diff options
Diffstat (limited to 'arch/i386')
| -rw-r--r-- | arch/i386/Kconfig | 14 | ||||
| -rw-r--r-- | arch/i386/kernel/microcode.c | 774 | ||||
| -rw-r--r-- | arch/i386/kernel/setup.c | 26 | ||||
| -rw-r--r-- | arch/i386/kernel/srat.c | 97 | ||||
| -rw-r--r-- | arch/i386/kernel/traps.c | 7 | ||||
| -rw-r--r-- | arch/i386/mm/discontig.c | 69 |
6 files changed, 555 insertions, 432 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index 758044f5e718..3fd2f256f2be 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -401,6 +401,7 @@ config X86_REBOOTFIXUPS config MICROCODE tristate "/dev/cpu/microcode - Intel IA32 CPU microcode support" + select FW_LOADER ---help--- If you say Y here and also to "/dev file system support" in the 'File systems' section, you will be able to update the microcode on @@ -416,6 +417,11 @@ config MICROCODE To compile this driver as a module, choose M here: the module will be called microcode. +config MICROCODE_OLD_INTERFACE + bool + depends on MICROCODE + default y + config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" help @@ -598,12 +604,10 @@ config ARCH_SELECT_MEMORY_MODEL def_bool y depends on ARCH_SPARSEMEM_ENABLE -source "mm/Kconfig" +config ARCH_POPULATES_NODE_MAP + def_bool y -config HAVE_ARCH_EARLY_PFN_TO_NID - bool - default y - depends on NUMA +source "mm/Kconfig" config HIGHPTE bool "Allocate 3rd-level pagetables from highmem" diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index 40b44cc0d14b..9b9479768d5e 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -2,6 +2,7 @@ * Intel CPU Microcode Update Driver for Linux * * Copyright (C) 2000-2004 Tigran Aivazian + * 2006 Shaohua Li <shaohua.li@intel.com> * * This driver allows to upgrade microcode on Intel processors * belonging to IA-32 family - PentiumPro, Pentium II, @@ -82,6 +83,9 @@ #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/mutex.h> +#include <linux/cpu.h> +#include <linux/firmware.h> +#include <linux/platform_device.h> #include <asm/msr.h> #include <asm/uaccess.h> @@ -91,9 +95,6 @@ MODULE_DESCRIPTION("Intel CPU (IA-32) Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@veritas.com>"); MODULE_LICENSE("GPL"); -static int verbose; -module_param(verbose, int, 0644); - #define MICROCODE_VERSION "1.14a" #define DEFAULT_UCODE_DATASIZE (2000) /* 2000 bytes */ @@ -120,55 +121,40 @@ static DEFINE_SPINLOCK(microcode_update_lock); /* no concurrent ->write()s are allowed on /dev/cpu/microcode */ static DEFINE_MUTEX(microcode_mutex); -static void __user *user_buffer; /* user area microcode data buffer */ -static unsigned int user_buffer_size; /* it's size */ - -typedef enum mc_error_code { - MC_SUCCESS = 0, - MC_IGNORED = 1, - MC_NOTFOUND = 2, - MC_MARKED = 3, - MC_ALLOCATED = 4, -} mc_error_code_t; - static struct ucode_cpu_info { + int valid; unsigned int sig; - unsigned int pf, orig_pf; + unsigned int pf; unsigned int rev; - unsigned int cksum; - mc_error_code_t err; microcode_t *mc; } ucode_cpu_info[NR_CPUS]; - -static int microcode_open (struct inode *unused1, struct file *unused2) -{ - return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; -} -static void collect_cpu_info (void *unused) +static void collect_cpu_info(int cpu_num) { - int cpu_num = smp_processor_id(); struct cpuinfo_x86 *c = cpu_data + cpu_num; struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; unsigned int val[2]; - uci->sig = uci->pf = uci->rev = uci->cksum = 0; - uci->err = MC_NOTFOUND; + /* We should bind the task to the CPU */ + BUG_ON(raw_smp_processor_id() != cpu_num); + uci->pf = uci->rev = 0; uci->mc = NULL; + uci->valid = 1; if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || cpu_has(c, X86_FEATURE_IA64)) { - printk(KERN_ERR "microcode: CPU%d not a capable Intel processor\n", cpu_num); + printk(KERN_ERR "microcode: CPU%d not a capable Intel " + "processor\n", cpu_num); + uci->valid = 0; return; - } else { - uci->sig = cpuid_eax(0x00000001); + } - if ((c->x86_model >= 5) || (c->x86 > 6)) { - /* get processor flags from MSR 0x17 */ - rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - uci->pf = 1 << ((val[1] >> 18) & 7); - } - uci->orig_pf = uci->pf; + uci->sig = cpuid_eax(0x00000001); + + if ((c->x86_model >= 5) || (c->x86 > 6)) { + /* get processor flags from MSR 0x17 */ + rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); + uci->pf = 1 << ((val[1] >> 18) & 7); } wrmsr(MSR_IA32_UCODE_REV, 0, 0); @@ -180,218 +166,159 @@ static void collect_cpu_info (void *unused) uci->sig, uci->pf, uci->rev); } -static inline void mark_microcode_update (int cpu_num, microcode_header_t *mc_header, int sig, int pf, int cksum) +static inline int microcode_update_match(int cpu_num, + microcode_header_t *mc_header, int sig, int pf) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - pr_debug("Microcode Found.