From cc272163ea554a97dac180fa8dd6cd54c2810bd1 Mon Sep 17 00:00:00 2001
From: Mohit Gambhir <mohit.gambhir@oracle.com>
Date: Thu, 26 Jan 2017 13:12:27 -0500
Subject: x86/xen: Fix APIC id mismatch warning on Intel

This patch fixes the following warning message seen when booting the
kernel as Dom0 with Xen on Intel machines.

[0.003000] [Firmware Bug]: CPU1: APIC id mismatch. Firmware: 0 APIC: 1]

The code generating the warning in validate_apic_and_package_id() matches
cpu_data(cpu).apicid (initialized in init_intel()->
detect_extended_topology() using cpuid) against the apicid returned from
xen_apic_read(). Now, xen_apic_read() makes a hypercall to retrieve apicid
for the boot  cpu but returns 0 otherwise. Hence the warning gets thrown
for all but the boot cpu.

The idea behind xen_apic_read() returning 0 for apicid is that the
guests (even Dom0) should not need to know what physical processor their
vcpus are running on. This is because we currently  do not have topology
information in Xen and also because xen allows more vcpus than physical
processors. However, boot cpu's apicid is required for loading
xen-acpi-processor driver on AMD machines. Look at following patch for
details:

commit 558daa289a40 ("xen/apic: Return the APIC ID (and version) for CPU
0.")

So to get rid of the warning, this patch modifies
xen_cpu_present_to_apicid() to return cpu_data(cpu).apicid instead of
calling xen_apic_read().

The warning is not seen on AMD machines because init_amd() populates
cpu_data(cpu).apicid by calling hard_smp_processor_id()->xen_apic_read()
as opposed to using apicid from cpuid as is done on Intel machines.

Signed-off-by: Mohit Gambhir <mohit.gambhir@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/xen/apic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch')

diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 44c88ad1841a..bcea81f36fc5 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -145,7 +145,7 @@ static void xen_silent_inquire(int apicid)
 static int xen_cpu_present_to_apicid(int cpu)
 {
 	if (cpu_present(cpu))
-		return xen_get_apic_id(xen_apic_read(APIC_ID));
+		return cpu_data(cpu).apicid;
 	else
 		return BAD_APICID;
 }
-- 
cgit v1.2.3


From 5a7670ee23f2c07a639c263b70140eaf1da9f68f Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Fri, 3 Feb 2017 16:57:22 -0500
Subject: x86/boot/32: Convert the 32-bit pgtable setup code from assembly to C

The new Xen PVH entry point requires page tables to be setup by the
kernel since it is entered with paging disabled.

Pull the common code out of head_32.S so that mk_early_pgtbl_32() can be
invoked from both the new Xen entry point and the existing startup_32()
code.

Convert resulting common code to C.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: matt@codeblueprint.co.uk
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1481215471-9639-1-git-send-email-boris.ostrovsky@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/pgtable_32.h |  32 ++++++++++
 arch/x86/kernel/head32.c          |  62 +++++++++++++++++++
 arch/x86/kernel/head_32.S         | 121 +++-----------------------------------
 3 files changed, 101 insertions(+), 114 deletions(-)

(limited to 'arch')

diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index b6c0b404898a..fbc73360aea0 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -27,6 +27,7 @@ struct vm_area_struct;
 
 extern pgd_t swapper_pg_dir[1024];
 extern pgd_t initial_page_table[1024];
+extern pmd_t initial_pg_pmd[];
 
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
@@ -75,4 +76,35 @@ do {						\
 #define kern_addr_valid(kaddr)	(0)
 #endif
 
+/*
+ * This is how much memory in addition to the memory covered up to
+ * and including _end we need mapped initially.
+ * We need:
+ *     (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE)
+ *     (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE)
+ *
+ * Modulo rounding, each megabyte assigned here requires a kilobyte of
+ * memory, which is currently unreclaimed.
+ *
+ * This should be a multiple of a page.
+ *
+ * KERNEL_IMAGE_SIZE should be greater than pa(_end)
+ * and small than max_low_pfn, otherwise will waste some page table entries
+ */
+#if PTRS_PER_PMD > 1
+#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
+#else
+#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
+#endif
+
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT))
+
 #endif /* _ASM_X86_PGTABLE_32_H */
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index f16c55bfc090..e5fb436a6548 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -49,3 +49,65 @@ asmlinkage __visible void __init i386_start_kernel(void)
 
 	start_kernel();
 }
+
+/*
+ * Initialize page tables.  This creates a PDE and a set of page
+ * tables, which are located immediately beyond __brk_base.  The variable
+ * _brk_end is set up to point to the first "safe" location.
+ * Mappings are created both at virtual address 0 (identity mapping)
+ * and PAGE_OFFSET for up to _end.
+ *
+ * In PAE mode initial_page_table is statically defined to contain
+ * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
+ * entries). The identity mapping is handled by pointing two PGD entries
+ * to the first kernel PMD. Note the upper half of each PMD or PTE are
+ * always zero at this stage.
+ */
+void __init mk_early_pgtbl_32(void)
+{
+#ifdef __pa
+#undef __pa
+#endif
+#define __pa(x)  ((unsigned long)(x) - PAGE_OFFSET)
+	pte_t pte, *ptep;
+	int i;
+	unsigned long *ptr;
+	/* Enough space to fit pagetables for the low memory linear map */
+	const unsigned long limit = __pa(_end) +
+		(PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT);
+#ifdef CONFIG_X86_PAE
+	pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd);
+#define SET_PL2(pl2, val)    { (pl2).pmd = (val); }
+#else
+	pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table);
+#define SET_PL2(pl2, val)   { (pl2).pgd = (val); }
+#endif
+
+	ptep = (pte_t *)__pa(__brk_base);
+	pte.pte = PTE_IDENT_ATTR;
+
+	while ((pte.pte & PTE_PFN_MASK) < limit) {
+
+		SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR);
+		*pl2p = pl2;
+#ifndef CONFIG_X86_PAE
+		/* Kernel PDE entry */
+		*(pl2p +  ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2;
+#endif
+		for (i = 0; i < PTRS_PER_PTE; i++) {
+			*ptep = pte;
+			pte.pte += PAGE_SIZE;
+			ptep++;
+		}
+
+		pl2p++;
+	}
+
+	ptr = (unsigned long *)__pa(&max_pfn_mapped);
+	/* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */
+	*ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+
+	ptr = (unsigned long *)__pa(&_brk_end);
+	*ptr = (unsigned long)ptep + PAGE_OFFSET;
+}
+
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 4e8577d03372..1f85ee8f9439 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -24,6 +24,7 @@
 #include <asm/nops.h>
 #include <asm/bootparam.h>
 #include <asm/export.h>
+#include <asm/pgtable_32.h>
 
