@ int machine_kexec_prepare(struct kimage *image)*/ void machine_kexec_cleanup (struct kimage *image) { -if (nx_enabled) -set_pages_nx (image->control_code_page,1 ); +set_pages_nx (image->control_code_page,1 );machine_kexec_free_page_tables (image); }
arch/x86/kernel/mpparse.c +12 -32
83 lines not on this page · raw message
arch/x86/kernel/setup.c +43 -63
178 lines not on this page · raw message
arch/x86/kernel/tlb_uv.c +1 -3
@@ -819,10 +819,8 @@ static int __init uv_init_blade(int blade)*/ apicid =blade_to_first_apicid (blade); pa =uv_read_global_mmr64 (pnode,UVH_BAU_DATA_CONFIG ); -if ((pa &0xff ) !=UV_BAU_MESSAGE ) { -uv_write_global_mmr64 (pnode,UVH_BAU_DATA_CONFIG , +uv_write_global_mmr64 (pnode,UVH_BAU_DATA_CONFIG , ((apicid <<32 ) |UV_BAU_MESSAGE )); - }return 0 ; }
arch/x86/kernel/visws_quirks.c +1 -1
@@ -197,7 +197,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) apic_version[m->apicid] = ver; } -static void __init visws_find_smp_config (unsigned int reserve) +static void __init visws_find_smp_config (void ) {struct mpc_cpu *mp =phys_to_virt (CO_CPU_TAB_PHYS );unsigned short ncpus =readw (phys_to_virt (CO_CPU_NUM_PHYS ));
arch/x86/kernel/vmlinux.lds.S +33 -5
@@ -41,6 +41,32 @@ ENTRY(phys_startup_64) jiffies_64 = jiffies; #endif +#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +/* + * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA + * we retain large page mappings for boundaries spanning kernel text, rodata + * and data sections. + * + * However, kernel identity mappings will have different RWX permissions + * to the pages mapping to text and to the pages padding (which are freed) the + * text section. Hence kernel identity mappings will be broken to smaller + * pages. For 64-bit, kernel text and kernel identity mappings are different, + * so we can enable protection checks that come with CONFIG_DEBUG_RODATA, + * as well as retain 2MB large page mappings for kernel text. + */ +#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); + +#define X64_ALIGN_DEBUG_RODATA_END \ + . = ALIGN(HPAGE_SIZE); \ + __end_rodata_hpage_align = .; + +#else + +#define X64_ALIGN_DEBUG_RODATA_BEGIN +#define X64_ALIGN_DEBUG_RODATA_END + +#endif + PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(7); /* RWE */
@@ -90,7 +116,9 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 + X64_ALIGN_DEBUG_RODATA_BEGIN RO_DATA(PAGE_SIZE) + X64_ALIGN_DEBUG_RODATA_END /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) {
@@ -107,13 +135,13 @@ SECTIONS PAGE_ALIGNED_DATA(PAGE_SIZE) - CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES) + CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES) DATA_DATA CONSTRUCTORS /* rarely changed data like cpu maps */ - READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES) + READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES) /* End of data section */ _edata = .;
@@ -137,12 +165,12 @@ SECTIONS *(.vsyscall_0) } :user - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) } - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) { *(.vsyscall_gtod_data) }
@@ -166,7 +194,7 @@ SECTIONS } vgetcpu_mode = VVIRT(.vgetcpu_mode); - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) }
arch/x86/kernel/x86_init.c +2 -0
@@ -13,6 +13,7 @@#include <asm/e820.h> #include <asm/time.h> #include <asm/irq.h> +#include <asm/pat.h> #include <asm/tsc.h> void __cpuinit x86_init_noop (void ) { }
@@ -72,4 +73,5 @@ struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, + .is_untracked_pat_range = is_ISA_range, };
arch/x86/mm/init.c +0 -4
