diff options
Diffstat (limited to 'arch/i386')
-rw-r--r-- | arch/i386/boot/tools/build.c | 3 | ||||
-rw-r--r-- | arch/i386/kernel/acpi/boot.c | 57 | ||||
-rw-r--r-- | arch/i386/kernel/kprobes.c | 133 | ||||
-rw-r--r-- | arch/i386/kernel/process.c | 29 | ||||
-rw-r--r-- | arch/i386/kernel/syscall_table.S | 2 | ||||
-rw-r--r-- | arch/i386/pci/common.c | 8 | ||||
-rw-r--r-- | arch/i386/pci/irq.c | 51 | ||||
-rw-r--r-- | arch/i386/pci/legacy.c | 2 | ||||
-rw-r--r-- | arch/i386/pci/mmconfig.c | 39 | ||||
-rw-r--r-- | arch/i386/pci/numa.c | 2 | ||||
-rw-r--r-- | arch/i386/pci/pci.h | 1 |
11 files changed, 231 insertions, 96 deletions
diff --git a/arch/i386/boot/tools/build.c b/arch/i386/boot/tools/build.c index 4a17956..6835f6d 100644 --- a/arch/i386/boot/tools/build.c +++ b/arch/i386/boot/tools/build.c @@ -70,7 +70,8 @@ void usage(void) int main(int argc, char ** argv) { - unsigned int i, c, sz, setup_sectors; + unsigned int i, sz, setup_sectors; + int c; u32 sys_size; byte major_root, minor_root; struct stat sb; diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 9f63ae0..b7808a8 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -159,9 +159,15 @@ char *__acpi_map_table(unsigned long phys, unsigned long size) #endif #ifdef CONFIG_PCI_MMCONFIG -static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size) +/* The physical address of the MMCONFIG aperture. Set from ACPI tables. */ +struct acpi_table_mcfg_config *pci_mmcfg_config; +int pci_mmcfg_config_num; + +int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size) { struct acpi_table_mcfg *mcfg; + unsigned long i; + int config_size; if (!phys_addr || !size) return -EINVAL; @@ -172,18 +178,38 @@ static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size) return -ENODEV; } - if (mcfg->base_reserved) { - printk(KERN_ERR PREFIX "MMCONFIG not in low 4GB of memory\n"); + /* how many config structures do we have */ + pci_mmcfg_config_num = 0; + i = size - sizeof(struct acpi_table_mcfg); + while (i >= sizeof(struct acpi_table_mcfg_config)) { + ++pci_mmcfg_config_num; + i -= sizeof(struct acpi_table_mcfg_config); + }; + if (pci_mmcfg_config_num == 0) { + printk(KERN_ERR PREFIX "MMCONFIG has no entries\n"); return -ENODEV; } - pci_mmcfg_base_addr = mcfg->base_address; + config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config); + pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL); + if (!pci_mmcfg_config) { + printk(KERN_WARNING PREFIX + "No memory for MCFG config tables\n"); + return -ENOMEM; + } + + memcpy(pci_mmcfg_config, &mcfg->config, config_size); + for (i = 0; i < pci_mmcfg_config_num; ++i) { + if (mcfg->config[i].base_reserved) { + printk(KERN_ERR PREFIX + "MMCONFIG not in low 4GB of memory\n"); + return -ENODEV; + } + } return 0; } -#else -#define acpi_parse_mcfg NULL -#endif /* !CONFIG_PCI_MMCONFIG */ +#endif /* CONFIG_PCI_MMCONFIG */ #ifdef CONFIG_X86_LOCAL_APIC static int __init @@ -507,6 +533,22 @@ acpi_unmap_lsapic(int cpu) EXPORT_SYMBOL(acpi_unmap_lsapic); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +int +acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) +{ + /* TBD */ + return -EINVAL; +} +EXPORT_SYMBOL(acpi_register_ioapic); + +int +acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base) +{ + /* TBD */ + return -EINVAL; +} +EXPORT_SYMBOL(acpi_unregister_ioapic); + static unsigned long __init acpi_scan_rsdp ( unsigned long start, @@ -1123,7 +1165,6 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_HPET, acpi_parse_hpet); - acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg); return 0; } diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index 3762f6b..fc8b175 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -127,48 +127,23 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs) regs->eip = (unsigned long)&p->ainsn.insn; } -struct task_struct *arch_get_kprobe_task(void *ptr) -{ - return ((struct thread_info *) (((unsigned long) ptr) & - (~(THREAD_SIZE -1))))->task; -} - void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { unsigned long *sara = (unsigned long *)®s->esp; - struct kretprobe_instance *ri; - static void *orig_ret_addr; + struct kretprobe_instance *ri; + + if ((ri = get_free_rp_inst(rp)) != NULL) { + ri->rp = rp; + ri->task = current; + ri->ret_addr = (kprobe_opcode_t *) *sara; - /* - * Save the return address when the return probe hits - * the first time, and use it to populate the (krprobe - * instance)->ret_addr for subsequent return probes at - * the same addrress since stack address would have - * the kretprobe_trampoline by then. - */ - if (((void*) *sara) != kretprobe_trampoline) - orig_ret_addr = (void*) *sara; - - if ((ri = get_free_rp_inst(rp)) != NULL) { - ri->rp = rp; - ri->stack_addr = sara; - ri->ret_addr = orig_ret_addr; - add_rp_inst(ri); /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; - } else { - rp->nmissed++; - } -} -void arch_kprobe_flush_task(struct task_struct *tk) -{ - struct kretprobe_instance *ri; - while ((ri = get_rp_inst_tsk(tk)) != NULL) { - *((unsigned long *)(ri->stack_addr)) = - (unsigned long) ri->ret_addr; - recycle_rp_inst(ri); - } + add_rp_inst(ri); + } else { + rp->nmissed++; + } } /* @@ -286,36 +261,59 @@ no_kprobe: */ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - struct task_struct *tsk; - struct kretprobe_instance *ri; - struct hlist_head *head; - struct hlist_node *node; - unsigned long *sara = ((unsigned long *) ®s->esp) - 1; - - tsk = arch_get_kprobe_task(sara); - head = kretprobe_inst_table_head(tsk); - - hlist_for_each_entry(ri, node, head, hlist) { - if (ri->stack_addr == sara && ri->rp) { - if (ri->rp->handler) - ri->rp->handler(ri, regs); - } - } - return 0; -} + struct kretprobe_instance *ri = NULL; + struct hlist_head *head; + struct hlist_node *node, *tmp; + unsigned long orig_ret_address = 0; + unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; -void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs, - unsigned long flags) -{ - struct kretprobe_instance *ri; - /* RA already popped */ - unsigned long *sara = ((unsigned long *)®s->esp) - 1; + head = kretprobe_inst_table_head(current); - while ((ri = get_rp_inst(sara))) { - regs->eip = (unsigned long)ri->ret_addr; + /* + * It is possible to have multiple instances associated with a given + * task either because an multiple functions in the call path + * have a return probe installed on them, and/or more then one return + * return probe was registered for a target function. + * + * We can handle this because: + * - instances are always inserted at the head of the list + * - when multiple return probes are registered for the same + * function, the first instance's ret_addr will point to the + * real return address, and all the rest will point to + * kretprobe_trampoline + */ + hlist_for_each_entry_safe(ri, node, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + if (ri->rp && ri->rp->handler) + ri->rp->handler(ri, regs); + + orig_ret_address = (unsigned long)ri->ret_addr; recycle_rp_inst(ri); + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; } - regs->eflags &= ~TF_MASK; + + BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address)); + regs->eip = orig_ret_address; + + unlock_kprobes(); + preempt_enable_no_resched(); + + /* + * By returning a non-zero value, we are telling + * kprobe_handler() that we have handled unlocking + * and re-enabling preemption. + */ + return 1; } /* @@ -403,8 +401,7 @@ static inline int post_kprobe_handler(struct pt_regs *regs) current_kprobe->post_handler(current_kprobe, regs, 0); } - if (current_kprobe->post_handler != trampoline_post_handler) - resume_execution(current_kprobe, regs); + resume_execution(current_kprobe, regs); regs->eflags |= kprobe_saved_eflags; /*Restore back the original saved kprobes variables and continue. */ @@ -534,3 +531,13 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) } return 0; } + +static struct kprobe trampoline_p = { + .