Merge branch 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into stable/for-linus-3.7

* 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (9690 commits)
  x86: Document x86_init.paging.pagetable_init()
  x86: xen: Cleanup and remove x86_init.paging.pagetable_setup_done()
  x86: Move paging_init() call to x86_init.paging.pagetable_init()
  x86: Rename pagetable_setup_start() to pagetable_init()
  x86: Remove base argument from x86_init.paging.pagetable_setup_start
  Linux 3.6-rc5
  HID: tpkbd: work even if the new Lenovo Keyboard driver is not configured
  Remove user-triggerable BUG from mpol_to_str
  xen/pciback: Fix proper FLR steps.
  uml: fix compile error in deliver_alarm()
  dj: memory scribble in logi_dj
  Fix order of arguments to compat_put_time[spec|val]
  xen: Use correct masking in xen_swiotlb_alloc_coherent.
  xen: fix logical error in tlb flushing
  xen/p2m: Fix one-off error in checking the P2M tree directory.
  powerpc: Don't use __put_user() in patch_instruction
  powerpc: Make sure IPI handlers see data written by IPI senders
  powerpc: Restore correct DSCR in context switch
  powerpc: Fix DSCR inheritance in copy_thread()
  powerpc: Keep thread.dscr and thread.dscr_inherit in sync
  ...

5 files changed, 225 insertions, 84 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index cb1b191..2766746 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -38,6 +38,7 @@
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
 #include <xen/interface/memory.h>
+#include <xen/interface/xen-mca.h>
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/hvm.h>
@@ -109,7 +110,7 @@ EXPORT_SYMBOL_GPL(xen_have_vector_callback);
  * Point at some empty memory to start with. We map the real shared_info
  * page as soon as fixmap is up and running.
  */
-struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
+struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;
 
 /*
  * Flag to determine whether vcpu info placement is available on all
@@ -126,6 +127,19 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
  */
 static int have_vcpu_info_placement = 1;
 
+struct tls_descs {
+	struct desc_struct desc[3];
+};
+
+/*
+ * Updating the 3 TLS descriptors in the GDT on every task switch is
+ * surprisingly expensive so we avoid updating them if they haven't
+ * changed.  Since Xen writes different descriptors than the one
+ * passed in the update_descriptor hypercall we keep shadow copies to
+ * compare against.
+ */
+static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
+
 static void clamp_max_cpus(void)
 {
 #ifdef CONFIG_SMP
@@ -343,9 +357,7 @@ static void __init xen_init_cpuid_mask(void)
 	unsigned int xsave_mask;
 
 	cpuid_leaf1_edx_mask =
-		~((1 << X86_FEATURE_MCE)  |  /* disable MCE */
-		  (1 << X86_FEATURE_MCA)  |  /* disable MCA */
-		  (1 << X86_FEATURE_MTRR) |  /* disable MTRR */
+		~((1 << X86_FEATURE_MTRR) |  /* disable MTRR */
 		  (1 << X86_FEATURE_ACC));   /* thermal monitoring */
 
 	if (!xen_initial_domain())
@@ -542,12 +554,28 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
 		BUG();
 }
 
+static inline bool desc_equal(const struct desc_struct *d1,
+			      const struct desc_struct *d2)
+{
+	return d1->a == d2->a && d1->b == d2->b;
+}
+
 static void load_TLS_descriptor(struct thread_struct *t,
 				unsigned int cpu, unsigned int i)
 {
-	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
-	xmaddr_t maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
-	struct multicall_space mc = __xen_mc_entry(0);
+	struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i];
+	struct desc_struct *gdt;
+	xmaddr_t maddr;
+	struct multicall_space mc;
+
+	if (desc_equal(shadow, &t->tls_array[i]))
+		return;
+
+	*shadow = t->tls_array[i];
+
+	gdt = get_cpu_gdt_table(cpu);
+	maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]);
+	mc = __xen_mc_entry(0);
 