 /* Physical address */
 #define pa(X) ((X) - __PAGE_OFFSET)
@@ -41,43 +42,9 @@
 #define X86_CAPABILITY	new_cpu_data+CPUINFO_x86_capability
 #define X86_VENDOR_ID	new_cpu_data+CPUINFO_x86_vendor_id
 
-/*
- * This is how much memory in addition to the memory covered up to
- * and including _end we need mapped initially.
- * We need:
- *     (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE)
- *     (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE)
- *
- * Modulo rounding, each megabyte assigned here requires a kilobyte of
- * memory, which is currently unreclaimed.
- *
- * This should be a multiple of a page.
- *
- * KERNEL_IMAGE_SIZE should be greater than pa(_end)
- * and small than max_low_pfn, otherwise will waste some page table entries
- */
-
-#if PTRS_PER_PMD > 1
-#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
-#else
-#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
-#endif
 
 #define SIZEOF_PTREGS 17*4
 
-/*
- * Number of possible pages in the lowmem region.
- *
- * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
- * gas warning about overflowing shift count when gas has been compiled
- * with only a host target support using a 32-bit type for internal
- * representation.
- */
-LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
-
-/* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
-
 /*
  * Worst-case size of the kernel mapping we need to make:
  * a relocatable kernel can live anywhere in lowmem, so we need to be able
@@ -160,90 +127,15 @@ ENTRY(startup_32)
 	call load_ucode_bsp
 #endif
 
-/*
- * Initialize page tables.  This creates a PDE and a set of page
- * tables, which are located immediately beyond __brk_base.  The variable
- * _brk_end is set up to point to the first "safe" location.
- * Mappings are created both at virtual address 0 (identity mapping)
- * and PAGE_OFFSET for up to _end.
- */
-#ifdef CONFIG_X86_PAE
-
-	/*
-	 * In PAE mode initial_page_table is statically defined to contain
-	 * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
-	 * entries). The identity mapping is handled by pointing two PGD entries
-	 * to the first kernel PMD.
-	 *
-	 * Note the upper half of each PMD or PTE are always zero at this stage.
-	 */
-
-#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
-
-	xorl %ebx,%ebx				/* %ebx is kept at zero */
-
-	movl $pa(__brk_base), %edi
-	movl $pa(initial_pg_pmd), %edx
-	movl $PTE_IDENT_ATTR, %eax
-10:
-	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PMD entry */
-	movl %ecx,(%edx)			/* Store PMD entry */
-						/* Upper half already zero */
-	addl $8,%edx
-	movl $512,%ecx
-11:
-	stosl
-	xchgl %eax,%ebx
-	stosl
-	xchgl %eax,%ebx
-	addl $0x1000,%eax
-	loop 11b
-
-	/*
-	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
-	 */
-	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-	cmpl %ebp,%eax
-	jb 10b
-1:
-	addl $__PAGE_OFFSET, %edi
-	movl %edi, pa(_brk_end)
-	shrl $12, %eax
-	movl %eax, pa(max_pfn_mapped)
+	/* Create early pagetables. */
+	call  mk_early_pgtbl_32
 
 	/* Do early initialization of the fixmap area */
 	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+#ifdef  CONFIG_X86_PAE
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
 	movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
-#else	/* Not PAE */
-
-page_pde_offset = (__PAGE_OFFSET >> 20);
-
-	movl $pa(__brk_base), %edi
-	movl $pa(initial_page_table), %edx
-	movl $PTE_IDENT_ATTR, %eax
-10:
-	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PDE entry */
-	movl %ecx,(%edx)			/* Store identity PDE entry */
-	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */
-	addl $4,%edx
-	movl $1024, %ecx
-11:
-	stosl
-	addl $0x1000,%eax
-	loop 11b
-	/*
-	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
-	 */
-	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-	cmpl %ebp,%eax
-	jb 10b
-	addl $__PAGE_OFFSET, %edi
-	movl %edi, pa(_brk_end)
-	shrl $12, %eax
-	movl %eax, pa(max_pfn_mapped)
-
-	/* Do early initialization of the fixmap area */
-	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+#else
 	movl %eax,pa(initial_page_table+0xffc)
 #endif
 
@@ -666,6 +558,7 @@ ENTRY(setup_once_ref)
 __PAGE_ALIGNED_BSS
 	.align PAGE_SIZE
 #ifdef CONFIG_X86_PAE
+.globl initial_pg_pmd
 initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
-- 
cgit v1.2.3


From 063334f30543597430f172bd7690d21e3590e148 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Fri, 3 Feb 2017 16:57:22 -0500
Subject: xen/x86: Remove PVH support

We are replacing existing PVH guests with new implementation.

We are keeping xen_pvh_domain() macro (for now set to zero) because
when we introduce new PVH implementation later in this series we will
reuse current PVH-specific code (xen_pvh_gnttab_setup()), and that
code is conditioned by 'if (xen_pvh_domain())'. (We will also need
a noop xen_pvh_domain() for !CONFIG_XEN_PVH).

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/xen/enlighten.c         | 140 ++++++---------------------------------
 arch/x86/xen/mmu.c               |  21 +-----
 arch/x86/xen/setup.c             |  37 +----------
 arch/x86/xen/smp.c               |  78 ++++++++--------------
 arch/x86/xen/smp.h               |   8 ---
 arch/x86/xen/xen-head.S          |  62 ++---------------
 arch/x86/xen/xen-ops.h           |   1 -
 drivers/xen/events/events_base.c |   1 -
 include/xen/xen.h                |  13 +---
 9 files changed, 54 insertions(+), 307 deletions(-)

(limited to 'arch')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 51ef95232725..828f1b226f56 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1138,10 +1138,11 @@ void xen_setup_vcpu_info_placement(void)
 		xen_vcpu_setup(cpu);
 	}
 