\n"); - pr_debug(" Header Revision 0x%x\n", mc_header->hdrver); - pr_debug(" Loader Revision 0x%x\n", mc_header->ldrver); - pr_debug(" Revision 0x%x \n", mc_header->rev); - pr_debug(" Date %x/%x/%x\n", - ((mc_header->date >> 24 ) & 0xff), - ((mc_header->date >> 16 ) & 0xff), - (mc_header->date & 0xFFFF)); - pr_debug(" Signature 0x%x\n", sig); - pr_debug(" Type 0x%x Family 0x%x Model 0x%x Stepping 0x%x\n", - ((sig >> 12) & 0x3), - ((sig >> 8) & 0xf), - ((sig >> 4) & 0xf), - ((sig & 0xf))); - pr_debug(" Processor Flags 0x%x\n", pf); - pr_debug(" Checksum 0x%x\n", cksum); - - if (mc_header->rev < uci->rev) { - if (uci->err == MC_NOTFOUND) { - uci->err = MC_IGNORED; - uci->cksum = mc_header->rev; - } else if (uci->err == MC_IGNORED && uci->cksum < mc_header->rev) - uci->cksum = mc_header->rev; - } else if (mc_header->rev == uci->rev) { - if (uci->err < MC_MARKED) { - /* notify the caller of success on this cpu */ - uci->err = MC_SUCCESS; - } - } else if (uci->err != MC_ALLOCATED || mc_header->rev > uci->mc->hdr.rev) { - pr_debug("microcode: CPU%d found a matching microcode update with " - " revision 0x%x (current=0x%x)\n", cpu_num, mc_header->rev, uci->rev); - uci->cksum = cksum; - uci->pf = pf; /* keep the original mc pf for cksum calculation */ - uci->err = MC_MARKED; /* found the match */ - for_each_online_cpu(cpu_num) { - if (ucode_cpu_info + cpu_num != uci - && ucode_cpu_info[cpu_num].mc == uci->mc) { - uci->mc = NULL; - break; - } - } - if (uci->mc != NULL) { - vfree(uci->mc); - uci->mc = NULL; - } - } - return; + if (!sigmatch(sig, uci->sig, pf, uci->pf) + || mc_header->rev <= uci->rev) + return 0; + return 1; } -static int find_matching_ucodes (void) +static int microcode_sanity_check(void *mc) { - int cursor = 0; - int error = 0; - - while (cursor + MC_HEADER_SIZE < user_buffer_size) { - microcode_header_t mc_header; - void *newmc = NULL; - int i, sum, cpu_num, allocated_flag, total_size, data_size, ext_table_size; + microcode_header_t *mc_header = mc; + struct extended_sigtable *ext_header = NULL; + struct extended_signature *ext_sig; + unsigned long total_size, data_size, ext_table_size; + int sum, orig_sum, ext_sigcount = 0, i; + + total_size = get_totalsize(mc_header); + data_size = get_datasize(mc_header); + if (data_size + MC_HEADER_SIZE > total_size) { + printk(KERN_ERR "microcode: error! " + "Bad data size in microcode data file\n"); + return -EINVAL; + } - if (copy_from_user(&mc_header, user_buffer + cursor, MC_HEADER_SIZE)) { - printk(KERN_ERR "microcode: error! Can not read user data\n"); - error = -EFAULT; - goto out; + if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { + printk(KERN_ERR "microcode: error! " + "Unknown microcode update format\n"); + return -EINVAL; + } + ext_table_size = total_size - (MC_HEADER_SIZE + data_size); + if (ext_table_size) { + if ((ext_table_size < EXT_HEADER_SIZE) + || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { + printk(KERN_ERR "microcode: error! " + "Small exttable size in microcode data file\n"); + return -EINVAL; } - - total_size = get_totalsize(&mc_header); - if ((cursor + total_size > user_buffer_size) || (total_size < DEFAULT_UCODE_TOTALSIZE)) { - printk(KERN_ERR "microcode: error! Bad data in microcode data file\n"); - error = -EINVAL; - goto out; + ext_header = mc + MC_HEADER_SIZE + data_size; + if (ext_table_size != exttable_size(ext_header)) { + printk(KERN_ERR "microcode: error! " + "Bad exttable size in microcode data file\n"); + return -EFAULT; } + ext_sigcount = ext_header->count; + } - data_size = get_datasize(&mc_header); - if ((data_size + MC_HEADER_SIZE > total_size) || (data_size < DEFAULT_UCODE_DATASIZE)) { - printk(KERN_ERR "microcode: error! Bad data in microcode data file\n"); - error = -EINVAL; - goto out; + /* check extended table checksum */ + if (ext_table_size) { + int ext_table_sum = 0; + int *ext_tablep = (int *)ext_header; + + i = ext_table_size / DWSIZE; + while (i--) + ext_table_sum += ext_tablep[i]; + if (ext_table_sum) { + printk(KERN_WARNING "microcode: aborting, " + "bad extended signature table checksum\n"); + return -EINVAL; } + } - if (mc_header.ldrver != 1 || mc_header.hdrver != 1) { - printk(KERN_ERR "microcode: error! Unknown microcode update format\n"); - error = -EINVAL; - goto out; + /* calculate the checksum */ + orig_sum = 0; + i = (MC_HEADER_SIZE + data_size) / DWSIZE; + while (i--) + orig_sum += ((int *)mc)[i]; + if (orig_sum) { + printk(KERN_ERR "microcode: aborting, bad checksum\n"); + return -EINVAL; + } + if (!ext_table_size) + return 0; + /* check extended signature checksum */ + for (i = 0; i < ext_sigcount; i++) { + ext_sig = (struct extended_signature *)((void *)ext_header + + EXT_HEADER_SIZE + EXT_SIGNATURE_SIZE * i); + sum = orig_sum + - (mc_header->sig + mc_header->pf + mc_header->cksum) + + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); + if (sum) { + printk(KERN_ERR "microcode: aborting, bad checksum\n"); + return -EINVAL; } + } + return 0; +} - for_each_online_cpu(cpu_num) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - - if (sigmatch(mc_header.sig, uci->sig, mc_header.pf, uci->orig_pf)) - mark_microcode_update(cpu_num, &mc_header, mc_header.sig, mc_header.pf, mc_header.cksum); - } +/* + * return 0 - no update found + * return 1 - found update + * return < 0 - error + */ +static int get_maching_microcode(void *mc, int cpu) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + microcode_header_t *mc_header = mc; + struct extended_sigtable *ext_header; + unsigned long total_size = get_totalsize(mc_header); + int ext_sigcount, i; + struct extended_signature *ext_sig; + void *new_mc; + + if (microcode_update_match(cpu, mc_header, + mc_header->sig, mc_header->pf)) + goto find; + + if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE) + return 0; + + ext_header = (struct extended_sigtable *)(mc + + get_datasize(mc_header) + MC_HEADER_SIZE); + ext_sigcount = ext_header->count; + ext_sig = (struct extended_signature *)((void *)ext_header + + EXT_HEADER_SIZE); + for (i = 0; i < ext_sigcount; i++) { + if (microcode_update_match(cpu, mc_header, + ext_sig->sig, ext_sig->pf)) + goto find; + ext_sig++; + } + return 0; +find: + pr_debug("microcode: CPU %d found a matching microcode update with" + " version 0x%x (current=0x%x)\n", cpu, mc_header->rev,uci->rev); + new_mc = vmalloc(total_size); + if (!new_mc) { + printk(KERN_ERR "microcode: error! Can not allocate memory\n"); + return -ENOMEM; + } - ext_table_size = total_size - (MC_HEADER_SIZE + data_size); - if (ext_table_size) { - struct extended_sigtable ext_header; - struct extended_signature ext_sig; - int ext_sigcount; + /* free previous update file */ + vfree(uci->mc); - if ((ext_table_size < EXT_HEADER_SIZE) - || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { - printk(KERN_ERR "microcode: error! Bad data in microcode data file\n"); - error = -EINVAL; - goto out; - } - if (copy_from_user(&ext_header, user_buffer + cursor - + MC_HEADER_SIZE + data_size, EXT_HEADER_SIZE)) { - printk(KERN_ERR "microcode: error! Can not read user data\n"); - error = -EFAULT; - goto out; - } - if (ext_table_size != exttable_size(&ext_header)) { - printk(KERN_ERR "microcode: error! Bad data in microcode data file\n"); - error = -EFAULT; - goto out; - } - - ext_sigcount = ext_header.count; - - for (i = 0; i < ext_sigcount; i++) { - if (copy_from_user(&ext_sig, user_buffer + cursor + MC_HEADER_SIZE + data_size + EXT_HEADER_SIZE - + EXT_SIGNATURE_SIZE * i, EXT_SIGNATURE_SIZE)) { - printk(KERN_ERR "microcode: error! Can not read user data\n"); - error = -EFAULT; - goto out; - } - for_each_online_cpu(cpu_num) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - - if (sigmatch(ext_sig.sig, uci->sig, ext_sig.pf, uci->orig_pf)) { - mark_microcode_update(cpu_num, &mc_header, ext_sig.sig, ext_sig.pf, ext_sig.cksum); - } - } - } - } - /* now check if any cpu has matched */ - allocated_flag = 0; - sum = 0; - for_each_online_cpu(cpu_num) { - if (ucode_cpu_info[cpu_num].err == MC_MARKED) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - if (!allocated_flag) { - allocated_flag = 1; - newmc = vmalloc(total_size); - if (!newmc) { - printk(KERN_ERR "microcode: error! Can not allocate memory\n"); - error = -ENOMEM; - goto out; - } - if (copy_from_user(newmc + MC_HEADER_SIZE, - user_buffer + cursor + MC_HEADER_SIZE, - total_size - MC_HEADER_SIZE)) { - printk(KERN_ERR "microcode: error! Can not read user data\n"); - vfree(newmc); - error = -EFAULT; - goto out; - } - memcpy(newmc, &mc_header, MC_HEADER_SIZE); - /* check extended table checksum */ - if (ext_table_size) { - int ext_table_sum = 0; - int * ext_tablep = (((void *) newmc) + MC_HEADER_SIZE + data_size); - i = ext_table_size / DWSIZE; - while (i--) ext_table_sum += ext_tablep[i]; - if (ext_table_sum) { - printk(KERN_WARNING "microcode: aborting, bad extended signature table checksum\n"); - vfree(newmc); - error = -EINVAL; - goto out; - } - } - - /* calculate the checksum */ - i = (MC_HEADER_SIZE + data_size) / DWSIZE; - while (i--) sum += ((int *)newmc)[i]; - sum -= (mc_header.sig + mc_header.pf + mc_header.cksum); - } - ucode_cpu_info[cpu_num].mc = newmc; - ucode_cpu_info[cpu_num].err = MC_ALLOCATED; /* mc updated */ - if (sum + uci->sig + uci->pf + uci->cksum != 0) { - printk(KERN_ERR "microcode: CPU%d aborting, bad checksum\n", cpu_num); - error = -EINVAL; - goto out; - } - } - } - cursor += total_size; /* goto the next update patch */ - } /* end of while */ -out: - return error; + memcpy(new_mc, mc, total_size); + uci->mc = new_mc; + return 1; } -static void do_update_one (void * unused) +static void apply_microcode(int cpu) { unsigned long flags; unsigned int val[2]; - int cpu_num = smp_processor_id(); + int cpu_num = raw_smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; - if (uci->mc == NULL) { - if (verbose) { - if (uci->err == MC_SUCCESS) - printk(KERN_INFO "microcode: CPU%d already at revision 0x%x\n", - cpu_num, uci->rev); - else - printk(KERN_INFO "microcode: No new microcode data for CPU%d\n", cpu_num); - } + /* We should bind the task to the CPU */ + BUG_ON(cpu_num != cpu); + + if (uci->mc == NULL) return; - } /* serialize access to the physical write to MSR 0x79 */ spin_lock_irqsave(µcode_update_lock, flags); @@ -408,68 +335,107 @@ static void do_update_one (void * unused) /* get the current revision from MSR 0x8B */ rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - /* notify the caller of success on this cpu */ - uci->err = MC_SUCCESS; spin_unlock_irqrestore(µcode_update_lock, flags); - printk(KERN_INFO "microcode: CPU%d updated from revision " + if (val[1] != uci->mc->hdr.rev) { + printk(KERN_ERR "microcode: CPU%d updated from revision " + "0x%x to 0x%x failed\n", cpu_num, uci->rev, val[1]); + return; + } + pr_debug("microcode: CPU%d updated from revision " "0x%x to 0x%x, date = %08x \n", cpu_num, uci->rev, val[1], uci->mc->hdr.date); - return; + uci->rev = val[1]; } -static int do_microcode_update (void) -{ - int i, error; +#ifdef CONFIG_MICROCODE_OLD_INTERFACE +static void __user *user_buffer; /* user area microcode data buffer */ +static unsigned int user_buffer_size; /* it's size */ - if (on_each_cpu(collect_cpu_info, NULL, 1, 1) != 0) { - printk(KERN_ERR "microcode: Error! Could not run on all processors\n"); - error = -EIO; - goto out; +static long get_next_ucode(void **mc, long offset) +{ + microcode_header_t mc_header; + unsigned long total_size; + + /* No more data */ + if (offset >= user_buffer_size) + return 0; + if (copy_from_user(&mc_header, user_buffer + offset, MC_HEADER_SIZE)) { + printk(KERN_ERR "microcode: error! Can not read user data\n"); + return -EFAULT; } - - if ((error = find_matching_ucodes())) { - printk(KERN_ERR "microcode: Error in the microcode data\n"); - goto out_free; + total_size = get_totalsize(&mc_header); + if (offset + total_size > user_buffer_size) { + printk(KERN_ERR "microcode: error! Bad total size in microcode " + "data file\n"); + return -EINVAL; } - - if (on_each_cpu(do_update_one, NULL, 1, 1) != 0) { - printk(KERN_ERR "microcode: Error! Could not run on all processors\n"); - error = -EIO; + *mc = vmalloc(total_size); + if (!