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .pre_handler = trampoline_probe_handler +}; + +int __init arch_init(void) +{ + return register_kprobe(&trampoline_p); +} diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 5f8cfa6..ba243a4 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -617,6 +617,33 @@ handle_io_bitmap(struct thread_struct *next, struct tss_struct *tss) } /* + * This function selects if the context switch from prev to next + * has to tweak the TSC disable bit in the cr4. + */ +static inline void disable_tsc(struct task_struct *prev_p, + struct task_struct *next_p) +{ + struct thread_info *prev, *next; + + /* + * gcc should eliminate the ->thread_info dereference if + * has_secure_computing returns 0 at compile time (SECCOMP=n). + */ + prev = prev_p->thread_info; + next = next_p->thread_info; + + if (has_secure_computing(prev) || has_secure_computing(next)) { + /* slow path here */ + if (has_secure_computing(prev) && + !has_secure_computing(next)) { + write_cr4(read_cr4() & ~X86_CR4_TSD); + } else if (!has_secure_computing(prev) && + has_secure_computing(next)) + write_cr4(read_cr4() | X86_CR4_TSD); + } +} + +/* * switch_to(x,yn) should switch tasks from x to y. * * We fsave/fwait so that an exception goes off at the right time @@ -695,6 +722,8 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) handle_io_bitmap(next, tss); + disable_tsc(prev_p, next_p); + return prev_p; } diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index 442a6e9..3db9a04 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -289,3 +289,5 @@ ENTRY(sys_call_table) .long sys_add_key .long sys_request_key .long sys_keyctl + .long sys_ioprio_set + .long sys_ioprio_get /* 290 */ diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c index 720975e..8732526 100644 --- a/arch/i386/pci/common.c +++ b/arch/i386/pci/common.c @@ -25,7 +25,8 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | int pci_routeirq; int pcibios_last_bus = -1; -struct pci_bus *pci_root_bus = NULL; +unsigned long pirq_table_addr; +struct pci_bus *pci_root_bus; struct pci_raw_ops *raw_pci_ops; static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value) @@ -133,7 +134,7 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum) printk("PCI: Probing PCI hardware (bus %02x)\n", busnum); - return pci_scan_bus(busnum, &pci_root_ops, NULL); + return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, NULL); } extern u8 pci_cache_line_size; @@ -188,6 +189,9 @@ char * __devinit pcibios_setup(char *str) } else if (!strcmp(str, "biosirq")) { pci_probe |= PCI_BIOS_IRQ_SCAN; return NULL; + } else if (!strncmp(str, "pirqaddr=", 9)) { + pirq_table_addr = simple_strtoul(str+9, NULL, 0); + return NULL; } #endif #ifdef CONFIG_PCI_DIRECT diff --git a/arch/i386/pci/irq.c b/arch/i386/pci/irq.c index 83458f8..78ca1ec 100644 --- a/arch/i386/pci/irq.c +++ b/arch/i386/pci/irq.c @@ -58,6 +58,35 @@ struct irq_router_handler { int (*pcibios_enable_irq)(struct pci_dev *dev) = NULL; /* + * Check passed address for the PCI IRQ Routing Table signature + * and perform checksum verification. + */ + +static inline struct irq_routing_table * pirq_check_routing_table(u8 *addr) +{ + struct irq_routing_table *rt; + int i; + u8 sum; + + rt = (struct irq_routing_table *) addr; + if (rt->signature != PIRQ_SIGNATURE || + rt->version != PIRQ_VERSION || + rt->size % 16 || + rt->size < sizeof(struct irq_routing_table)) + return NULL; + sum = 0; + for (i=0; i < rt->size; i++) + sum += addr[i]; + if (!sum) { + DBG("PCI: Interrupt Routing Table found at 0x%p\n", rt); + return rt; + } + return NULL; +} + + + +/* * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table. */ @@ -65,23 +94,17 @@ static struct irq_routing_table * __init pirq_find_routing_table(void) { u8 *addr; struct irq_routing_table *rt; - int i; - u8 sum; + if (pirq_table_addr) { + rt = pirq_check_routing_table((u8 *) __va(pirq_table_addr)); + if (rt) + return rt; + printk(KERN_WARNING "PCI: PIRQ table NOT found