Merge branches 'x86/paravirt', 'x86/pat', 'x86/setup-v2', 'x86/subarch', 'x86/uaccess' and 'x86/urgent' into x86/core

arch/x86/boot/a20.c

@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -15,16 +16,23 @@
 #include "boot.h"
 
 #define MAX_8042_LOOPS	100000
+#define MAX_8042_FF	32
 
 static int empty_8042(void)
 {
 	u8 status;
 	int loops = MAX_8042_LOOPS;
+	int ffs   = MAX_8042_FF;
 
 	while (loops--) {
 		io_delay();
 
 		status = inb(0x64);
+		if (status == 0xff) {
+			/* FF is a plausible, but very unlikely status */
+			if (!--ffs)
+				return -1; /* Assume no KBC present */
+		}
 		if (status & 1) {
 			/* Read and discard input data */
 			io_delay();
@@ -118,18 +126,14 @@ static void enable_a20_fast(void)
 
 int enable_a20(void)
 {
-#if defined(CONFIG_X86_ELAN)
+#ifdef CONFIG_X86_VOYAGER
-	/* Elan croaks if we try to touch the KBC */
-	enable_a20_fast();
-	while (!a20_test_long())
-		;
-	return 0;
-#elif defined(CONFIG_X86_VOYAGER)
 	/* On Voyager, a20_test() is unsafe? */
 	enable_a20_kbc();
 	return 0;
 #else
        int loops = A20_ENABLE_LOOPS;
+       int kbc_err;
+
        while (loops--) {
 	       /* First, check to see if A20 is already enabled
 		  (legacy free, etc.) */
@@ -142,13 +146,16 @@ int enable_a20(void)
 		       return 0;
 	       
 	       /* Try enabling A20 through the keyboard controller */
-		empty_8042();
+	       kbc_err = empty_8042();
+
 	       if (a20_test_short())
 		       return 0; /* BIOS worked, but with delayed reaction */
 	
+	       if (!kbc_err) {
 		       enable_a20_kbc();
 		       if (a20_test_long())
 			       return 0;
+	       }
 	       
 	       /* Finally, try enabling the "fast A20 gate" */
 	       enable_a20_fast();

arch/x86/include/asm/page.h

@@ -57,7 +57,6 @@ typedef struct { pgdval_t pgd; } pgd_t;
 typedef struct { pgprotval_t pgprot; } pgprot_t;
 
 extern int page_is_ram(unsigned long pagenr);
-extern int pagerange_is_ram(unsigned long start, unsigned long end);
 extern int devmem_is_allowed(unsigned long pagenr);
 extern void map_devmem(unsigned long pfn, unsigned long size,
 		       pgprot_t vma_prot);

arch/x86/include/asm/paravirt.h

@@ -1431,14 +1431,7 @@ static inline void arch_leave_lazy_cpu_mode(void)
 	PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
 }
 
-static inline void arch_flush_lazy_cpu_mode(void)
+void arch_flush_lazy_cpu_mode(void);
-{
-	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)) {
-		arch_leave_lazy_cpu_mode();
-		arch_enter_lazy_cpu_mode();
-	}
-}
-
 
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
@@ -1451,13 +1444,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-static inline void arch_flush_lazy_mmu_mode(void)
+void arch_flush_lazy_mmu_mode(void);
-{
-	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU)) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-}
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 				unsigned long phys, pgprot_t flags)

arch/x86/kernel/hpet.c

@@ -269,6 +269,8 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		now = hpet_readl(HPET_COUNTER);
 		cmp = now + (unsigned long) delta;
 		cfg = hpet_readl(HPET_Tn_CFG(timer));
+		/* Make sure we use edge triggered interrupts */
+		cfg &= ~HPET_TN_LEVEL;
 		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
 		       HPET_TN_SETVAL | HPET_TN_32BIT;
 		hpet_writel(cfg, HPET_Tn_CFG(timer));

arch/x86/kernel/paravirt.c

@@ -286,6 +286,32 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return __get_cpu_var(paravirt_lazy_mode);
 }
 
+void arch_flush_lazy_mmu_mode(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		WARN_ON(preempt_count() == 1);
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
+void arch_flush_lazy_cpu_mode(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
+		WARN_ON(preempt_count() == 1);
+		arch_leave_lazy_cpu_mode();
+		arch_enter_lazy_cpu_mode();
+	}
+
+	preempt_enable();
+}
+
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,

arch/x86/kernel/ptrace.c

@@ -805,12 +805,16 @@ static void ptrace_bts_untrace(struct task_struct *child)
 
 static void ptrace_bts_detach(struct task_struct *child)
 {
-	if (unlikely(child->bts)) {
+	/*
-		ds_release_bts(child->bts);
+	 * Ptrace_detach() races with ptrace_untrace() in case
-		child->bts = NULL;
+	 * the child dies and is reaped by another thread.
-
+	 *
-		ptrace_bts_free_buffer(child);
+	 * We only do the memory accounting at this point and
-	}
+	 * leave the buffer deallocation and the bts tracer
+	 * release to ptrace_bts_untrace() which will be called
+	 * later on with tasklist_lock held.
+	 */
+	release_locked_buffer(child->bts_buffer, child->bts_size);
 }
 #else
 static inline void ptrace_bts_fork(struct task_struct *tsk) {}

arch/x86/mm/ioremap.c

@@ -134,25 +134,6 @@ int page_is_ram(unsigned long pagenr)
 	return 0;
 }
 
-int pagerange_is_ram(unsigned long start, unsigned long end)
-{
-	int ram_page = 0, not_rampage = 0;
-	unsigned long page_nr;
-
-	for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
-	     ++page_nr) {
-		if (page_is_ram(page_nr))
-			ram_page = 1;
-		else
-			not_rampage = 1;
-
-		if (ram_page == not_rampage)
-			return -1;
-	}
-
-	return ram_page;
-}
-
 /*
  * Fix up the linear direct mapping of the kernel to avoid cache attribute
  * conflicts.

