Merge tag 'stable/for-linus-3.12-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull Xen fixes from Konrad Rzeszutek Wilk:
 "Bug-fixes and one update to the kernel-paramters.txt documentation.

   - Fix PV spinlocks triggering jump_label code bug
   - Remove extraneous code in the tpm front driver
   - Fix ballooning out of pages when non-preemptible
   - Fix deadlock when using a 32-bit initial domain with large amount
     of memory
   - Add xen_nopvpsin parameter to the documentation"

* tag 'stable/for-linus-3.12-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/spinlock: Document the xen_nopvspin parameter.
  xen/p2m: check MFN is in range before using the m2p table
  xen/balloon: don't alloc page while non-preemptible
  xen: Do not enable spinlocks before jump_label_init() has executed
  tpm: xen-tpmfront: Remove the locality sysfs attribute
  tpm: xen-tpmfront: Fix default durations

6 files changed, 63 insertions, 67 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1a036cd972fb..539a23631990 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3485,6 +3485,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                                 the unplug protocol
                         never -- do not unplug even if version check succeeds
 
+        xen_nopvspin    [X86,XEN]
+                        Disables the ticketlock slowpath using Xen PV
+                        optimizations.
+
         xirc2ps_cs=     [NET,PCMCIA]
                         Format:
                         <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b7..b913915e8e63 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
         return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 {
         unsigned long pfn;
-        int ret = 0;
+        int ret;
 
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return mfn;
 
-        if (unlikely(mfn >= machine_to_phys_nr)) {
-                pfn = ~0;
-                goto try_override;
-        }
-        pfn = 0;
+        if (unlikely(mfn >= machine_to_phys_nr))
+                return ~0;
+
         /*
          * The array access can fail (e.g., device space beyond end of RAM).
          * In such cases it doesn't matter what we return (we return garbage),
          * but we must handle the fault without crashing!
          */
         ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
-        /* ret might be < 0 if there are no entries in the m2p for mfn */
         if (ret < 0)
-                pfn = ~0;
-        else if (get_phys_to_machine(pfn) != mfn)
+                return ~0;
+
+        return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+        unsigned long pfn;
+
+        if (xen_feature(XENFEAT_auto_translated_physmap))
+                return mfn;
+
+        pfn = mfn_to_pfn_no_overrides(mfn);
+        if (get_phys_to_machine(pfn) != mfn) {
                 /*
                  * If this appears to be a foreign mfn (because the pfn
                  * doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
                  * m2p_find_override_pfn returns ~0 if it doesn't find anything.
                  */
                 pfn = m2p_find_override_pfn(mfn, ~0);
+        }
 
         /* 
          * pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8b901e8d782d..a61c7d5811be 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -879,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
         unsigned long uninitialized_var(address);
         unsigned level;
         pte_t *ptep = NULL;
-        int ret = 0;
 
         pfn = page_to_pfn(page);
         if (!PageHighMem(page)) {
@@ -926,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
          * frontend pages while they are being shared with the backend,
          * because mfn_to_pfn (that ends up being called by GUPF) will
          * return the backend pfn rather than the frontend pfn. */
-        ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-        if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+        pfn = mfn_to_pfn_no_overrides(mfn);
+        if (get_phys_to_machine(pfn) == mfn)
                 set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
 
         return 0;
@@ -942,7 +941,6 @@ int m2p_remove_override(struct page *page,
         unsigned long uninitialized_var(address);
         unsigned level;
         pte_t *ptep = NULL;
-        int ret = 0;
 
         pfn = page_to_pfn(page);
         mfn = get_phys_to_machine(pfn);
@@ -1029,8 +1027,8 @@ int m2p_remove_override(struct page *page,
          * the original pfn causes mfn_to_pfn(mfn) to return the frontend
          * pfn again. */
         mfn &= ~FOREIGN_FRAME_BIT;
-        ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-        if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+        pfn = mfn_to_pfn_no_overrides(mfn);
+        if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
                         m2p_find_override(mfn) == NULL)
                 set_phys_to_machine(pfn, mfn);
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 253f63fceea1..be6b86078957 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -259,6 +259,14 @@ void xen_uninit_lock_cpu(int cpu)
 }
 
 
+/*
+ * Our init of PV spinlocks is split in two init functions due to us
+ * using paravirt patching and jump labels patching and having to do
+ * all of this before SMP code is invoked.
+ *
+ * The paravirt patching needs to be done _before_ the alternative asm code
+ * is started, otherwise we would not patch the core kernel code.
+ */
 void __init xen_init_spinlocks(void)
 {
 
@@ -267,12 +275,26 @@ void __init xen_init_spinlocks(void)
                 return;
         }
 
-        static_key_slow_inc(&paravirt_ticketlocks_enabled);
-
         pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
         pv_lock_ops.unlock_kick = xen_unlock_kick;
 }
 