-	/* xen_vcpu_setup managed to place the vcpu_info within the
-	 * percpu area for all cpus, so make use of it. Note that for
-	 * PVH we want to use native IRQ mechanism. */
-	if (have_vcpu_info_placement && !xen_pvh_domain()) {
+	/*
+	 * xen_vcpu_setup managed to place the vcpu_info within the
+	 * percpu area for all cpus, so make use of it.
+	 */
+	if (have_vcpu_info_placement) {
 		pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
 		pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
 		pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
@@ -1413,49 +1414,9 @@ static void __init xen_boot_params_init_edd(void)
  * Set up the GDT and segment registers for -fstack-protector.  Until
  * we do this, we have to be careful not to call any stack-protected
  * function, which is most of the kernel.
- *
- * Note, that it is __ref because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
  */
-static void __ref xen_setup_gdt(int cpu)
+static void xen_setup_gdt(int cpu)
 {
-	if (xen_feature(XENFEAT_auto_translated_physmap)) {
-#ifdef CONFIG_X86_64
-		unsigned long dummy;
-
-		load_percpu_segment(cpu); /* We need to access per-cpu area */
-		switch_to_new_gdt(cpu); /* GDT and GS set */
-
-		/* We are switching of the Xen provided GDT to our HVM mode
-		 * GDT. The new GDT has  __KERNEL_CS with CS.L = 1
-		 * and we are jumping to reload it.
-		 */
-		asm volatile ("pushq %0\n"
-			      "leaq 1f(%%rip),%0\n"
-			      "pushq %0\n"
-			      "lretq\n"
-			      "1:\n"
-			      : "=&r" (dummy) : "0" (__KERNEL_CS));
-
-		/*
-		 * While not needed, we also set the %es, %ds, and %fs
-		 * to zero. We don't care about %ss as it is NULL.
-		 * Strictly speaking this is not needed as Xen zeros those
-		 * out (and also MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE)
-		 *
-		 * Linux zeros them in cpu_init() and in secondary_startup_64
-		 * (for BSP).
-		 */
-		loadsegment(es, 0);
-		loadsegment(ds, 0);
-		loadsegment(fs, 0);
-#else
-		/* PVH: TODO Implement. */
-		BUG();
-#endif
-		return; /* PVH does not need any PV GDT ops. */
-	}
 	pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot;
 	pv_cpu_ops.load_gdt = xen_load_gdt_boot;
 
@@ -1466,59 +1427,6 @@ static void __ref xen_setup_gdt(int cpu)
 	pv_cpu_ops.load_gdt = xen_load_gdt;
 }
 
-#ifdef CONFIG_XEN_PVH
-/*
- * A PV guest starts with default flags that are not set for PVH, set them
- * here asap.
- */
-static void xen_pvh_set_cr_flags(int cpu)
-{
-
-	/* Some of these are setup in 'secondary_startup_64'. The others:
-	 * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests
-	 * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */
-	write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM);
-
-	if (!cpu)
-		return;
-	/*
-	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
-	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
-	*/
-	if (boot_cpu_has(X86_FEATURE_PSE))
-		cr4_set_bits_and_update_boot(X86_CR4_PSE);
-
-	if (boot_cpu_has(X86_FEATURE_PGE))
-		cr4_set_bits_and_update_boot(X86_CR4_PGE);
-}
-
-/*
- * Note, that it is ref - because the only caller of this after init
- * is PVH which is not going to use xen_load_gdt_boot or other
- * __init functions.
- */
-void __ref xen_pvh_secondary_vcpu_init(int cpu)
-{
-	xen_setup_gdt(cpu);
-	xen_pvh_set_cr_flags(cpu);
-}
-
-static void __init xen_pvh_early_guest_init(void)
-{
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
-	BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector));
-
-	xen_pvh_early_cpu_init(0, false);
-	xen_pvh_set_cr_flags(0);
-
-#ifdef CONFIG_X86_32
-	BUG(); /* PVH: Implement proper support. */
-#endif
-}
-#endif    /* CONFIG_XEN_PVH */
-
 static void __init xen_dom0_set_legacy_features(void)
 {
 	x86_platform.legacy.rtc = 1;
@@ -1555,24 +1463,17 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_domain_type = XEN_PV_DOMAIN;
 
 	xen_setup_features();
-#ifdef CONFIG_XEN_PVH
-	xen_pvh_early_guest_init();
-#endif
+
 	xen_setup_machphys_mapping();
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
-	if (!xen_pvh_domain()) {
-		pv_cpu_ops = xen_cpu_ops;
+	pv_cpu_ops = xen_cpu_ops;
 
-		x86_platform.get_nmi_reason = xen_get_nmi_reason;
-	}
+	x86_platform.get_nmi_reason = xen_get_nmi_reason;
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
-	else
-		x86_init.resources.memory_setup = xen_memory_setup;
+	x86_init.resources.memory_setup = xen_memory_setup;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
@@ -1665,18 +1566,15 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/* set the limit of our address space */
 	xen_reserve_top();
 
-	/* PVH: runs at default kernel iopl of 0 */
-	if (!xen_pvh_domain()) {
-		/*
-		 * We used to do this in xen_arch_setup, but that is too late
-		 * on AMD were early_cpu_init (run before ->arch_setup()) calls
-		 * early_amd_init which pokes 0xcf8 port.
-		 */
-		set_iopl.iopl = 1;
-		rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-		if (rc != 0)
-			xen_raw_printk("physdev_op failed %d\n", rc);
-	}
+	/*
+	 * We used to do this in xen_arch_setup, but that is too late
+	 * on AMD were early_cpu_init (run before ->arch_setup()) calls
+	 * early_amd_init which pokes 0xcf8 port.
+	 */
+	set_iopl.iopl = 1;
+	rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+	if (rc != 0)
+		xen_raw_printk("physdev_op failed %d\n", rc);
 
 #ifdef CONFIG_X86_32
 	/* set up basic CPUID stuff */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 7d5afdb417cc..f6740b5b1738 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1792,10 +1792,6 @@ static void __init set_page_prot_flags(void *addr, pgprot_t prot,
 	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
 	pte_t pte = pfn_pte(pfn, prot);
 
-	/* For PVH no need to set R/O or R/W to pin them or unpin them. */
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
 		BUG();
 }
@@ -1902,8 +1898,7 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
  * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
  * kernel has a physical mapping to start with - but that's enough to
  * get __va working.  We need to fill in the rest of the physical
- * mapping once some sort of allocator has been set up.  NOTE: for
- * PVH, the page tables are native.
+ * mapping once some sort of allocator has been set up.
  */
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
@@ -2812,16 +2807,6 @@ static int do_remap_gfn(struct vm_area_struct *vma,
 
 	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
 
-	if (xen_feature(XENFEAT_auto_translated_physmap)) {
-#ifdef CONFIG_XEN_PVH
-		/* We need to update the local page tables and the xen HAP */
-		return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr,
-						 prot, domid, pages);
-#else
-		return -EINVAL;
-#endif
-        }
-
 	rmd.mfn = gfn;
 	rmd.prot = prot;
 	/* We use the err_ptr to indicate if there we are doing a contiguous
@@ -2915,10 +2900,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
 	if (!pages || !xen_feature(XENFEAT_auto_translated_physmap))
 		return 0;
 
-#ifdef CONFIG_XEN_PVH
-	return xen_xlate_unmap_gfn_range(vma, numpgs, pages);
-#else
 	return -EINVAL;
-#endif
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index f3f7b41116f7..a8c306cf8868 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -914,39 +914,6 @@ char * __init xen_memory_setup(void)
 	return "Xen";
 }
 