*mc) + return -ENOMEM; + if (copy_from_user(*mc, user_buffer + offset, total_size)) { + printk(KERN_ERR "microcode: error! Can not read user data\n"); + vfree(*mc); + return -EFAULT; } + return offset + total_size; +} + +static int do_microcode_update (void) +{ + long cursor = 0; + int error = 0; + void *new_mc; + int cpu; + cpumask_t old; + + old = current->cpus_allowed; -out_free: - for_each_online_cpu(i) { - if (ucode_cpu_info[i].mc) { - int j; - void *tmp = ucode_cpu_info[i].mc; - vfree(tmp); - for_each_online_cpu(j) { - if (ucode_cpu_info[j].mc == tmp) - ucode_cpu_info[j].mc = NULL; - } + while ((cursor = get_next_ucode(&new_mc, cursor)) > 0) { + error = microcode_sanity_check(new_mc); + if (error) + goto out; + /* + * It's possible the data file has multiple matching ucode, + * lets keep searching till the latest version + */ + for_each_online_cpu(cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + + if (!uci->valid) + continue; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); + error = get_maching_microcode(new_mc, cpu); + if (error < 0) + goto out; + if (error == 1) + apply_microcode(cpu); } - if (ucode_cpu_info[i].err == MC_IGNORED && verbose) - printk(KERN_WARNING "microcode: CPU%d not 'upgrading' to earlier revision" - " 0x%x (current=0x%x)\n", i, ucode_cpu_info[i].cksum, ucode_cpu_info[i].rev); + vfree(new_mc); } out: + if (cursor > 0) + vfree(new_mc); + if (cursor < 0) + error = cursor; + set_cpus_allowed(current, old); return error; } +static int microcode_open (struct inode *unused1, struct file *unused2) +{ + return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; +} + static ssize_t microcode_write (struct file *file, const char __user *buf, size_t len, loff_t *ppos) { ssize_t ret; - if (len < DEFAULT_UCODE_TOTALSIZE) { - printk(KERN_ERR "microcode: not enough data\n"); - return -EINVAL; - } - if ((len >> PAGE_SHIFT) > num_physpages) { printk(KERN_ERR "microcode: too much data (max %ld pages)\n", num_physpages); return -EINVAL; } + lock_cpu_hotplug(); mutex_lock(µcode_mutex); user_buffer = (void __user *) buf; @@ -480,6 +446,7 @@ static ssize_t microcode_write (struct file *file, const char __user *buf, size_ ret = (ssize_t)len; mutex_unlock(µcode_mutex); + unlock_cpu_hotplug(); return ret; } @@ -496,7 +463,7 @@ static struct miscdevice microcode_dev = { .fops = µcode_fops, }; -static int __init microcode_init (void) +static int __init microcode_dev_init (void) { int error; @@ -508,6 +475,280 @@ static int __init microcode_init (void) return error; } + return 0; +} + +static void __exit microcode_dev_exit (void) +{ + misc_deregister(µcode_dev); +} + +MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); +#else +#define microcode_dev_init() 0 +#define microcode_dev_exit() do { } while(0) +#endif + +static long get_next_ucode_from_buffer(void **mc, void *buf, + unsigned long size, long offset) +{ + microcode_header_t *mc_header; + unsigned long total_size; + + /* No more data */ + if (offset >= size) + return 0; + mc_header = (microcode_header_t *)(buf + offset); + total_size = get_totalsize(mc_header); + + if (offset + total_size > size) { + printk(KERN_ERR "microcode: error! Bad data in microcode data file\n"); + return -EINVAL; + } + + *mc = vmalloc(total_size); + if (!*mc) { + printk(KERN_ERR "microcode: error! Can not allocate memory\n"); + return -ENOMEM; + } + memcpy(*mc, buf + offset, total_size); + return offset + total_size; +} + +/* fake device for request_firmware */ +static struct platform_device *microcode_pdev; + +static int cpu_request_microcode(int cpu) +{ + char name[30]; + struct cpuinfo_x86 *c = cpu_data + cpu; + const struct firmware *firmware; + void *buf; + unsigned long size; + long offset = 0; + int error; + void *mc; + + /* We should bind the task to the CPU */ + BUG_ON(cpu != raw_smp_processor_id()); + sprintf(name,"intel-ucode/%02x-%02x-%02x", + c->x86, c->x86_model, c->x86_mask); + error = request_firmware(&firmware, name, µcode_pdev->dev); + if (error) { + pr_debug("ucode data file %s load failed\n", name); + return error; + } + buf = (void *)firmware->data; + size = firmware->size; + while ((offset = get_next_ucode_from_buffer(&mc, buf, size, offset)) + > 0) { + error = microcode_sanity_check(mc); + if (error) + break; + error = get_maching_microcode(mc, cpu); + if (error < 0) + break; + /* + * It's possible the data file has multiple matching ucode, + * lets keep searching till the latest version + */ + if (error == 1) { + apply_microcode(cpu); + error = 0; + } + vfree(mc); + } + if (offset > 0) + vfree(mc); + if (offset < 0) + error = offset; + release_firmware(firmware); + + return error; +} + +static void microcode_init_cpu(int cpu) +{ + cpumask_t old; + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + + old = current->cpus_allowed; + + set_cpus_allowed(current, cpumask_of_cpu(cpu)); + mutex_lock(µcode_mutex); + collect_cpu_info(cpu); + if (uci->valid) + cpu_request_microcode(cpu); + mutex_unlock(µcode_mutex); + set_cpus_allowed(current, old); +} + +static void microcode_fini_cpu(int cpu) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + + mutex_lock(µcode_mutex); + uci->valid = 0; + vfree(uci->mc); + uci->mc = NULL; + mutex_unlock(µcode_mutex); +} + +static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t sz) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + dev->id; + char *end; + unsigned long val = simple_strtoul(buf, &end, 0); + int err = 0; + int cpu = dev->id; + + if (end == buf) + return -EINVAL; + if (val == 1) { + cpumask_t old; + + old = current->cpus_allowed; + + lock_cpu_hotplug(); + set_cpus_allowed(current, cpumask_of_cpu(cpu)); + + mutex_lock(µcode_mutex); + if (uci->valid) + err = cpu_request_microcode(cpu); + mutex_unlock(µcode_mutex); + unlock_cpu_hotplug(); + set_cpus_allowed(current, old); + } + if (err) + return err; + return sz; +} + +static ssize_t version_show(struct sys_device *dev, char *buf) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + dev->id; + + return sprintf(buf, "0x%x\n", uci->rev); +} + +static ssize_t pf_show(struct sys_device *dev, char *buf) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + dev->id; + + return sprintf(buf, "0x%x\n", uci->pf); +} + +static SYSDEV_ATTR(reload, 0200, NULL, reload_store); +static SYSDEV_ATTR(version, 0400, version_show, NULL); +static SYSDEV_ATTR(processor_flags, 0400, pf_show, NULL); + +static struct attribute *mc_default_attrs[] = { + &attr_reload.attr, + &attr_version.attr, + &attr_processor_flags.attr, + NULL +}; + +static struct attribute_group mc_attr_group = { + .attrs = mc_default_attrs, + .name = "microcode", +}; + +static int mc_sysdev_add(struct sys_device *sys_dev) +{ + int cpu = sys_dev->id; + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + + if (!cpu_online(cpu)) + return 0; + pr_debug("Microcode:CPU %d added\n", cpu); + memset(uci, 0, sizeof(*uci)); + sysfs_create_group(&sys_dev->kobj, &mc_attr_group); + + microcode_init_cpu(cpu); + return 0; +} + +static int mc_sysdev_remove(struct sys_device *sys_dev) +{ + int cpu = sys_dev->id; + + if (!cpu_online(cpu)) + return 0; + pr_debug("Microcode:CPU %d removed\n", cpu); + microcode_fini_cpu(cpu); + sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); + return 0; +} + +static int mc_sysdev_resume(struct sys_device *dev) +{ + int cpu = dev->id; + + if (!cpu_online(cpu)) + return 0; + pr_debug("Microcode:CPU %d resumed\n", cpu); + /* only CPU 0 will apply ucode here */ + apply_microcode(0); + return 0; +} + +static struct sysdev_driver mc_sysdev_driver = { + .add = mc_sysdev_add, + .remove = mc_sysdev_remove, + .resume = mc_sysdev_resume, +}; + +#ifdef CONFIG_HOTPLUG_CPU +static __cpuinit int +mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + struct sys_device *sys_dev; + + sys_dev = get_cpu_sysdev(cpu); + switch (action) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + mc_sysdev_add(sys_dev); + break; + case CPU_DOWN_PREPARE: + mc_sysdev_remove(sys_dev); + break; + } + return NOTIFY_OK; +} + +static struct notifier_block mc_cpu_notifier = { + .notifier_call = mc_cpu_callback, +}; +#endif + +static int __init microcode_init (void) +{ + int error; + + error = microcode_dev_init(); + if (error) + return error; + microcode_pdev = platform_device_register_simple("microcode", -1, + NULL, 0); + if (IS_ERR(microcode_pdev)) { + microcode_dev_exit(); + return PTR_ERR(microcode_pdev); + } + + lock_cpu_hotplug(); + error = sysdev_driver_register(&cpu_sysdev_class, &mc_sysdev_driver); + unlock_cpu_hotplug(); + if (error) { + microcode_dev_exit(); + platform_device_unregister(microcode_pdev); + return error; + } + + register_hotcpu_notifier(&mc_cpu_notifier); + printk(KERN_INFO "IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@veritas.com>\n"); return 0; @@ -515,9 +756,16 @@ static int __init microcode_init (void) static void __exit microcode_exit (void) { - misc_deregister(µcode_dev); + microcode_dev_exit(); + + unregister_hotcpu_notifier(&mc_cpu_notifier); + + lock_cpu_hotplug(); + sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver); + unlock_cpu_hotplug(); + + platform_device_unregister(microcode_pdev); } module_init(microcode_init) module_exit(microcode_exit) -MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 