 	MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]);
 }
@@ -629,8 +657,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 	/*
 	 * Look for known traps using IST, and substitute them
 	 * appropriately.  The debugger ones are the only ones we care
-	 * about.  Xen will handle faults like double_fault and
-	 * machine_check, so we should never see them.  Warn if
+	 * about.  Xen will handle faults like double_fault,
+	 * so we should never see them.  Warn if
 	 * there's an unexpected IST-using fault handler.
 	 */
 	if (addr == (unsigned long)debug)
@@ -645,7 +673,11 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 		return 0;
 #ifdef CONFIG_X86_MCE
 	} else if (addr == (unsigned long)machine_check) {
-		return 0;
+		/*
+		 * when xen hypervisor inject vMCE to guest,
+		 * use native mce handler to handle it
+		 */
+		;
 #endif
 	} else {
 		/* Some other trap using IST? */
@@ -1126,9 +1158,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.wbinvd = native_wbinvd,
 
 	.read_msr = native_read_msr_safe,
-	.rdmsr_regs = native_rdmsr_safe_regs,
 	.write_msr = xen_write_msr_safe,
-	.wrmsr_regs = native_wrmsr_safe_regs,
 
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
@@ -1441,32 +1471,6 @@ asmlinkage void __init xen_start_kernel(void)
 #endif
 }
 
-static int init_hvm_pv_info(int *major, int *minor)
-{
-	uint32_t eax, ebx, ecx, edx, pages, msr, base;
-	u64 pfn;
-
-	base = xen_cpuid_base();
-	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
-
-	*major = eax >> 16;
-	*minor = eax & 0xffff;
-	printk(KERN_INFO "Xen version %d.%d.\n", *major, *minor);
-
-	cpuid(base + 2, &pages, &msr, &ecx, &edx);
-
-	pfn = __pa(hypercall_page);
-	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
-
-	xen_setup_features();
-
-	pv_info.name = "Xen HVM";
-
-	xen_domain_type = XEN_HVM_DOMAIN;
-
-	return 0;
-}
-
 void __ref xen_hvm_init_shared_info(void)
 {
 	int cpu;
@@ -1499,6 +1503,31 @@ void __ref xen_hvm_init_shared_info(void)
 }
 
 #ifdef CONFIG_XEN_PVHVM
+static void __init init_hvm_pv_info(void)
+{
+	int major, minor;
+	uint32_t eax, ebx, ecx, edx, pages, msr, base;
+	u64 pfn;
+
+	base = xen_cpuid_base();
+	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
+
+	major = eax >> 16;
+	minor = eax & 0xffff;
+	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
+
+	cpuid(base + 2, &pages, &msr, &ecx, &edx);
+
+	pfn = __pa(hypercall_page);
+	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+	xen_setup_features();
+
+	pv_info.name = "Xen HVM";
+
+	xen_domain_type = XEN_HVM_DOMAIN;
+}
+
 static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 				    unsigned long action, void *hcpu)
 {
@@ -1521,12 +1550,7 @@ static struct notifier_block xen_hvm_cpu_notifier __cpuinitdata = {
 
 static void __init xen_hvm_guest_init(void)
 {
-	int r;
-	int major, minor;
-
-	r = init_hvm_pv_info(&major, &minor);
-	if (r < 0)
-		return;
+	init_hvm_pv_info();
 
 	xen_hvm_init_shared_info();
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 2d9e7c9..dfc9004 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -308,8 +308,20 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 
 static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
 {
-	if (!xen_batched_set_pte(ptep, pteval))
-		native_set_pte(ptep, pteval);
+	if (!xen_batched_set_pte(ptep, pteval)) {
+		/*
+		 * Could call native_set_pte() here and trap and
+		 * emulate the PTE write but with 32-bit guests this
+		 * needs two traps (one for each of the two 32-bit
+		 * words in the PTE) so do one hypercall directly
+		 * instead.
+		 */
+		struct mmu_update u;
+
+		u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE;
+		u.val = pte_val_ma(pteval);
+		HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF);
+	}
 }
 
 static void xen_set_pte(pte_t *ptep, pte_t pteval)
@@ -1162,8 +1174,13 @@ static void xen_exit_mmap(struct mm_struct *mm)
 	spin_unlock(&mm->page_table_lock);
 }
 
-static void __init xen_pagetable_setup_start(pgd_t *base)
+static void xen_post_allocator_init(void);
+
+static void __init xen_pagetable_init(void)
 {
+	paging_init();
+	xen_setup_shared_info();
+	xen_post_allocator_init();
 }
 
 static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
@@ -1180,14 +1197,6 @@ static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
 	}
 }
 