-/*
- * Machine specific memory setup for auto-translated guests.
- */
-char * __init xen_auto_xlated_memory_setup(void)
-{
-	struct xen_memory_map memmap;
-	int i;
-	int rc;
-
-	memmap.nr_entries = ARRAY_SIZE(xen_e820_map);
-	set_xen_guest_handle(memmap.buffer, xen_e820_map);
-
-	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
-	if (rc < 0)
-		panic("No memory map (%d)\n", rc);
-
-	xen_e820_map_entries = memmap.nr_entries;
-
-	sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
-			  &xen_e820_map_entries);
-
-	for (i = 0; i < xen_e820_map_entries; i++)
-		e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size,
-				xen_e820_map[i].type);
-
-	/* Remove p2m info, it is not needed. */
-	xen_start_info->mfn_list = 0;
-	xen_start_info->first_p2m_pfn = 0;
-	xen_start_info->nr_p2m_frames = 0;
-
-	return "Xen";
-}
-
 /*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
@@ -1032,8 +999,8 @@ void __init xen_pvmmu_arch_setup(void)
 void __init xen_arch_setup(void)
 {
 	xen_panic_handler_init();
-	if (!xen_feature(XENFEAT_auto_translated_physmap))
-		xen_pvmmu_arch_setup();
+
+	xen_pvmmu_arch_setup();
 
 #ifdef CONFIG_ACPI
 	if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 311acad7dad2..0dee6f59ea82 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -99,18 +99,8 @@ static void cpu_bringup(void)
 	local_irq_enable();
 }
 
-/*
- * Note: cpu parameter is only relevant for PVH. The reason for passing it
- * is we can't do smp_processor_id until the percpu segments are loaded, for
- * which we need the cpu number! So we pass it in rdi as first parameter.
- */
-asmlinkage __visible void cpu_bringup_and_idle(int cpu)
+asmlinkage __visible void cpu_bringup_and_idle(void)
 {
-#ifdef CONFIG_XEN_PVH
-	if (xen_feature(XENFEAT_auto_translated_physmap) &&
-	    xen_feature(XENFEAT_supervisor_mode_kernel))
-		xen_pvh_secondary_vcpu_init(cpu);
-#endif
 	cpu_bringup();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
@@ -404,61 +394,47 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	gdt = get_cpu_gdt_table(cpu);
 
 #ifdef CONFIG_X86_32
-	/* Note: PVH is not yet supported on x86_32. */
 	ctxt->user_regs.fs = __KERNEL_PERCPU;
 	ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
 #endif
 	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
 
-	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
-		ctxt->flags = VGCF_IN_KERNEL;
-		ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
-		ctxt->user_regs.ds = __USER_DS;
-		ctxt->user_regs.es = __USER_DS;
-		ctxt->user_regs.ss = __KERNEL_DS;
+	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
+	ctxt->flags = VGCF_IN_KERNEL;
+	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
+	ctxt->user_regs.ds = __USER_DS;
+	ctxt->user_regs.es = __USER_DS;
+	ctxt->user_regs.ss = __KERNEL_DS;
 
-		xen_copy_trap_info(ctxt->trap_ctxt);
+	xen_copy_trap_info(ctxt->trap_ctxt);
 
-		ctxt->ldt_ents = 0;
+	ctxt->ldt_ents = 0;
 
-		BUG_ON((unsigned long)gdt & ~PAGE_MASK);
+	BUG_ON((unsigned long)gdt & ~PAGE_MASK);
 
-		gdt_mfn = arbitrary_virt_to_mfn(gdt);
-		make_lowmem_page_readonly(gdt);
-		make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
+	gdt_mfn = arbitrary_virt_to_mfn(gdt);
+	make_lowmem_page_readonly(gdt);
+	make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
 
-		ctxt->gdt_frames[0] = gdt_mfn;
-		ctxt->gdt_ents      = GDT_ENTRIES;
+	ctxt->gdt_frames[0] = gdt_mfn;
+	ctxt->gdt_ents      = GDT_ENTRIES;
 
-		ctxt->kernel_ss = __KERNEL_DS;
-		ctxt->kernel_sp = idle->thread.sp0;
+	ctxt->kernel_ss = __KERNEL_DS;
+	ctxt->kernel_sp = idle->thread.sp0;
 
 #ifdef CONFIG_X86_32
-		ctxt->event_callback_cs     = __KERNEL_CS;
-		ctxt->failsafe_callback_cs  = __KERNEL_CS;
+	ctxt->event_callback_cs     = __KERNEL_CS;
+	ctxt->failsafe_callback_cs  = __KERNEL_CS;
 #else
-		ctxt->gs_base_kernel = per_cpu_offset(cpu);
-#endif
-		ctxt->event_callback_eip    =
-					(unsigned long)xen_hypervisor_callback;
-		ctxt->failsafe_callback_eip =
-					(unsigned long)xen_failsafe_callback;
-		ctxt->user_regs.cs = __KERNEL_CS;
-		per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
-	}
-#ifdef CONFIG_XEN_PVH
-	else {
-		/*
-		 * The vcpu comes on kernel page tables which have the NX pte
-		 * bit set. This means before DS/SS is touched, NX in
-		 * EFER must be set. Hence the following assembly glue code.
-		 */
-		ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init;
-		ctxt->user_regs.rdi = cpu;
-		ctxt->user_regs.rsi = true;  /* entry == true */
-	}
+	ctxt->gs_base_kernel = per_cpu_offset(cpu);
 #endif
+	ctxt->event_callback_eip    =
+		(unsigned long)xen_hypervisor_callback;
+	ctxt->failsafe_callback_eip =
+		(unsigned long)xen_failsafe_callback;
+	ctxt->user_regs.cs = __KERNEL_CS;
+	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
+
 	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
 	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
 	if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index c5c16dc4f694..9beef333584a 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -21,12 +21,4 @@ static inline int xen_smp_intr_init(unsigned int cpu)
 static inline void xen_smp_intr_free(unsigned int cpu) {}
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_XEN_PVH
-extern void xen_pvh_early_cpu_init(int cpu, bool entry);
-#else
-static inline void xen_pvh_early_cpu_init(int cpu, bool entry)
-{
-}
-#endif
-
 #endif
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 7f8d8abf4c1a..37794e42b67d 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -16,25 +16,6 @@
 #include <xen/interface/xen-mca.h>
 #include <asm/xen/interface.h>
 