76a524b4c90f..814cdebf7377 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -1089,22 +1089,20 @@ static unsigned long __init setup_memory(void) void __init zone_sizes_init(void) { - unsigned long zones_size[MAX_NR_ZONES] = { 0, }; - unsigned int max_dma, low; - - max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - low = max_low_pfn; - - if (low < max_dma) - zones_size[ZONE_DMA] = low; - else { - zones_size[ZONE_DMA] = max_dma; - zones_size[ZONE_NORMAL] = low - max_dma; #ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = highend_pfn - low; + unsigned long max_zone_pfns[MAX_NR_ZONES] = { + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, + max_low_pfn, + highend_pfn}; + add_active_range(0, 0, highend_pfn); +#else + unsigned long max_zone_pfns[MAX_NR_ZONES] = { + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, + max_low_pfn}; + add_active_range(0, 0, max_low_pfn); #endif - } - free_area_init(zones_size); + + free_area_init_nodes(max_zone_pfns); } #else extern unsigned long __init setup_memory(void); diff --git a/arch/i386/kernel/srat.c b/arch/i386/kernel/srat.c index 83db411b3aa7..32413122c4c2 100644 --- a/arch/i386/kernel/srat.c +++ b/arch/i386/kernel/srat.c @@ -54,8 +54,6 @@ struct node_memory_chunk_s { static struct node_memory_chunk_s node_memory_chunk[MAXCHUNKS]; static int num_memory_chunks; /* total number of memory chunks */ -static int zholes_size_init; -static unsigned long zholes_size[MAX_NUMNODES * MAX_NR_ZONES]; extern void * boot_ioremap(unsigned long, unsigned long); @@ -135,47 +133,6 @@ static void __init parse_memory_affinity_structure (char *sratp) "enabled and removable" : "enabled" ) ); } -/* Take a chunk of pages from page frame cstart to cend and count the number - * of pages in each zone, returned via zones[]. - */ -static __init void chunk_to_zones(unsigned long cstart, unsigned long cend, - unsigned long *zones) -{ - unsigned long max_dma; - extern unsigned long max_low_pfn; - - int z; - unsigned long rend; - - /* FIXME: MAX_DMA_ADDRESS and max_low_pfn are trying to provide - * similarly scoped information and should be handled in a consistant - * manner. - */ - max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - - /* Split the hole into the zones in which it falls. Repeatedly - * take the segment in which the remaining hole starts, round it - * to the end of that zone. - */ - memset(zones, 0, MAX_NR_ZONES * sizeof(long)); - while (cstart < cend) { - if (cstart < max_dma) { - z = ZONE_DMA; - rend = (cend < max_dma)? cend : max_dma; - - } else if (cstart < max_low_pfn) { - z = ZONE_NORMAL; - rend = (cend < max_low_pfn)? cend : max_low_pfn; - - } else { - z = ZONE_HIGHMEM; - rend = cend; - } - zones[z] += rend - cstart; - cstart = rend; - } -} - /* * The SRAT table always lists ascending addresses, so can always * assume that the first "start" address that you see is the real @@ -220,7 +177,6 @@ static int __init acpi20_parse_srat(struct acpi_table_srat *sratp) memset(pxm_bitmap, 0, sizeof(pxm_bitmap)); /* init proximity domain bitmap */ memset(node_memory_chunk, 0, sizeof(node_memory_chunk)); - memset(zholes_size, 0, sizeof(zholes_size)); num_memory_chunks = 0; while (p < end) { @@ -284,6 +240,7 @@ static int __init acpi20_parse_srat(struct acpi_table_srat *sratp) printk("chunk %d nid %d start_pfn %08lx end_pfn %08lx\n", j, chunk->nid, chunk->start_pfn, chunk->end_pfn); node_read_chunk(chunk->nid, chunk); + add_active_range(chunk->nid, chunk->start_pfn, chunk->end_pfn); } for_each_online_node(nid) { @@ -392,57 +349,7 @@ int __init get_memcfg_from_srat(void) return acpi20_parse_srat((struct acpi_table_srat *)header); } out_err: + remove_all_active_ranges(); printk("failed to get NUMA memory information from SRAT table\n"); return 0; } - -/* For each node run the memory list to determine whether there are - * any memory holes. For each hole determine which ZONE they fall - * into. - * - * NOTE#1: this requires knowledge of the zone boundries and so - * _cannot_ be performed before those are calculated in setup_memory. - * - * NOTE#2: we rely on the fact that the memory chunks are ordered by - * start pfn number during setup. - */ -static void __init get_zholes_init(void) -{ - int nid; - int c; - int first; - unsigned long end = 0; - - for_each_online_node(nid) { - first = 1; - for (c = 