arch/x86/mm/pageattr.c

@@ -575,7 +575,6 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 		address = cpa->vaddr[cpa->curpage];
 	else
 		address = *cpa->vaddr;
-
 repeat:
 	kpte = lookup_address(address, &level);
 	if (!kpte)
@@ -812,6 +811,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	vm_unmap_aliases();
 
+	/*
+	 * If we're called with lazy mmu updates enabled, the
+	 * in-memory pte state may be stale.  Flush pending updates to
+	 * bring them up to date.
+	 */
+	arch_flush_lazy_mmu_mode();
+
 	cpa.vaddr = addr;
 	cpa.numpages = numpages;
 	cpa.mask_set = mask_set;
@@ -854,6 +860,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	} else
 		cpa_flush_all(cache);
 
+	/*
+	 * If we've been called with lazy mmu updates enabled, then
+	 * make sure that everything gets flushed out before we
+	 * return.
+	 */
+	arch_flush_lazy_mmu_mode();
+
 out:
 	return ret;
 }

arch/x86/mm/pat.c

@@ -220,6 +220,33 @@ chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type)
 static struct memtype *cached_entry;
 static u64 cached_start;
 
+static int pat_pagerange_is_ram(unsigned long start, unsigned long end)
+{
+	int ram_page = 0, not_rampage = 0;
+	unsigned long page_nr;
+
+	for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
+	     ++page_nr) {
+		/*
+		 * For legacy reasons, physical address range in the legacy ISA
+		 * region is tracked as non-RAM. This will allow users of
+		 * /dev/mem to map portions of legacy ISA region, even when
+		 * some of those portions are listed(or not even listed) with
+		 * different e820 types(RAM/reserved/..)
+		 */
+		if (page_nr >= (ISA_END_ADDRESS >> PAGE_SHIFT) &&
+		    page_is_ram(page_nr))
+			ram_page = 1;
+		else
+			not_rampage = 1;
+
+		if (ram_page == not_rampage)
+			return -1;
+	}
+
+	return ram_page;
+}
+
 /*
  * For RAM pages, mark the pages as non WB memory type using
  * PageNonWB (PG_arch_1). We allow only one set_memory_uc() or
@@ -345,20 +372,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	if (new_type)
 		*new_type = actual_type;
 
-	/*
+	is_range_ram = pat_pagerange_is_ram(start, end);
-	 * For legacy reasons, some parts of the physical address range in the
-	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
-	 * the e820 tables).  So we will track the memory attributes of this
-	 * legacy 1MB region using the linear memtype_list always.
-	 */
-	if (end >= ISA_END_ADDRESS) {
-		is_range_ram = pagerange_is_ram(start, end);
 	if (is_range_ram == 1)
 		return reserve_ram_pages_type(start, end, req_type,
 					      new_type);
 	else if (is_range_ram < 0)
 		return -EINVAL;
-	}
 
 	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
@@ -455,19 +474,11 @@ int free_memtype(u64 start, u64 end)
 	if (is_ISA_range(start, end - 1))
 		return 0;
 
-	/*
+	is_range_ram = pat_pagerange_is_ram(start, end);
-	 * For legacy reasons, some parts of the physical address range in the
-	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
-	 * the e820 tables).  So we will track the memory attributes of this
-	 * legacy 1MB region using the linear memtype_list always.
-	 */
-	if (end >= ISA_END_ADDRESS) {
-		is_range_ram = pagerange_is_ram(start, end);
 	if (is_range_ram == 1)
 		return free_ram_pages_type(start, end);
 	else if (is_range_ram < 0)
 		return -EINVAL;
-	}
 
 	spin_lock(&memtype_lock);
 	list_for_each_entry(entry, &memtype_list, nd) {
@@ -635,17 +646,13 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 	unsigned long flags;
 	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
 
-	is_ram = pagerange_is_ram(paddr, paddr + size);
+	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
 
-	if (is_ram != 0) {
 	/*
-		 * For mapping RAM pages, drivers need to call
+	 * reserve_pfn_range() doesn't support RAM pages.
-		 * set_memory_[uc|wc|wb] directly, for reserve and free, before
-		 * setting up the PTE.
 	 */
-		WARN_ON_ONCE(1);
+	if (is_ram != 0)
-		return 0;
+		return -EINVAL;
-	}
 
 	ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
 	if (ret)
@@ -702,7 +709,7 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 {
 	int is_ram;
 
-	is_ram = pagerange_is_ram(paddr, paddr + size);
+	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
 	if (is_ram == 0)
 		free_memtype(paddr, paddr + size);
 }

include/linux/mm.h

@@ -1304,5 +1304,6 @@ void vmemmap_populate_print_last(void);
 
 extern void *alloc_locked_buffer(size_t size);
 extern void free_locked_buffer(void *buffer, size_t size);
+extern void release_locked_buffer(void *buffer, size_t size);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

mm/mlock.c

@@ -660,7 +660,7 @@ void *alloc_locked_buffer(size_t size)
 	return buffer;
 }
 
-void free_locked_buffer(void *buffer, size_t size)
+void release_locked_buffer(void *buffer, size_t size)
 {
 	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
@@ -670,6 +670,11 @@ void free_locked_buffer(void *buffer, size_t size)
 	current->mm->locked_vm -= pgsz;
 
 	up_write(&current->mm->mmap_sem);
+}
+
+void free_locked_buffer(void *buffer, size_t size)
+{
+	release_locked_buffer(buffer, size);
 
 	kfree(buffer);
 }