4 files changed, 149 insertions, 185 deletions

diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 157190d986b..d206d7e49cf 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -1064,7 +1064,6 @@ void print_all_local_APICs (void)
 
 void __apicdebuginit print_PIC(void)
 {
-	extern spinlock_t i8259A_lock;
 	unsigned int v;
 	unsigned long flags;
 
diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c
index 4e680f87a75..5c6dc705148 100644
--- a/arch/x86_64/kernel/kprobes.c
+++ b/arch/x86_64/kernel/kprobes.c
@@ -38,7 +38,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/preempt.h>
-#include <linux/moduleloader.h>
+
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/kdebug.h>
@@ -51,8 +51,6 @@ static struct kprobe *kprobe_prev;
 static unsigned long kprobe_status_prev, kprobe_old_rflags_prev, kprobe_saved_rflags_prev;
 static struct pt_regs jprobe_saved_regs;
 static long *jprobe_saved_rsp;
-static kprobe_opcode_t *get_insn_slot(void);
-static void free_insn_slot(kprobe_opcode_t *slot);
 void jprobe_return_end(void);
 
 /* copy of the kernel stack at the probe fire time */
@@ -274,48 +272,23 @@ static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->rip = (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 *)regs->rsp;
-	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++;
+        }
 }
 
 /*
@@ -428,36 +401,59 @@ 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 *)regs->rsp - 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 *)regs->rsp) - 1;
+        head = kretprobe_inst_table_head(current);
 
-	while ((ri = get_rp_inst(sara))) {
-		regs->rip = (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->rip = 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;
 }
 
 /*
@@ -550,8 +546,7 @@ 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_rflags;
 
 	/* Restore the original saved kprobes variables and continue. */
@@ -682,111 +677,12 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 
-/*
- * kprobe->ainsn.insn points to the copy of the instruction to be single-stepped.
- * By default on x86_64, pages we get from kmalloc or vmalloc are not
- * executable.  Single-stepping an instruction on such a page yields an
- * oops.  So instead of storing the instruction copies in their respective
- * kprobe objects, we allocate a page, map it executable, and store all the
- * instruction copies there.  (We can allocate additional pages if somebody
- * inserts a huge number of probes.)  Each page can hold up to INSNS_PER_PAGE
- * instruction slots, each of which is MAX_INSN_SIZE*sizeof(kprobe_opcode_t)
- * bytes.
- */
-#define INSNS_PER_PAGE (PAGE_SIZE/(MAX_INSN_SIZE*sizeof(kprobe_opcode_t)))
-struct kprobe_insn_page {
-	struct hlist_node hlist;
-	kprobe_opcode_t *insns;		/* page of instruction slots */
-	char slot_used[INSNS_PER_PAGE];
-	int nused;
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
 };
 
-static struct hlist_head kprobe_insn_pages;
-
-/**
- * get_insn_slot() - Find a slot on an executable page for an instruction.
- * We allocate an executable page if there's no room on existing ones.
- */
-static kprobe_opcode_t *get_insn_slot(void)
-{
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
-
-	hlist_for_each(pos, &kprobe_insn_pages) {
-		kip = hlist_entry(pos, struct kprobe_insn_page, hlist);
-		if (kip->nused < INSNS_PER_PAGE) {
-			int i;
-			for (i = 0; i < INSNS_PER_PAGE; i++) {
-				if (!kip->slot_used[i]) {
-					kip->slot_used[i] = 1;
-					kip->nused++;
-					return kip->insns + (i*MAX_INSN_SIZE);
-				}
-			}
-			/* Surprise!  No unused slots.  Fix kip->nused. */
-			kip->nused = INSNS_PER_PAGE;
-		}
-	}
-
-	/* All out of space.  Need to allocate a new page. Use slot 0.*/
-	kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
-	if (!kip) {
-		return NULL;
-	}
-
-	/*
-	 * For the %rip-relative displacement fixups to be doable, we
-	 * need our instruction copy to be within +/- 2GB of any data it
-	 * might access via %rip.  That is, within 2GB of where the
-	 * kernel image and loaded module images reside.  So we allocate
-	 * a page in the module loading area.
-	 */
-	kip->insns = module_alloc(PAGE_SIZE);
-	if (!kip->insns) {
-		kfree(kip);
-		return NULL;
-	}
-	INIT_HLIST_NODE(&kip->hlist);
-	hlist_add_head(&kip->hlist, &kprobe_insn_pages);
-	memset(kip->slot_used, 0, INSNS_PER_PAGE);
-	kip->slot_used[0] = 1;
-	kip->nused = 1;
-	return kip->insns;
-}
-
-/**
- * free_insn_slot() - Free instruction slot obtained from get_insn_slot().
- */
-static void free_insn_slot(kprobe_opcode_t *slot)
+int __init arch_init_kprobes(void)
 {
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
-
-	hlist_for_each(pos, &kprobe_insn_pages) {
-		kip = hlist_entry(pos, struct kprobe_insn_page, hlist);
-		if (kip->insns <= slot
-		    && slot < kip->insns+(INSNS_PER_PAGE*MAX_INSN_SIZE)) {
-			int i = (slot - kip->insns) / MAX_INSN_SIZE;
-			kip->slot_used[i] = 0;
-			kip->nused--;
-			if (kip->nused == 0) {
-				/*
-				 * Page is no longer in use.  Free it unless
-				 * it's the last one.  We keep the last one
-				 * so as not to have to set it up again the
-				 * next time somebody inserts a probe.
-				 */
-				hlist_del(&kip->hlist);
-				if (hlist_empty(&kprobe_insn_pages)) {
-					INIT_HLIST_NODE(&kip->hlist);
-					hlist_add_head(&kip->hlist,
-						&kprobe_insn_pages);
-				} else {
-					module_free(NULL, kip->insns);
-					kfree(kip);
-				}
-			}
-			return;
-		}
-	}
+	return register_kprobe(&trampoline_p);
 }
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 1d91271796e..7577f9d7a75 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -482,6 +482,33 @@ out:
 }
 