@@ -146,10 +146,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, use_gbpages = direct_gbpages;#endif -set_nx (); -if (nx_enabled) -printk (KERN_INFO "NX (Execute Disable) protection: active\n" ); -/* Enable PSE if available */ if (cpu_has_pse)set_in_cr4 (X86_CR4_PSE );
arch/x86/mm/init_32.c +5 -5
@@ -412,7 +412,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -static void __init add_one_highpage_init (struct page *page,int pfn) +static void __init add_one_highpage_init (struct page *page) {ClearPageReserved (page);init_page_count (page);
@@ -445,7 +445,7 @@ static int __init add_highpages_work_fn(unsigned long start_pfn,if (!pfn_valid (node_pfn))continue ; page =pfn_to_page (node_pfn); -add_one_highpage_init (page, node_pfn); +add_one_highpage_init (page); }return 0 ;
@@ -703,8 +703,8 @@ void __init find_low_pfn_range(void) }#ifndef CONFIG_NEED_MULTIPLE_NODES -void __init initmem_init (unsigned long start_pfn, -unsigned long end_pfn) +void __init initmem_init (unsigned long start_pfn,unsigned long end_pfn, +int acpi,int k8) {#ifdef CONFIG_HIGHMEM highstart_pfn = highend_pfn = max_pfn;
@@ -997,7 +997,7 @@ static noinline int do_test_wp_bit(void)const int rodata_test_data =0xC3 ;EXPORT_SYMBOL_GPL (rodata_test_data); -static int kernel_set_to_readonly; +int kernel_set_to_readonly__read_mostly ;void set_kernel_text_rw (void ) {
arch/x86/mm/init_64.c +28 -7
@@ -568,7 +568,8 @@ kernel_physical_mapping_init(unsigned long start, }#ifndef CONFIG_NUMA -void __init initmem_init (unsigned long start_pfn,unsigned long end_pfn) +void __init initmem_init (unsigned long start_pfn,unsigned long end_pfn, +int acpi,int k8) {unsigned long bootmap_size, bootmap;
@@ -694,12 +695,12 @@ void __init mem_init(void)const int rodata_test_data =0xC3 ;EXPORT_SYMBOL_GPL (rodata_test_data); -static int kernel_set_to_readonly; +int kernel_set_to_readonly;void set_kernel_text_rw (void ) { -unsigned long start =PFN_ALIGN (_stext); -unsigned long end =PFN_ALIGN (__start_rodata); +unsigned long start =PFN_ALIGN (_text); +unsigned long end =PFN_ALIGN (__stop___ex_table);if (!kernel_set_to_readonly)return ;
@@ -707,13 +708,18 @@ void set_kernel_text_rw(void)pr_debug ("Set kernel text: %lx - %lx for read write\n" , start, end); +/* +* Make the kernel identity mapping for text RW. Kernel text +* mapping will always be RO. Refer to the comment in +* static_protections() in pageattr.c +*/ set_memory_rw (start, (end - start) >>PAGE_SHIFT ); }void set_kernel_text_ro (void ) { -unsigned long start =PFN_ALIGN (_stext); -unsigned long end =PFN_ALIGN (__start_rodata); +unsigned long start =PFN_ALIGN (_text); +unsigned long end =PFN_ALIGN (__stop___ex_table);if (!kernel_set_to_readonly)return ;
@@ -721,14 +727,21 @@ void set_kernel_text_ro(void)pr_debug ("Set kernel text: %lx - %lx for read only\n" , start, end); +/* +* Set the kernel identity mapping for text RO. +*/ set_memory_ro (start, (end - start) >>PAGE_SHIFT ); }void mark_rodata_ro (void ) { -unsigned long start =PFN_ALIGN (_stext), end =PFN_ALIGN (__end_rodata); +unsigned long start =PFN_ALIGN (_text);unsigned long rodata_start = ((unsigned long )__start_rodata +PAGE_SIZE -1 ) &PAGE_MASK ; +unsigned long end = (unsigned long ) &__end_rodata_hpage_align; +unsigned long text_end =PAGE_ALIGN ((unsigned long ) &__stop___ex_table); +unsigned long rodata_end =PAGE_ALIGN ((unsigned long ) &__end_rodata); +unsigned long data_start = (unsigned long ) &_sdata;printk (KERN_INFO "Write protecting the kernel read-only data: %luk\n" , (end - start) >>10 );