at pirqaddr\n"); + } for(addr = (u8 *) __va(0xf0000); addr < (u8 *) __va(0x100000); addr += 16) { - rt = (struct irq_routing_table *) addr; - if (rt->signature != PIRQ_SIGNATURE || - rt->version != PIRQ_VERSION || - rt->size % 16 || - rt->size < sizeof(struct irq_routing_table)) - continue; - sum = 0; - for(i=0; i<rt->size; i++) - sum += addr[i]; - if (!sum) { - DBG("PCI: Interrupt Routing Table found at 0x%p\n", rt); + rt = pirq_check_routing_table(addr); + if (rt) return rt; - } } return NULL; } diff --git a/arch/i386/pci/legacy.c b/arch/i386/pci/legacy.c index 1492e37..149a958 100644 --- a/arch/i386/pci/legacy.c +++ b/arch/i386/pci/legacy.c @@ -45,6 +45,8 @@ static int __init pci_legacy_init(void) printk("PCI: Probing PCI hardware\n"); pci_root_bus = pcibios_scan_root(0); + if (pci_root_bus) + pci_bus_add_devices(pci_root_bus); pcibios_fixup_peer_bridges(); diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index 021a50a..60f0e7a 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -11,11 +11,9 @@ #include <linux/pci.h> #include <linux/init.h> +#include <linux/acpi.h> #include "pci.h" -/* The physical address of the MMCONFIG aperture. Set from ACPI tables. */ -u32 pci_mmcfg_base_addr; - #define mmcfg_virt_addr ((void __iomem *) fix_to_virt(FIX_PCIE_MCFG)) /* The base address of the last MMCONFIG device accessed */ @@ -24,10 +22,31 @@ static u32 mmcfg_last_accessed_device; /* * Functions for accessing PCI configuration space with MMCONFIG accesses */ +static u32 get_base_addr(unsigned int seg, int bus) +{ + int cfg_num = -1; + struct acpi_table_mcfg_config *cfg; + + while (1) { + ++cfg_num; + if (cfg_num >= pci_mmcfg_config_num) { + /* something bad is going on, no cfg table is found. */ + /* so we fall back to the old way we used to do this */ + /* and just rely on the first entry to be correct. */ + return pci_mmcfg_config[0].base_address; + } + cfg = &pci_mmcfg_config[cfg_num]; + if (cfg->pci_segment_group_number != seg) + continue; + if ((cfg->start_bus_number <= bus) && + (cfg->end_bus_number >= bus)) + return cfg->base_address; + } +} -static inline void pci_exp_set_dev_base(int bus, int devfn) +static inline void pci_exp_set_dev_base(unsigned int seg, int bus, int devfn) { - u32 dev_base = pci_mmcfg_base_addr | (bus << 20) | (devfn << 12); + u32 dev_base = get_base_addr(seg, bus) | (bus << 20) | (devfn << 12); if (dev_base != mmcfg_last_accessed_device) { mmcfg_last_accessed_device = dev_base; set_fixmap_nocache(FIX_PCIE_MCFG, dev_base); @@ -44,7 +63,7 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus, spin_lock_irqsave(&pci_config_lock, flags); - pci_exp_set_dev_base(bus, devfn); + pci_exp_set_dev_base(seg, bus, devfn); switch (len) { case 1: @@ -73,7 +92,7 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, spin_lock_irqsave(&pci_config_lock, flags); - pci_exp_set_dev_base(bus, devfn); + pci_exp_set_dev_base(seg, bus, devfn); switch (len) { case 1: @@ -101,7 +120,11 @@ static int __init pci_mmcfg_init(void) { if ((pci_probe & PCI_PROBE_MMCONF) == 0) goto out; - if (!pci_mmcfg_base_addr) + + acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg); + if ((pci_mmcfg_config_num == 0) || + (pci_mmcfg_config == NULL) || + (pci_mmcfg_config[0].base_address == 0)) goto out; /* Kludge for now. Don't use mmconfig on AMD systems because diff --git a/arch/i386/pci/numa.c b/arch/i386/pci/numa.c index 9e36954..adbe17a 100644 --- a/arch/i386/pci/numa.c +++ b/arch/i386/pci/numa.c @@ -115,6 +115,8 @@ static int __init pci_numa_init(void) return 0; pci_root_bus = pcibios_scan_root(0); + if (pci_root_bus) + pci_bus_add_devices(pci_root_bus); if (num_online_nodes() > 1) for_each_online_node(quad) { if (quad == 0) diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h index a8fc80c..a80f0f5 100644 --- a/arch/i386/pci/pci.h +++ b/arch/i386/pci/pci.h @@ -27,6 +27,7 @@ #define PCI_ASSIGN_ALL_BUSSES 0x4000 extern unsigned int pci_probe; +extern unsigned long pirq_table_addr; /* pci-i386.c */ |