 /*
+ * 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);
+	}
+}
+
+/*
  * This special macro can be used to load a debugging register
  */
 #define loaddebug(thread,r) set_debug(thread->debugreg ## r, r)
@@ -599,6 +626,8 @@ struct task_struct *__switch_to(struct task_struct *prev_p, struct task_struct *
 		}
 	}
 
+	disable_tsc(prev_p, next_p);
+
 	return prev_p;
 }
 
diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c
index b693c232fd0..657e88aa090 100644
--- a/arch/x86_64/pci/mmconfig.c
+++ b/arch/x86_64/pci/mmconfig.c
@@ -7,25 +7,50 @@
 
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/acpi.h>
 #include "pci.h"
 
 #define MMCONFIG_APER_SIZE (256*1024*1024)
 
-/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
-u32 pci_mmcfg_base_addr;
-
 /* Static virtual mapping of the MMCONFIG aperture */
-char *pci_mmcfg_virt;
+struct mmcfg_virt {
+	struct acpi_table_mcfg_config *cfg;
+	char *virt;
+};
+static struct mmcfg_virt *pci_mmcfg_virt;
 
-static inline char *pci_dev_base(unsigned int bus, unsigned int devfn)
+static char *get_virt(unsigned int seg, int bus)
 {
-	return pci_mmcfg_virt + ((bus << 20) | (devfn << 12));
+	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_virt[0].virt;
+		}
+		cfg = pci_mmcfg_virt[cfg_num].cfg;
+		if (cfg->pci_segment_group_number != seg)
+			continue;
+		if ((cfg->start_bus_number <= bus) &&
+		    (cfg->end_bus_number >= bus))
+			return pci_mmcfg_virt[cfg_num].virt;
+	}
+}
+
+static inline char *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn)
+{
+
+	return get_virt(seg, bus) + ((bus << 20) | (devfn << 12));
 }
 
 static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
-	char *addr = pci_dev_base(bus, devfn); 
+	char *addr = pci_dev_base(seg, bus, devfn);
 
 	if (unlikely(!value || (bus > 255) || (devfn > 255) || (reg > 4095)))
 		return -EINVAL;
@@ -48,7 +73,7 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 			   unsigned int devfn, int reg, int len, u32 value)
 {
-	char *addr = pci_dev_base(bus,devfn);
+	char *addr = pci_dev_base(seg, bus, devfn);
 
 	if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095)))
 		return -EINVAL;
@@ -75,9 +100,15 @@ static struct pci_raw_ops pci_mmcfg = {
 
 static int __init pci_mmcfg_init(void)
 {
+	int i;
+
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
 		return 0;
-	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))
 		return 0;
 
 	/* Kludge for now. Don't use mmconfig on AMD systems because
@@ -88,13 +119,22 @@ static int __init pci_mmcfg_init(void)
 		return 0; 
 
 	/* RED-PEN i386 doesn't do _nocache right now */
-	pci_mmcfg_virt = ioremap_nocache(pci_mmcfg_base_addr, MMCONFIG_APER_SIZE);
-	if (!pci_mmcfg_virt) { 
-		printk("PCI: Cannot map mmconfig aperture\n");
+	pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL);
+	if (pci_mmcfg_virt == NULL) {
+		printk("PCI: Can not allocate memory for mmconfig structures\n");
 		return 0;
-	}	
+	}
+	for (i = 0; i < pci_mmcfg_config_num; ++i) {
+		pci_mmcfg_virt[i].cfg = &pci_mmcfg_config[i];
+		pci_mmcfg_virt[i].virt = ioremap_nocache(pci_mmcfg_config[i].base_address, MMCONFIG_APER_SIZE);
+		if (!pci_mmcfg_virt[i].virt) {
+			printk("PCI: Cannot map mmconfig aperture for segment %d\n",
+			       pci_mmcfg_config[i].pci_segment_group_number);
+			return 0;
+		}
+		printk(KERN_INFO "PCI: Using MMCONFIG at %x\n", pci_mmcfg_config[i].base_address);
+	}
 
-	printk(KERN_INFO "PCI: Using MMCONFIG at %x\n", pci_mmcfg_base_addr);
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;