4 files changed, 76 insertions, 4 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0fb662a..9f808af 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -62,6 +62,7 @@
 #include <asm/reboot.h>
 #include <asm/stackprotector.h>
 #include <asm/hypervisor.h>
+#include <asm/pci_x86.h>
 
 #include "xen-ops.h"
 #include "mmu.h"
@@ -197,6 +198,9 @@ static void __init xen_banner(void)
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
 
+#define CPUID_THERM_POWER_LEAF 6
+#define APERFMPERF_PRESENT 0
+
 static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
 static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
 
@@ -217,6 +221,11 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		maskedx = cpuid_leaf1_edx_mask;
 		break;
 
+	case CPUID_THERM_POWER_LEAF:
+		/* Disabling APERFMPERF for kernel usage */
+		maskecx = ~(1 << APERFMPERF_PRESENT);
+		break;
+
 	case 0xb:
 		/* Suppress extended topology stuff */
 		maskebx = 0;
@@ -794,7 +803,16 @@ static void xen_write_cr4(unsigned long cr4)
 
 	native_write_cr4(cr4);
 }
-
+#ifdef CONFIG_X86_64
+static inline unsigned long xen_read_cr8(void)
+{
+	return 0;
+}
+static inline void xen_write_cr8(unsigned long val)
+{
+	BUG_ON(val);
+}
+#endif
 static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 {
 	int ret;
@@ -959,6 +977,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_cr4_safe = native_read_cr4_safe,
 	.write_cr4 = xen_write_cr4,
 
+#ifdef CONFIG_X86_64
+	.read_cr8 = xen_read_cr8,
+	.write_cr8 = xen_write_cr8,
+#endif
+
 	.wbinvd = native_wbinvd,
 
 	.read_msr = native_read_msr_safe,
@@ -966,6 +989,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
 
+	.read_tscp = native_read_tscp,
+
 	.iret = xen_iret,
 	.irq_enable_sysexit = xen_sysexit,
 #ifdef CONFIG_X86_64
@@ -1259,8 +1284,10 @@ asmlinkage void __init xen_start_kernel(void)
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
-		
-
+#ifdef CONFIG_PCI
+	/* PCI BIOS service won't work from a PV guest. */
+	pci_probe &= ~PCI_PROBE_BIOS;
+#endif
 	xen_raw_console_write("about to get started...\n");
 
 	xen_setup_runstate_info(0);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5f76c0a..d957dce 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -320,8 +320,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
 	if (val & _PAGE_PRESENT) {
 		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		unsigned long pfn = mfn_to_pfn(mfn);
+
 		pteval_t flags = val & PTE_FLAGS_MASK;
-		val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+		if (unlikely(pfn == ~0))
+			val = flags & ~_PAGE_PRESENT;
+		else
+			val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
 	}
 
 	return val;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 58efeb9..2f7847d 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -683,6 +683,7 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
+	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	if (!PageHighMem(page)) {
@@ -706,6 +707,24 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
 	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
 
+	/* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in
+	 * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other
+	 * pfn so that the following mfn_to_pfn(mfn) calls will return the
+	 * pfn from the m2p_override (the backend pfn) instead.
+	 * We need to do this because the pages shared by the frontend
+	 * (xen-blkfront) can be already locked (lock_page, called by
+	 * do_read_cache_page); when the userspace backend tries to use them
+	 * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
+	 * do_blockdev_direct_IO is going to try to lock the same pages
+	 * again resulting in a deadlock.
+	 * As a side effect get_user_pages_fast might not be safe on the
+	 * 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)
+		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(m2p_add_override);
@@ -717,6 +736,7 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 	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);
@@ -743,6 +763,22 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 		/* No tlb flush necessary because the caller already
 		 * left the pte unmapped. */
 
+	/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
+	 * somewhere in this domain, even before being added to the
+	 * m2p_override (see comment above in m2p_add_override).
+	 * If there are no other entries in the m2p_override corresponding
+	 * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for
+	 * the original pfn (the one shared by the frontend): the backend
+	 * cannot do any IO on this page anymore because it has been
+	 * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of
+	 * 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) &&
+			m2p_find_override(mfn) == NULL)
+		set_phys_to_machine(pfn, mfn);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(m2p_remove_override);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f8dcda4..5669564 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -15,6 +15,7 @@
 #include <asm/e820.h>
 #include <asm/setup.h>
 #include <asm/acpi.h>
+#include <asm/numa.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
@@ -463,4 +464,7 @@ void __init xen_arch_setup(void)
 	boot_option_idle_override = IDLE_HALT;
 
 	fiddle_vdso();
+#ifdef CONFIG_NUMA
+	numa_off = 1;
+#endif
 }