0; c < num_memory_chunks; c++){ - if (node_memory_chunk[c].nid == nid) { - if (first) { - end = node_memory_chunk[c].end_pfn; - first = 0; - - } else { - /* Record any gap between this chunk - * and the previous chunk on this node - * against the zones it spans. - */ - chunk_to_zones(end, - node_memory_chunk[c].start_pfn, - &zholes_size[nid * MAX_NR_ZONES]); - } - } - } - } -} - -unsigned long * __init get_zholes_size(int nid) -{ - if (!zholes_size_init) { - zholes_size_init++; - get_zholes_init(); - } - if (nid >= MAX_NUMNODES || !node_online(nid)) - printk("%s: nid = %d is invalid/offline. num_online_nodes = %d", - __FUNCTION__, nid, num_online_nodes()); - return &zholes_size[nid * MAX_NR_ZONES]; -} diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 21aa1cd57773..a13037fe0ee3 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -28,6 +28,7 @@ #include <linux/kprobes.h> #include <linux/kexec.h> #include <linux/unwind.h> +#include <linux/uaccess.h> #ifdef CONFIG_EISA #include <linux/ioport.h> @@ -40,7 +41,6 @@ #include <asm/processor.h> #include <asm/system.h> -#include <asm/uaccess.h> #include <asm/io.h> #include <asm/atomic.h> #include <asm/debugreg.h> @@ -409,7 +409,7 @@ static void handle_BUG(struct pt_regs *regs) if (eip < PAGE_OFFSET) return; - if (__get_user(ud2, (unsigned short __user *)eip)) + if (probe_kernel_address((unsigned short __user *)eip, ud2)) return; if (ud2 != 0x0b0f) return; @@ -422,7 +422,8 @@ static void handle_BUG(struct pt_regs *regs) char *file; char c; - if (__get_user(line, (unsigned short __user *)(eip + 2))) + if (probe_kernel_address((unsigned short __user *)(eip + 2), + line)) break; if (__get_user(file, (char * __user *)(eip + 4)) || (unsigned long)file < PAGE_OFFSET || __get_user(c, file)) diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index 941d1a5ebabb..51e3739dd227 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -157,21 +157,6 @@ static void __init find_max_pfn_node(int nid) BUG(); } -/* Find the owning node for a pfn. */ -int early_pfn_to_nid(unsigned long pfn) -{ - int nid; - - for_each_node(nid) { - if (node_end_pfn[nid] == 0) - break; - if (node_start_pfn[nid] <= pfn && node_end_pfn[nid] >= pfn) - return nid; - } - - return 0; -} - /* * Allocate memory for the pg_data_t for this node via a crude pre-bootmem * method. For node zero take this from the bottom of memory, for @@ -227,6 +212,8 @@ static unsigned long calculate_numa_remap_pages(void) unsigned long pfn; for_each_online_node(nid) { + unsigned old_end_pfn = node_end_pfn[nid]; + /* * The acpi/srat node info can show hot-add memroy zones * where memory could be added but not currently present. @@ -276,6 +263,7 @@ static unsigned long calculate_numa_remap_pages(void) node_end_pfn[nid] -= size; node_remap_start_pfn[nid] = node_end_pfn[nid]; + shrink_active_range(nid, old_end_pfn, node_end_pfn[nid]); } printk("Reserving total of %ld pages for numa KVA remap\n", reserve_pages); @@ -369,45 +357,22 @@ void __init numa_kva_reserve(void) void __init zone_sizes_init(void) { int nid; - - - for_each_online_node(nid) { - unsigned long zones_size[MAX_NR_ZONES] = {0, }; - unsigned long *zholes_size; - unsigned int max_dma; - - unsigned long low = max_low_pfn; - unsigned long start = node_start_pfn[nid]; - unsigned long high = node_end_pfn[nid]; - - max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - - if (node_has_online_mem(nid)){ - if (start > low) { -#ifdef CONFIG_HIGHMEM - BUG_ON(start > high); - zones_size[ZONE_HIGHMEM] = high - start; -#endif - } else { - if (low < max_dma) - zones_size[ZONE_DMA] = low; - else { - BUG_ON(max_dma > low); - BUG_ON(low > high); - zones_size[ZONE_DMA] = max_dma; - zones_size[ZONE_NORMAL] = low - max_dma; -#ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = high - low; -#endif - } - } + unsigned long max_zone_pfns[MAX_NR_ZONES] = { + virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT, + max_low_pfn, + highend_pfn + }; + + /* If SRAT has not registered memory, register it now */ + if (find_max_pfn_with_active_regions() == 0) { + for_each_online_node(nid) { + if (node_has_online_mem(nid)) + add_active_range(nid, node_start_pfn[nid], + node_end_pfn[nid]); } - - zholes_size = get_zholes_size(nid); - - free_area_init_node(nid, NODE_DATA(nid), zones_size, start, - zholes_size); } + + free_area_init_nodes(max_zone_pfns); return; } |