@@ -751,6 +764,14 @@ void mark_rodata_ro(void)printk (KERN_INFO "Testing CPA: again\n" );set_memory_ro (start, (end-start) >>PAGE_SHIFT );#endif + +free_init_pages ("unused kernel memory" , + (unsigned long )page_address (virt_to_page (text_end)), + (unsigned long ) +page_address (virt_to_page (rodata_start))); +free_init_pages ("unused kernel memory" , + (unsigned long )page_address (virt_to_page (rodata_end)), + (unsigned long) page_address(virt_to_page(data_start))); }#endif
arch/x86/mm/k8topology_64.c +57 -44
201 lines not on this page · raw message
arch/x86/mm/numa_32.c +2 -2
@@ -347,8 +347,8 @@ static void init_remap_allocator(int nid) (ulong) node_remap_end_vaddr[nid]); } -void __init initmem_init (unsigned long start_pfn, -unsigned long end_pfn) +void __init initmem_init (unsigned long start_pfn,unsigned long end_pfn, +int acpi,int k8) {int nid;long kva_target_pfn;
arch/x86/mm/numa_64.c +217 -35
384 lines not on this page · raw message
arch/x86/mm/pageattr.c +22 -0
@@ -279,6 +279,22 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))pgprot_val (forbidden) |= _PAGE_RW; +#if defined(CONFIG_X86_64 ) && defined(CONFIG_DEBUG_RODATA ) +/* +* Once the kernel maps the text as RO (kernel_set_to_readonly is set), +* kernel text mappings for the large page aligned text, rodata sections +* will be always read-only. For the kernel identity mappings covering +* the holes caused by this alignment can be anything that user asks. +* +* This will preserve the large page mappings for kernel text/data +* at no extra cost. +*/ +if (kernel_set_to_readonly && +within (address, (unsigned long )_text, + (unsigned long )__end_rodata_hpage_align)) +pgprot_val (forbidden) |= _PAGE_RW; +#endif + prot =__pgprot (pgprot_val (prot) & ~pgprot_val (forbidden));return prot;
@@ -1069,12 +1085,18 @@ EXPORT_SYMBOL(set_memory_array_wb);int set_memory_x (unsigned long addr,int numpages) { +if (!(__supported_pte_mask & _PAGE_NX)) +return 0 ; +return change_page_attr_clear (&addr, numpages,__pgprot (_PAGE_NX),0 ); }EXPORT_SYMBOL (set_memory_x);int set_memory_nx (unsigned long addr,int numpages) { +if (!(__supported_pte_mask & _PAGE_NX)) +return 0 ; +return change_page_attr_set (&addr, numpages,__pgprot (_PAGE_NX),0 ); }EXPORT_SYMBOL (set_memory_nx);
arch/x86/mm/pat.c +8 -5
@@ -20,6 +20,7 @@#include <asm/cacheflush.h> #include <asm/processor.h> #include <asm/tlbflush.h> +#include <asm/x86_init.h> #include <asm/pgtable.h> #include <asm/fcntl.h> #include <asm/e820.h>
@@ -388,7 +389,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, }/* Low ISA region is always mapped WB in page table. No need to track */ -if (is_ISA_range (start, end -1 )) { +if (x86_platform.is_untracked_pat_range (start, end)) {if (new_type) *new_type = _PAGE_CACHE_WB;return 0 ;
@@ -499,7 +500,7 @@ int free_memtype(u64 start, u64 end)return 0 ;/* Low ISA region is always mapped WB. No need to track */ -if (is_ISA_range (start, end -1 )) +if (x86_platform.is_untracked_pat_range (start, end))return 0 ; is_range_ram =pat_pagerange_is_ram (start, end);
@@ -582,7 +583,7 @@ static unsigned long lookup_memtype(u64 paddr)int rettype = _PAGE_CACHE_WB;struct memtype *entry; -if (is_ISA_range (paddr, paddr +PAGE_SIZE -1 )) +if (x86_platform.is_untracked_pat_range (paddr, paddr +PAGE_SIZE ))return rettype;if (pat_pagerange_is_ram (paddr, paddr +PAGE_SIZE )) {
@@ -1018,8 +1019,10 @@ static const struct file_operations memtype_fops = {static int __init pat_memtype_list_init (void ) { -debugfs_create_file ("pat_memtype_list" ,S_IRUSR , arch_debugfs_dir, -NULL , &memtype_fops); +if (pat_enabled) { +debugfs_create_file ("pat_memtype_list" ,S_IRUSR , + arch_debugfs_dir,NULL , &memtype_fops); + }return 0 ; }
