Merge tag 'stable/for-linus-3.6-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull three xen bug-fixes from Konrad Rzeszutek Wilk:
 - Revert the kexec fix which caused on non-kexec shutdowns a race.
 - Reuse existing P2M leafs - instead of requiring to allocate a large
   area of bootup virtual address estate.
 - Fix a one-off error when adding PFNs for balloon pages.

* tag 'stable/for-linus-3.6-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen/setup: Fix one-off error when adding for-balloon PFNs to the P2M.
  xen/p2m: Reuse existing P2M leafs if they are filled with 1:1 PFNs or INVALID.
  Revert "xen PVonHVM: move shared_info to MMIO before kexec"

7 files changed, 113 insertions, 130 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bf4bda6d3e9a..9642d4a38602 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -31,7 +31,6 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/syscore_ops.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -1470,130 +1469,38 @@ asmlinkage void __init xen_start_kernel(void)
 #endif
 }
 
-#ifdef CONFIG_XEN_PVHVM
-/*
- * The pfn containing the shared_info is located somewhere in RAM. This
- * will cause trouble if the current kernel is doing a kexec boot into a
- * new kernel. The new kernel (and its startup code) can not know where
- * the pfn is, so it can not reserve the page. The hypervisor will
- * continue to update the pfn, and as a result memory corruption occours
- * in the new kernel.
- *
- * One way to work around this issue is to allocate a page in the
- * xen-platform pci device's BAR memory range. But pci init is done very
- * late and the shared_info page is already in use very early to read
- * the pvclock. So moving the pfn from RAM to MMIO is racy because some
- * code paths on other vcpus could access the pfn during the small
- * window when the old pfn is moved to the new pfn. There is even a
- * small window were the old pfn is not backed by a mfn, and during that
- * time all reads return -1.
- *
- * Because it is not known upfront where the MMIO region is located it
- * can not be used right from the start in xen_hvm_init_shared_info.
- *
- * To minimise trouble the move of the pfn is done shortly before kexec.
- * This does not eliminate the race because all vcpus are still online
- * when the syscore_ops will be called. But hopefully there is no work
- * pending at this point in time. Also the syscore_op is run last which
- * reduces the risk further.
- */
-
-static struct shared_info *xen_hvm_shared_info;
-
-static void xen_hvm_connect_shared_info(unsigned long pfn)
+void __ref xen_hvm_init_shared_info(void)
 {
+        int cpu;
         struct xen_add_to_physmap xatp;
+        static struct shared_info *shared_info_page = 0;
 
+        if (!shared_info_page)
+                shared_info_page = (struct shared_info *)
+                        extend_brk(PAGE_SIZE, PAGE_SIZE);
         xatp.domid = DOMID_SELF;
         xatp.idx = 0;
         xatp.space = XENMAPSPACE_shared_info;
-        xatp.gpfn = pfn;
+        xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
         if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
                 BUG();
 
-}
-static void xen_hvm_set_shared_info(struct shared_info *sip)
-{
-        int cpu;
-
-        HYPERVISOR_shared_info = sip;
+        HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
 
         /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
          * page, we use it in the event channel upcall and in some pvclock
          * related functions. We don't need the vcpu_info placement
          * optimizations because we don't use any pv_mmu or pv_irq op on
          * HVM.
-         * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is
-         * online but xen_hvm_set_shared_info is run at resume time too and
+         * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
+         * online but xen_hvm_init_shared_info is run at resume time too and
          * in that case multiple vcpus might be online. */
         for_each_online_cpu(cpu) {
                 per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
         }
 }
 