-static void xen_post_allocator_init(void);
-
-static void __init xen_pagetable_setup_done(pgd_t *base)
-{
-	xen_setup_shared_info();
-	xen_post_allocator_init();
-}
-
 static void xen_write_cr2(unsigned long cr2)
 {
 	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
@@ -1244,7 +1253,8 @@ static void xen_flush_tlb_single(unsigned long addr)
 }
 
 static void xen_flush_tlb_others(const struct cpumask *cpus,
-				 struct mm_struct *mm, unsigned long va)
+				 struct mm_struct *mm, unsigned long start,
+				 unsigned long end)
 {
 	struct {
 		struct mmuext_op op;
@@ -1256,7 +1266,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	} *args;
 	struct multicall_space mcs;
 
-	trace_xen_mmu_flush_tlb_others(cpus, mm, va);
+	trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
 
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
@@ -1269,11 +1279,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
-	if (va == TLB_FLUSH_ALL) {
-		args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	} else {
+	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
-		args->op.arg1.linear_addr = va;
+		args->op.arg1.linear_addr = start;
 	}
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
@@ -1416,13 +1425,28 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
 }
 #endif /* CONFIG_X86_64 */
 
-/* Init-time set_pte while constructing initial pagetables, which
-   doesn't allow RO pagetable pages to be remapped RW */
+/*
+ * Init-time set_pte while constructing initial pagetables, which
+ * doesn't allow RO page table pages to be remapped RW.
+ *
+ * If there is no MFN for this PFN then this page is initially
+ * ballooned out so clear the PTE (as in decrease_reservation() in
+ * drivers/xen/balloon.c).
+ *
+ * Many of these PTE updates are done on unpinned and writable pages
+ * and doing a hypercall for these is unnecessary and expensive.  At
+ * this point it is not possible to tell if a page is pinned or not,
+ * so always write the PTE directly and rely on Xen trapping and
+ * emulating any updates as necessary.
+ */
 static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 {
-	pte = mask_rw_pte(ptep, pte);
+	if (pte_mfn(pte) != INVALID_P2M_ENTRY)
+		pte = mask_rw_pte(ptep, pte);
+	else
+		pte = __pte_ma(0);
 
-	xen_set_pte(ptep, pte);
+	native_set_pte(ptep, pte);
 }
 
 static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
@@ -2041,8 +2065,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 void __init xen_init_mmu_ops(void)
 {
 	x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
-	x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
-	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
+	x86_init.paging.pagetable_init = xen_pagetable_init;
 	pv_mmu_ops = xen_mmu_ops;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 64effdc6..76ba0e9 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -194,6 +194,13 @@ RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID
  * boundary violation will require three middle nodes. */
 RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
 
+/* When we populate back during bootup, the amount of pages can vary. The
+ * max we have is seen is 395979, but that does not mean it can't be more.
+ * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle
+ * it can re-use Xen provided mfn_list array, so we only need to allocate at
+ * most three P2M top nodes. */
+RESERVE_BRK(p2m_populated, PAGE_SIZE * 3);
+
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
 	BUG_ON(pfn >= MAX_P2M_PFN);
@@ -570,12 +577,99 @@ static bool __init early_alloc_p2m(unsigned long pfn)
 	}
 	return true;
 }
+
+/*
+ * Skim over the P2M tree looking at pages that are either filled with
+ * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and
+ * replace the P2M leaf with a p2m_missing or p2m_identity.
+ * Stick the old page in the new P2M tree location.
+ */
+bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn)
+{
+	unsigned topidx;
+	unsigned mididx;
+	unsigned ident_pfns;
+	unsigned inv_pfns;
+	unsigned long *p2m;
+	unsigned long *mid_mfn_p;
+	unsigned idx;
+	unsigned long pfn;
+
+	/* We only look when this entails a P2M middle layer */
+	if (p2m_index(set_pfn))
+		return false;
+
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
+		topidx = p2m_top_index(pfn);
+
+		if (!p2m_top[topidx])
+			continue;
+
+		if (p2m_top[topidx] == p2m_mid_missing)
+			continue;
+
+		mididx = p2m_mid_index(pfn);
+		p2m = p2m_top[topidx][mididx];
+		if (!p2m)
+			continue;
+
+		if ((p2m == p2m_missing) || (p2m == p2m_identity))
+			continue;
+
+		if ((unsigned long)p2m == INVALID_P2M_ENTRY)
+			continue;
+
+		ident_pfns = 0;
+		inv_pfns = 0;
+		for (idx = 0; idx < P2M_PER_PAGE; idx++) {
+			/* IDENTITY_PFNs are 1:1 */
+			if (p2m[idx] == IDENTITY_FRAME(pfn + idx))
+				ident_pfns++;
+			else if (p2m[idx] == INVALID_P2M_ENTRY)
+				inv_pfns++;
+			else
+				break;
+		}
+		if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE))
+			goto found;
+	}
+	return false;
+found:
+	/* Found one, replace old with p2m_identity or p2m_missing */
+	p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing);
+	/* And the other for save/restore.. */
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	/* NOTE: Even if it is a p2m_identity it should still be point to
+	 * a page filled with INVALID_P2M_ENTRY entries. */
+	mid_mfn_p[mididx] = virt_to_mfn(p2m_missing);
+
+	/* Reset where we want to stick the old page in. */
+	topidx = p2m_top_index(set_pfn);
+	mididx = p2m_mid_index(set_pfn);
+
+	/* This shouldn't happen */
+	if (WARN_ON(p2m_top[topidx] == p2m_mid_missing))
+		early_alloc_p2m(set_pfn);
+
+	if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing))
+		return false;
+
+	p2m_init(p2m);
+	p2m_top[topidx][mididx] = p2m;
+	mid_mfn_p = p2m_top_mfn_p[topidx];
+	mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
+	return true;
+}
 bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
 		if (!early_alloc_p2m(pfn))
 			return false;
 