arch/x86/mm/setup_nx.c +25 -34
83 lines not on this page · raw message
arch/x86/mm/srat_64.c +21 -8
@@ -290,8 +290,6 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)printk (KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n" , node, pxm, start, end); -e820_register_active_regions (node, start >>PAGE_SHIFT , - end >>PAGE_SHIFT );if (ma->flags &ACPI_SRAT_MEM_HOT_PLUGGABLE ) {update_nodes_add (node, start, end);
@@ -338,6 +336,19 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)void __init acpi_numa_arch_fixup (void ) {} +int __init acpi_get_nodes (struct bootnode *physnodes) +{ +int i; +int ret =0 ; + +for_each_node_mask (i, nodes_parsed) { + physnodes[ret].start = nodes[i].start; + physnodes[ret].end = nodes[i].end; + ret++; + } +return ret; +} +/* Use the information discovered above to actually set up the nodes. */ int __init acpi_scan_nodes (unsigned long start,unsigned long end) {
@@ -350,11 +361,6 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)for (i =0 ; i <MAX_NUMNODES ; i++)cutoff_node (i, start, end); -if (!nodes_cover_memory (nodes)) { -bad_srat (); -return -1 ; - } - memnode_shift =compute_hash_shift (node_memblk_range, num_node_memblks, memblk_nodeid);if (memnode_shift <0 ) {
@@ -364,6 +370,14 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)return -1 ; } +for_each_node_mask (i, nodes_parsed) +e820_register_active_regions (i, nodes[i].start >>PAGE_SHIFT , + nodes[i].end >>PAGE_SHIFT ); +if (!nodes_cover_memory (nodes)) { +bad_srat (); +return -1 ; + } +/* Account for nodes with cpus and no memory */ nodes_or (node_possible_map, nodes_parsed, cpu_nodes_parsed);
@@ -454,7 +468,6 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)for (i =0 ; i < num_nodes; i++)if (fake_nodes[i].start != fake_nodes[i].end)node_set (i, nodes_parsed); -WARN_ON (!nodes_cover_memory (fake_nodes)); }static int null_slit_node_compare (int a,int b)
arch/x86/mm/tlb.c +2 -1
@@ -8,6 +8,7 @@#include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h>
@@ -43,7 +44,7 @@ union smp_flush_state {spinlock_t tlbstate_lock;DECLARE_BITMAP (flush_cpumask,NR_CPUS ); }; -char pad[CONFIG_X86_INTERNODE_CACHE_BYTES ]; +char pad[INTERNODE_CACHE_BYTES ]; }____cacheline_internodealigned_in_smp ;/* State is put into the per CPU data section, but padded
arch/x86/xen/enlighten.c +1 -3
@@ -1082,10 +1082,8 @@ asmlinkage void __init xen_start_kernel(void) __supported_pte_mask |= _PAGE_IOMAP; -#ifdef CONFIG_X86_64 /* Work out if we support NX */ -check_efer (); -#endif +x86_configure_nx ();xen_setup_features ();
drivers/acpi/numa.c +6 -4
@@ -283,22 +283,24 @@ acpi_table_parse_srat(enum acpi_srat_type id,int __init acpi_numa_init (void ) { +int ret =0 ; +/* SRAT: Static Resource Affinity Table */ if (!acpi_table_parse (ACPI_SIG_SRAT , acpi_parse_srat)) {acpi_table_parse_srat (ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY , acpi_parse_x2apic_affinity,NR_CPUS );acpi_table_parse_srat (ACPI_SRAT_TYPE_CPU_AFFINITY , acpi_parse_processor_affinity,NR_CPUS ); -acpi_table_parse_srat (ACPI_SRAT_TYPE_MEMORY_AFFINITY , - acpi_parse_memory_affinity, -NR_NODE_MEMBLKS ); + ret =acpi_table_parse_srat (ACPI_SRAT_TYPE_MEMORY_AFFINITY , + acpi_parse_memory_affinity, +NR_NODE_MEMBLKS ); }/* SLIT: System Locality Information Table */ acpi_table_parse (ACPI_SIG_SLIT , acpi_parse_slit);acpi_numa_arch_fixup (); -return 0 ; +return ret; }int acpi_get_pxm (acpi_handle h)