-#ifdef CONFIG_XEN_PVH
-#define PVH_FEATURES_STR  "|writable_descriptor_tables|auto_translated_physmap|supervisor_mode_kernel"
-/* Note the lack of 'hvm_callback_vector'. Older hypervisor will
- * balk at this being part of XEN_ELFNOTE_FEATURES, so we put it in
- * XEN_ELFNOTE_SUPPORTED_FEATURES which older hypervisors will ignore.
- */
-#define PVH_FEATURES ((1 << XENFEAT_writable_page_tables) | \
-		      (1 << XENFEAT_auto_translated_physmap) | \
-		      (1 << XENFEAT_supervisor_mode_kernel) | \
-		      (1 << XENFEAT_hvm_callback_vector))
-/* The XENFEAT_writable_page_tables is not stricly necessary as we set that
- * up regardless whether this CONFIG option is enabled or not, but it
- * clarifies what the right flags need to be.
- */
-#else
-#define PVH_FEATURES_STR  ""
-#define PVH_FEATURES (0)
-#endif
-
 	__INIT
 ENTRY(startup_xen)
 	cld
@@ -54,41 +35,6 @@ ENTRY(startup_xen)
 
 	__FINIT
 
-#ifdef CONFIG_XEN_PVH
-/*
- * xen_pvh_early_cpu_init() - early PVH VCPU initialization
- * @cpu:   this cpu number (%rdi)
- * @entry: true if this is a secondary vcpu coming up on this entry
- *         point, false if this is the boot CPU being initialized for
- *         the first time (%rsi)
- *
- * Note: This is called as a function on the boot CPU, and is the entry point
- *       on the secondary CPU.
- */
-ENTRY(xen_pvh_early_cpu_init)
-	mov     %rsi, %r11
-
-	/* Gather features to see if NX implemented. */
-	mov     $0x80000001, %eax
-	cpuid
-	mov     %edx, %esi
-
-	mov     $MSR_EFER, %ecx
-	rdmsr
-	bts     $_EFER_SCE, %eax
-
-	bt      $20, %esi
-	jnc     1f      	/* No NX, skip setting it */
-	bts     $_EFER_NX, %eax
-1:	wrmsr
-#ifdef CONFIG_SMP
-	cmp     $0, %r11b
-	jne     cpu_bringup_and_idle
-#endif
-	ret
-
-#endif /* CONFIG_XEN_PVH */
-
 .pushsection .text
 	.balign PAGE_SIZE
 ENTRY(hypercall_page)
@@ -114,10 +60,10 @@ ENTRY(hypercall_page)
 #endif
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          _ASM_PTR startup_xen)
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page)
-	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .ascii "!writable_page_tables|pae_pgdir_above_4gb"; .asciz PVH_FEATURES_STR)
-	ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long (PVH_FEATURES) |
-						(1 << XENFEAT_writable_page_tables) |
-						(1 << XENFEAT_dom0))
+	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,
+		.ascii "!writable_page_tables|pae_pgdir_above_4gb")
+	ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES,
+		.long (1 << XENFEAT_writable_page_tables) | (1 << XENFEAT_dom0))
 	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
 	ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
 	ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID,
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index ac0a2b0f9e62..f6a41c41ebc7 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -146,5 +146,4 @@ __visible void xen_adjust_exception_frame(void);
 
 extern int xen_panic_handler_init(void);
 
-void xen_pvh_secondary_vcpu_init(int cpu);
 #endif /* XEN_OPS_H */
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index fd8e872d2943..6a53577772c9 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1704,7 +1704,6 @@ void __init xen_init_IRQ(void)
 		pirq_eoi_map = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 		eoi_gmfn.gmfn = virt_to_gfn(pirq_eoi_map);
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_pirq_eoi_gmfn_v2, &eoi_gmfn);
-		/* TODO: No PVH support for PIRQ EOI */
 		if (rc != 0) {
 			free_page((unsigned long) pirq_eoi_map);
 			pirq_eoi_map = NULL;
diff --git a/include/xen/xen.h b/include/xen/xen.h
index f0f0252cff9a..d0f96840f71f 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -29,17 +29,6 @@ extern enum xen_domain_type xen_domain_type;
 #define xen_initial_domain()	(0)
 #endif	/* CONFIG_XEN_DOM0 */
 
-#ifdef CONFIG_XEN_PVH
-/* This functionality exists only for x86. The XEN_PVHVM support exists
- * only in x86 world - hence on ARM it will be always disabled.
- * N.B. ARM guests are neither PV nor HVM nor PVHVM.
- * It's a bit like PVH but is different also (it's further towards the H
- * end of the spectrum than even PVH).
- */
-#include <xen/features.h>
-#define xen_pvh_domain() (xen_pv_domain() && \
-			  xen_feature(XENFEAT_auto_translated_physmap))
-#else
 #define xen_pvh_domain()	(0)
-#endif
+
 #endif	/* _XEN_XEN_H */
-- 
cgit v1.2.3


From 7243b93345f7f8de260e8f5b4670803e64fcbb00 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Sun, 5 Feb 2017 19:50:52 -0500
Subject: xen/pvh: Bootstrap PVH guest

Start PVH guest at XEN_ELFNOTE_PHYS32_ENTRY address. Setup hypercall
page, initialize boot_params, enable early page tables.

Since this stub is executed before kernel entry point we cannot use
variables in .bss which is cleared by kernel. We explicitly place
variables that are initialized here into .data.

While adjusting xen_hvm_init_shared_info() make it use cpuid_e?x()
instead of cpuid() (wherever possible).

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
---
 arch/x86/xen/Kconfig     |   2 +-
 arch/x86/xen/Makefile    |   1 +
 arch/x86/xen/enlighten.c | 124 +++++++++++++++++++++++++++++++++---
 arch/x86/xen/xen-pvh.S   | 161 +++++++++++++++++++++++++++++++++++++++++++++++
 include/xen/xen.h        |   5 ++
 5 files changed, 282 insertions(+), 11 deletions(-)
 create mode 100644 arch/x86/xen/xen-pvh.S

(limited to 'arch')

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index c7b15f3e2cf3..76b6dbd627df 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -53,5 +53,5 @@ config XEN_DEBUG_FS
 
 config XEN_PVH
 	bool "Support for running as a PVH guest"
-	depends on X86_64 && XEN && XEN_PVHVM
+	depends on XEN && XEN_PVHVM && ACPI
 	def_bool n
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index e47e52787d32..cb0164aee156 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -23,3 +23,4 @@ obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
 obj-$(CONFIG_XEN_EFI)		+= efi.o
+obj-$(CONFIG_XEN_PVH)	 	+= xen-pvh.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 828f1b226f56..d2144f7c8fab 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -45,6 +45,7 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/nmi.h>
 #include <xen/interface/xen-mca.h>
+#include <xen/interface/hvm/start_info.h>
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/hvm.h>
@@ -176,6 +177,20 @@ struct tls_descs {
  */
 static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
 