+/*
+ * While the jump_label init code needs to happend _after_ the jump labels are
+ * enabled and before SMP is started. Hence we use pre-SMP initcall level
+ * init. We cannot do it in xen_init_spinlocks as that is done before
+ * jump labels are activated.
+ */
+static __init int xen_init_spinlocks_jump(void)
+{
+        if (!xen_pvspin)
+                return 0;
+
+        static_key_slow_inc(&paravirt_ticketlocks_enabled);
+        return 0;
+}
+early_initcall(xen_init_spinlocks_jump);
+
 static __init int xen_parse_nopvspin(char *arg)
 {
         xen_pvspin = false;
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 7a7929ba2658..06189e55b4e5 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -142,32 +142,6 @@ static int vtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count)
         return length;
 }
 
-ssize_t tpm_show_locality(struct device *dev, struct device_attribute *attr,
-                          char *buf)
-{
-        struct tpm_chip *chip = dev_get_drvdata(dev);
-        struct tpm_private *priv = TPM_VPRIV(chip);
-        u8 locality = priv->shr->locality;
-
-        return sprintf(buf, "%d\n", locality);
-}
-
-ssize_t tpm_store_locality(struct device *dev, struct device_attribute *attr,
-                        const char *buf, size_t len)
-{
-        struct tpm_chip *chip = dev_get_drvdata(dev);
-        struct tpm_private *priv = TPM_VPRIV(chip);
-        u8 val;
-
-        int rv = kstrtou8(buf, 0, &val);
-        if (rv)
-                return rv;
-
-        priv->shr->locality = val;
-
-        return len;
-}
-
 static const struct file_operations vtpm_ops = {
         .owner = THIS_MODULE,
         .llseek = no_llseek,
@@ -188,8 +162,6 @@ static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL);
 static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
 static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL);
 static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
-static DEVICE_ATTR(locality, S_IRUGO | S_IWUSR, tpm_show_locality,
-                tpm_store_locality);
 
 static struct attribute *vtpm_attrs[] = {
         &dev_attr_pubek.attr,
@@ -202,7 +174,6 @@ static struct attribute *vtpm_attrs[] = {
         &dev_attr_cancel.attr,
         &dev_attr_durations.attr,
         &dev_attr_timeouts.attr,
-        &dev_attr_locality.attr,
         NULL,
 };
 
@@ -210,8 +181,6 @@ static struct attribute_group vtpm_attr_grp = {
         .attrs = vtpm_attrs,
 };
 
-#define TPM_LONG_TIMEOUT   (10 * 60 * HZ)
-
 static const struct tpm_vendor_specific tpm_vtpm = {
         .status = vtpm_status,
         .recv = vtpm_recv,
@@ -224,11 +193,6 @@ static const struct tpm_vendor_specific tpm_vtpm = {
         .miscdev = {
                 .fops = &vtpm_ops,
         },
-        .duration = {
-                TPM_LONG_TIMEOUT,
-                TPM_LONG_TIMEOUT,
-                TPM_LONG_TIMEOUT,
-        },
 };
 
 static irqreturn_t tpmif_interrupt(int dummy, void *dev_id)
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index a50c6e3a7cc4..b232908a6192 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -398,8 +398,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
         if (nr_pages > ARRAY_SIZE(frame_list))
                 nr_pages = ARRAY_SIZE(frame_list);
 
-        scratch_page = get_balloon_scratch_page();
-
         for (i = 0; i < nr_pages; i++) {
                 page = alloc_page(gfp);
                 if (page == NULL) {
@@ -413,6 +411,12 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
                 scrub_page(page);
 
+                /*
+                 * Ballooned out frames are effectively replaced with
+                 * a scratch frame.  Ensure direct mappings and the
+                 * p2m are consistent.
+                 */
+                scratch_page = get_balloon_scratch_page();
 #ifdef CONFIG_XEN_HAVE_PVMMU
                 if (xen_pv_domain() && !PageHighMem(page)) {
                         ret = HYPERVISOR_update_va_mapping(
@@ -422,24 +426,19 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
                         BUG_ON(ret);
                 }
 #endif
-        }
-
-        /* Ensure that ballooned highmem pages don't have kmaps. */
-        kmap_flush_unused();
-        flush_tlb_all();
-
-        /* No more mappings: invalidate P2M and add to balloon. */
-        for (i = 0; i < nr_pages; i++) {
-                pfn = mfn_to_pfn(frame_list[i]);
                 if (!xen_feature(XENFEAT_auto_translated_physmap)) {
                         unsigned long p;
                         p = page_to_pfn(scratch_page);
                         __set_phys_to_machine(pfn, pfn_to_mfn(p));
                 }
+                put_balloon_scratch_page();
+
                 balloon_append(pfn_to_page(pfn));
         }
 
-        put_balloon_scratch_page();
+        /* Ensure that ballooned highmem pages don't have kmaps. */
+        kmap_flush_unused();
+        flush_tlb_all();
 
         set_xen_guest_handle(reservation.extent_start, frame_list);
         reservation.nr_extents   = nr_pages;