-/* Reconnect the shared_info pfn to a mfn */
-void xen_hvm_resume_shared_info(void)
-{
-        xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT);
-}
-
-#ifdef CONFIG_KEXEC
-static struct shared_info *xen_hvm_shared_info_kexec;
-static unsigned long xen_hvm_shared_info_pfn_kexec;
-
-/* Remember a pfn in MMIO space for kexec reboot */
-void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn)
-{
-        xen_hvm_shared_info_kexec = sip;
-        xen_hvm_shared_info_pfn_kexec = pfn;
-}
-
-static void xen_hvm_syscore_shutdown(void)
-{
-        struct xen_memory_reservation reservation = {
-                .domid = DOMID_SELF,
-                .nr_extents = 1,
-        };
-        unsigned long prev_pfn;
-        int rc;
-
-        if (!xen_hvm_shared_info_kexec)
-                return;
-
-        prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT;
-        set_xen_guest_handle(reservation.extent_start, &prev_pfn);
-
-        /* Move pfn to MMIO, disconnects previous pfn from mfn */
-        xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec);
-
-        /* Update pointers, following hypercall is also a memory barrier */
-        xen_hvm_set_shared_info(xen_hvm_shared_info_kexec);
-
-        /* Allocate new mfn for previous pfn */
-        do {
-                rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
-                if (rc == 0)
-                        msleep(123);
-        } while (rc == 0);
-
-        /* Make sure the previous pfn is really connected to a (new) mfn */
-        BUG_ON(rc != 1);
-}
-
-static struct syscore_ops xen_hvm_syscore_ops = {
-        .shutdown = xen_hvm_syscore_shutdown,
-};
-#endif
-
-/* Use a pfn in RAM, may move to MMIO before kexec. */
-static void __init xen_hvm_init_shared_info(void)
-{
-        /* Remember pointer for resume */
-        xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE);
-        xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT);
-        xen_hvm_set_shared_info(xen_hvm_shared_info);
-}
-
+#ifdef CONFIG_XEN_PVHVM
 static void __init init_hvm_pv_info(void)
 {
         int major, minor;
@@ -1644,9 +1551,6 @@ static void __init xen_hvm_guest_init(void)
         init_hvm_pv_info();
 
         xen_hvm_init_shared_info();
-#ifdef CONFIG_KEXEC
-        register_syscore_ops(&xen_hvm_syscore_ops);
-#endif
 
         if (xen_feature(XENFEAT_hvm_callback_vector))
                 xen_have_vector_callback = 1;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b2e91d40a4cb..d4b255463253 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -196,9 +196,11 @@ 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.
- * But some machines can have 3GB I/O holes even. So lets reserve enough
- * for 4GB of I/O and E820 holes. */
-RESERVE_BRK(p2m_populated, PMD_SIZE * 4);
+ * 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);
@@ -575,12 +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 ead85576d54a..d11ca11d14fc 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,
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index ae8a00c39de4..45329c8c226e 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled)
 {
 #ifdef CONFIG_XEN_PVHVM
         int cpu;
-        xen_hvm_resume_shared_info();
+        xen_hvm_init_shared_info();
         xen_callback_vector();
         xen_unplug_emulated_devices();
         if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 1e4329e04e0f..202d4c150154 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -41,7 +41,7 @@ void xen_enable_syscall(void);
 void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
-void xen_hvm_resume_shared_info(void);
+void xen_hvm_init_shared_info(void);
 void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
index d4c50d63acbc..97ca359ae2bd 100644
--- a/drivers/xen/platform-pci.c
+++ b/drivers/xen/platform-pci.c
@@ -101,19 +101,6 @@ static int platform_pci_resume(struct pci_dev *pdev)
         return 0;
 }
 
-static void __devinit prepare_shared_info(void)
-{
-#ifdef CONFIG_KEXEC
-        unsigned long addr;
-        struct shared_info *hvm_shared_info;
-
-        addr = alloc_xen_mmio(PAGE_SIZE);
-        hvm_shared_info = ioremap(addr, PAGE_SIZE);
-        memset(hvm_shared_info, 0, PAGE_SIZE);
-        xen_hvm_prepare_kexec(hvm_shared_info, addr >> PAGE_SHIFT);
-#endif
-}
-
 static int __devinit platform_pci_init(struct pci_dev *pdev,
                                        const struct pci_device_id *ent)
 {
@@ -151,8 +138,6 @@ static int __devinit platform_pci_init(struct pci_dev *pdev,
         platform_mmio = mmio_addr;
         platform_mmiolen = mmio_len;
 
-        prepare_shared_info();
-
         if (!xen_have_vector_callback) {
                 ret = xen_allocate_irq(pdev);
                 if (ret) {
diff --git a/include/xen/events.h b/include/xen/events.h
index 9c641deb65d2..04399b28e821 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -58,8 +58,6 @@ void notify_remote_via_irq(int irq);
 
 void xen_irq_resume(void);
 
-void xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn);
-
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq);
 void xen_set_irq_pending(int irq);