+#ifdef CONFIG_XEN_PVH
+/*
+ * PVH variables.
+ *
+ * xen_pvh and pvh_bootparams need to live in data segment since they
+ * are used after startup_{32|64}, which clear .bss, are invoked.
+ */
+bool xen_pvh __attribute__((section(".data"))) = 0;
+struct boot_params pvh_bootparams __attribute__((section(".data")));
+
+struct hvm_start_info pvh_start_info;
+unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
+#endif
+
 static void clamp_max_cpus(void)
 {
 #ifdef CONFIG_SMP
@@ -1656,6 +1671,90 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 }
 
+#ifdef CONFIG_XEN_PVH
+static void __init init_pvh_bootparams(void)
+{
+	struct xen_memory_map memmap;
+	unsigned int i;
+	int rc;
+
+	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+
+	memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map);
+	set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map);
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc) {
+		xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
+		BUG();
+	}
+
+	if (memmap.nr_entries < E820MAX - 1) {
+		pvh_bootparams.e820_map[memmap.nr_entries].addr =
+			ISA_START_ADDRESS;
+		pvh_bootparams.e820_map[memmap.nr_entries].size =
+			ISA_END_ADDRESS - ISA_START_ADDRESS;
+		pvh_bootparams.e820_map[memmap.nr_entries].type =
+			E820_RESERVED;
+		memmap.nr_entries++;
+	} else
+		xen_raw_printk("Warning: Can fit ISA range into e820\n");
+
+	sanitize_e820_map(pvh_bootparams.e820_map,
+			  ARRAY_SIZE(pvh_bootparams.e820_map),
+			  &memmap.nr_entries);
+
+	pvh_bootparams.e820_entries = memmap.nr_entries;
+	for (i = 0; i < pvh_bootparams.e820_entries; i++)
+		e820_add_region(pvh_bootparams.e820_map[i].addr,
+				pvh_bootparams.e820_map[i].size,
+				pvh_bootparams.e820_map[i].type);
+
+	pvh_bootparams.hdr.cmd_line_ptr =
+		pvh_start_info.cmdline_paddr;
+
+	/* The first module is always ramdisk. */
+	if (pvh_start_info.nr_modules) {
+		struct hvm_modlist_entry *modaddr =
+			__va(pvh_start_info.modlist_paddr);
+		pvh_bootparams.hdr.ramdisk_image = modaddr->paddr;
+		pvh_bootparams.hdr.ramdisk_size = modaddr->size;
+	}
+
+	/*
+	 * See Documentation/x86/boot.txt.
+	 *
+	 * Version 2.12 supports Xen entry point but we will use default x86/PC
+	 * environment (i.e. hardware_subarch 0).
+	 */
+	pvh_bootparams.hdr.version = 0x212;
+	pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */
+}
+
+/*
+ * This routine (and those that it might call) should not use
+ * anything that lives in .bss since that segment will be cleared later.
+ */
+void __init xen_prepare_pvh(void)
+{
+	u32 msr;
+	u64 pfn;
+
+	if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) {
+		xen_raw_printk("Error: Unexpected magic value (0x%08x)\n",
+				pvh_start_info.magic);
+		BUG();
+	}
+
+	xen_pvh = 1;
+
+	msr = cpuid_ebx(xen_cpuid_base() + 2);
+	pfn = __pa(hypercall_page);
+	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+
+	init_pvh_bootparams();
+}
+#endif
+
 void __ref xen_hvm_init_shared_info(void)
 {
 	int cpu;
@@ -1695,20 +1794,29 @@ void __ref xen_hvm_init_shared_info(void)
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
-	uint32_t eax, ebx, ecx, edx, pages, msr, base;
-	u64 pfn;
+	uint32_t eax, ebx, ecx, edx, base;
 
 	base = xen_cpuid_base();
-	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
+	eax = cpuid_eax(base + 1);
 
 	major = eax >> 16;
 	minor = eax & 0xffff;
 	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
 
-	cpuid(base + 2, &pages, &msr, &ecx, &edx);
+	xen_domain_type = XEN_HVM_DOMAIN;
 
-	pfn = __pa(hypercall_page);
-	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+	/* PVH set up hypercall page in xen_prepare_pvh(). */
+	if (xen_pvh_domain())
+		pv_info.name = "Xen PVH";
+	else {
+		u64 pfn;
+		uint32_t msr;
+
+		pv_info.name = "Xen HVM";
+		msr = cpuid_ebx(base + 2);
+		pfn = __pa(hypercall_page);
+		wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
+	}
 
 	xen_setup_features();
 
@@ -1717,10 +1825,6 @@ static void __init init_hvm_pv_info(void)
 		this_cpu_write(xen_vcpu_id, ebx);
 	else
 		this_cpu_write(xen_vcpu_id, smp_processor_id());
-
-	pv_info.name = "Xen HVM";
-
-	xen_domain_type = XEN_HVM_DOMAIN;
 }
 #endif
 
diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S
new file mode 100644
index 000000000000..5e246716d58f
--- /dev/null
+++ b/arch/x86/xen/xen-pvh.S
@@ -0,0 +1,161 @@
+/*
+ * Copyright C 2016, Oracle and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+	.code32
+	.text
+#define _pa(x)          ((x) - __START_KERNEL_map)
+
+#include <linux/elfnote.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/asm.h>
+#include <asm/boot.h>
+#include <asm/processor-flags.h>
+#include <asm/msr.h>
+#include <xen/interface/elfnote.h>
+
+	__HEAD
+
+/*
+ * Entry point for PVH guests.
+ *
+ * Xen ABI specifies the following register state when we come here:
+ *
+ * - `ebx`: contains the physical memory address where the loader has placed
+ *          the boot start info structure.
+ * - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared.
+ * - `cr4`: all bits are cleared.
+ * - `cs `: must be a 32-bit read/execute code segment with a base of ‘0’
+ *          and a limit of ‘0xFFFFFFFF’. The selector value is unspecified.
+ * - `ds`, `es`: must be a 32-bit read/write data segment with a base of
+ *               ‘0’ and a limit of ‘0xFFFFFFFF’. The selector values are all
+ *               unspecified.
+ * - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit
+ *         of '0x67'.
+ * - `eflags`: bit 17 (VM) must be cleared. Bit 9 (IF) must be cleared.
+ *             Bit 8 (TF) must be cleared. Other bits are all unspecified.
+ *
+ * All other processor registers and flag bits are unspecified. The OS is in
+ * charge of setting up it's own stack, GDT and IDT.
+ */
+
+ENTRY(pvh_start_xen)
+	cld
+
+	lgdt (_pa(gdt))
+
+	mov $(__BOOT_DS),%eax
+	mov %eax,%ds
+	mov %eax,%es
+	mov %eax,%ss
+
+	/* Stash hvm_start_info. */
+	mov $_pa(pvh_start_info), %edi
+	mov %ebx, %esi
+	mov _pa(pvh_start_info_sz), %ecx
+	shr $2,%ecx
+	rep
+	movsl
+
+	mov $_pa(early_stack_end), %esp
+
+	/* Enable PAE mode. */
+	mov %cr4, %eax
+	orl $X86_CR4_PAE, %eax
+	mov %eax, %cr4
+
+#ifdef CONFIG_X86_64
+	/* Enable Long mode. */
+	mov $MSR_EFER, %ecx
+	rdmsr
+	btsl $_EFER_LME, %eax
+	wrmsr
+
+	/* Enable pre-constructed page tables. */
+	mov $_pa(init_level4_pgt), %eax
+	mov %eax, %cr3
+	mov $(X86_CR0_PG | X86_CR0_PE), %eax
+	mov %eax, %cr0
+
+	/* Jump to 64-bit mode. */
+	ljmp $__KERNEL_CS, $_pa(1f)
+
+	/* 64-bit entry point. */
+	.code64
+1:
+	call xen_prepare_pvh
+
+	/* startup_64 expects boot_params in %rsi. */
+	mov $_pa(pvh_bootparams), %rsi
+	mov $_pa(startup_64), %rax
+	jmp *%rax
+
+#else /* CONFIG_X86_64 */
+
+	call mk_early_pgtbl_32
+
+	mov $_pa(initial_page_table), %eax
+	mov %eax, %cr3
+
+	mov %cr0, %eax
+	or $(X86_CR0_PG | X86_CR0_PE), %eax
+	mov %eax, %cr0
+
+	ljmp $__BOOT_CS, $1f
+1:
+	call xen_prepare_pvh
+	mov $_pa(pvh_bootparams), %esi
+
+	/* startup_32 doesn't expect paging and PAE to be on. */
+	ljmp $__BOOT_CS, $_pa(2f)
+2:
+	mov %cr0, %eax
+	and $~X86_CR0_PG, %eax
+	mov %eax, %cr0
+	mov %cr4, %eax
+	and $~X86_CR4_PAE, %eax
+	mov %eax, %cr4
+
+	ljmp $__BOOT_CS, $_pa(startup_32)
+#endif
+END(pvh_start_xen)
+
+	.section ".init.data","aw"
+	.balign 8
+gdt:
+	.word gdt_end - gdt_start
+	.long _pa(gdt_start)
+	.word 0
+gdt_start:
+	.quad 0x0000000000000000            /* NULL descriptor */
+	.quad 0x0000000000000000            /* reserved */
+#ifdef CONFIG_X86_64
+	.quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* __KERNEL_CS */
+#else
+	.quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* __KERNEL_CS */
+#endif
+	.quad GDT_ENTRY(0xc092, 0, 0xfffff) /* __KERNEL_DS */
+gdt_end:
+
+	.balign 4
+early_stack:
+	.fill 256, 1, 0
+early_stack_end:
+
+	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,
+	             _ASM_PTR (pvh_start_xen - __START_KERNEL_map))
diff --git a/include/xen/xen.h b/include/xen/xen.h
index d0f96840f71f..6e8b7fc79801 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -29,6 +29,11 @@ extern enum xen_domain_type xen_domain_type;
 #define xen_initial_domain()	(0)
 #endif	/* CONFIG_XEN_DOM0 */
 
+#ifdef CONFIG_XEN_PVH
+extern bool xen_pvh;
+#define xen_pvh_domain()	(xen_hvm_domain() && xen_pvh)
+#else
 #define xen_pvh_domain()	(0)
+#endif
 
 #endif	/* _XEN_XEN_H */
-- 
cgit v1.2.3


From 5adad168e586cb381633f45d181bb729b04393a5 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Sun, 5 Feb 2017 19:50:58 -0500
Subject: xen/pvh: Make sure we don't use ACPI_IRQ_MODEL_PIC for SCI

Since we are not using PIC and (at least currently) don't have IOAPIC
we want to make sure that acpi_irq_model doesn't stay set to
ACPI_IRQ_MODEL_PIC (which is the default value). If we allowed it to
stay then acpi_os_install_interrupt_handler() would try (and fail) to
request_irq() for PIC.

Instead we set the model to ACPI_IRQ_MODEL_PLATFORM which will prevent
this from happening.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
---
 arch/x86/xen/enlighten.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'arch')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d2144f7c8fab..6d406f3465bc 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1672,6 +1672,16 @@ asmlinkage __visible void __init xen_start_kernel(void)
 }
 
 #ifdef CONFIG_XEN_PVH
+
+static void xen_pvh_arch_setup(void)
+{
+#ifdef CONFIG_ACPI
+	/* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */
+	if (nr_ioapics == 0)
+		acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
+#endif
+}
+
 static void __init init_pvh_bootparams(void)
 {
 	struct xen_memory_map memmap;
@@ -1752,6 +1762,8 @@ void __init xen_prepare_pvh(void)
 	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
 
 	init_pvh_bootparams();
+
+	x86_init.oem.arch_setup = xen_pvh_arch_setup;
 }
 #endif
 
-- 
cgit v1.2.3


From bcc57df281d93dfa502c824e9f73e0191c3f7c34 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Mon, 6 Feb 2017 10:57:15 -0500
Subject: xen/pvh: PVH guests always have PV devices

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/xen/platform-pci-unplug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch')

diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 90d1b83cf35f..33a783c77d96 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -73,8 +73,8 @@ bool xen_has_pv_devices(void)
 	if (!xen_domain())
 		return false;
 
-	/* PV domains always have them. */
-	if (xen_pv_domain())
+	/* PV and PVH domains always have them. */
+	if (xen_pv_domain() || xen_pvh_domain())
 		return true;
 
 	/* And user has xen_platform_pci=0 set in guest config as
-- 
cgit v1.2.3


From 7a1c44ebc5ac2e2c28d95b0da6060728c334e7e4 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Mon, 6 Feb 2017 10:58:06 -0500
Subject: xen/pvh: Use Xen's emergency_restart op for PVH guests

Using native_machine_emergency_restart (called during reboot) will
lead PVH guests to machine_real_restart()  where we try to use
real_mode_header which is not initialized.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
---
 arch/x86/xen/enlighten.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch')

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 6d406f3465bc..ec1d5c46e58f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1924,6 +1924,9 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+
+	if (xen_pvh_domain())
+		machine_ops.emergency_restart = xen_emergency_restart;
 #ifdef CONFIG_KEXEC_CORE
 	machine_ops.shutdown = xen_hvm_shutdown;
 	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
-- 
cgit v1.2.3


From ab520be8cd5d56867fc95cfbc34b90880faf1f9d Mon Sep 17 00:00:00 2001
From: Paul Durrant <paul.durrant@citrix.com>
Date: Mon, 13 Feb 2017 17:03:23 +0000
Subject: xen/privcmd: Add IOCTL_PRIVCMD_DM_OP

Recently a new dm_op[1] hypercall was added to Xen to provide a mechanism
for restricting device emulators (such as QEMU) to a limited set of
hypervisor operations, and being able to audit those operations in the
kernel of the domain in which they run.