+		if (early_can_reuse_p2m_middle(pfn, mfn))
+			return __set_phys_to_machine(pfn, mfn);
+
 		if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
 			return false;
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index a4790bf..d11ca11 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -78,9 +78,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 	memblock_reserve(start, size);
 
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
+	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
+		unsigned long mfn = pfn_to_mfn(pfn);
+
+		if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
+			continue;
+		WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
+			pfn, mfn);
 
-	for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++)
 		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
 }
 
 static unsigned long __init xen_do_chunk(unsigned long start,
@@ -157,25 +164,24 @@ static unsigned long __init xen_populate_chunk(
 	unsigned long dest_pfn;
 
 	for (i = 0, entry = list; i < map_size; i++, entry++) {
-		unsigned long credits = credits_left;
 		unsigned long s_pfn;
 		unsigned long e_pfn;
 		unsigned long pfns;
 		long capacity;
 
-		if (credits <= 0)
+		if (credits_left <= 0)
 			break;
 
 		if (entry->type != E820_RAM)
 			continue;
 
-		e_pfn = PFN_UP(entry->addr + entry->size);
+		e_pfn = PFN_DOWN(entry->addr + entry->size);
 
 		/* We only care about E820 after the xen_start_info->nr_pages */
 		if (e_pfn <= max_pfn)
 			continue;
 
-		s_pfn = PFN_DOWN(entry->addr);
+		s_pfn = PFN_UP(entry->addr);
 		/* If the E820 falls within the nr_pages, we want to start
 		 * at the nr_pages PFN.
 		 * If that would mean going past the E820 entry, skip it
@@ -184,23 +190,19 @@ static unsigned long __init xen_populate_chunk(
 			capacity = e_pfn - max_pfn;
 			dest_pfn = max_pfn;
 		} else {
-			/* last_pfn MUST be within E820_RAM regions */
-			if (*last_pfn && e_pfn >= *last_pfn)
-				s_pfn = *last_pfn;
 			capacity = e_pfn - s_pfn;
 			dest_pfn = s_pfn;
 		}
-		/* If we had filled this E820_RAM entry, go to the next one. */
-		if (capacity <= 0)
-			continue;
 
-		if (credits > capacity)
-			credits = capacity;
+		if (credits_left < capacity)
+			capacity = credits_left;
 
-		pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
+		pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
 		done += pfns;
-		credits_left -= pfns;
 		*last_pfn = (dest_pfn + pfns);
+		if (pfns < capacity)
+			break;
+		credits_left -= pfns;
 	}
 	return done;
 }
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index afb250d..f58dca7 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -80,9 +80,7 @@ static void __cpuinit cpu_bringup(void)
 
 	notify_cpu_starting(cpu);
 
-	ipi_call_lock();
 	set_cpu_online(cpu, true);
-	ipi_call_unlock();
 
 	this_cpu_write(cpu_state, CPU_ONLINE);