This patch adds IOCTL_PRIVCMD_DM_OP as gateway for __HYPERVISOR_dm_op.

NOTE: There is no requirement for user-space code to bounce data through
      locked memory buffers (as with IOCTL_PRIVCMD_HYPERCALL) since
      privcmd has enough information to lock the original buffers
      directly.

[1] http://xenbits.xen.org/gitweb/?p=xen.git;a=commit;h=524a98c2

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/arm/xen/enlighten.c             |   1 +
 arch/arm/xen/hypercall.S             |   1 +
 arch/arm64/xen/hypercall.S           |   1 +
 arch/x86/include/asm/xen/hypercall.h |   7 ++
 drivers/xen/privcmd.c                | 139 +++++++++++++++++++++++++++++++++++
 include/uapi/xen/privcmd.h           |  13 ++++
 include/xen/arm/hypercall.h          |   1 +
 include/xen/interface/hvm/dm_op.h    |  32 ++++++++
 include/xen/interface/xen.h          |   1 +
 9 files changed, 196 insertions(+)
 create mode 100644 include/xen/interface/hvm/dm_op.h

(limited to 'arch')

diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 11d9f2898b16..81e3217b12d3 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -457,4 +457,5 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
+EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
 EXPORT_SYMBOL_GPL(privcmd_call);
diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
index a648dfc3be30..b0b80c0f09f3 100644
--- a/arch/arm/xen/hypercall.S
+++ b/arch/arm/xen/hypercall.S
@@ -92,6 +92,7 @@ HYPERCALL1(tmem_op);
 HYPERCALL1(platform_op_raw);
 HYPERCALL2(multicall);
 HYPERCALL2(vm_assist);
+HYPERCALL3(dm_op);
 
 ENTRY(privcmd_call)
 	stmdb sp!, {r4}
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 947830a459d2..401ceb71540c 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -84,6 +84,7 @@ HYPERCALL1(tmem_op);
 HYPERCALL1(platform_op_raw);
 HYPERCALL2(multicall);
 HYPERCALL2(vm_assist);
+HYPERCALL3(dm_op);
 
 ENTRY(privcmd_call)
 	mov x16, x0
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index a12a047184ee..f6d20f6cca12 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -472,6 +472,13 @@ HYPERVISOR_xenpmu_op(unsigned int op, void *arg)
 	return _hypercall2(int, xenpmu_op, op, arg);
 }
 
+static inline int
+HYPERVISOR_dm_op(
+	domid_t dom, unsigned int nr_bufs, void *bufs)
+{
+	return _hypercall3(int, dm_op, dom, nr_bufs, bufs);
+}
+
 static inline void
 MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
 {
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 5e5c7aef0c9f..1a6f1860e008 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -22,6 +22,7 @@
 #include <linux/pagemap.h>
 #include <linux/seq_file.h>
 #include <linux/miscdevice.h>
+#include <linux/moduleparam.h>
 
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
@@ -32,6 +33,7 @@
 #include <xen/xen.h>
 #include <xen/privcmd.h>
 #include <xen/interface/xen.h>
+#include <xen/interface/hvm/dm_op.h>
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/xen-ops.h>
@@ -43,6 +45,17 @@ MODULE_LICENSE("GPL");
 
 #define PRIV_VMA_LOCKED ((void *)1)
 
+static unsigned int privcmd_dm_op_max_num = 16;
+module_param_named(dm_op_max_nr_bufs, privcmd_dm_op_max_num, uint, 0644);
+MODULE_PARM_DESC(dm_op_max_nr_bufs,
+		 "Maximum number of buffers per dm_op hypercall");
+
+static unsigned int privcmd_dm_op_buf_max_size = 4096;
+module_param_named(dm_op_buf_max_size, privcmd_dm_op_buf_max_size, uint,
+		   0644);
+MODULE_PARM_DESC(dm_op_buf_max_size,
+		 "Maximum size of a dm_op hypercall buffer");
+
 static int privcmd_vma_range_is_mapped(
                struct vm_area_struct *vma,
                unsigned long addr,
@@ -548,6 +561,128 @@ out_unlock:
 	goto out;
 }
 
+static int lock_pages(
+	struct privcmd_dm_op_buf kbufs[], unsigned int num,
+	struct page *pages[], unsigned int nr_pages)
+{
+	unsigned int i;
+
+	for (i = 0; i < num; i++) {
+		unsigned int requested;
+		int pinned;
+
+		requested = DIV_ROUND_UP(
+			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
+			PAGE_SIZE);
+		if (requested > nr_pages)
+			return -ENOSPC;
+
+		pinned = get_user_pages_fast(
+			(unsigned long) kbufs[i].uptr,
+			requested, FOLL_WRITE, pages);
+		if (pinned < 0)
+			return pinned;
+
+		nr_pages -= pinned;
+		pages += pinned;
+	}
+
+	return 0;
+}
+
+static void unlock_pages(struct page *pages[], unsigned int nr_pages)
+{
+	unsigned int i;
+
+	if (!pages)
+		return;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (pages[i])
+			put_page(pages[i]);
+	}
+}
+
+static long privcmd_ioctl_dm_op(void __user *udata)
+{
+	struct privcmd_dm_op kdata;
+	struct privcmd_dm_op_buf *kbufs;
+	unsigned int nr_pages = 0;
+	struct page **pages = NULL;
+	struct xen_dm_op_buf *xbufs = NULL;
+	unsigned int i;
+	long rc;
+
+	if (copy_from_user(&kdata, udata, sizeof(kdata)))
+		return -EFAULT;
+
+	if (kdata.num == 0)
+		return 0;
+
+	if (kdata.num > privcmd_dm_op_max_num)
+		return -E2BIG;
+
+	kbufs = kcalloc(kdata.num, sizeof(*kbufs), GFP_KERNEL);
+	if (!kbufs)
+		return -ENOMEM;
+
+	if (copy_from_user(kbufs, kdata.ubufs,
+			   sizeof(*kbufs) * kdata.num)) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	for (i = 0; i < kdata.num; i++) {
+		if (kbufs[i].size > privcmd_dm_op_buf_max_size) {
+			rc = -E2BIG;
+			goto out;
+		}
+
+		if (!access_ok(VERIFY_WRITE, kbufs[i].uptr,
+			       kbufs[i].size)) {
+			rc = -EFAULT;
+			goto out;
+		}
+
+		nr_pages += DIV_ROUND_UP(
+			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
+			PAGE_SIZE);
+	}
+
+	pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
+	if (!pages) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	xbufs = kcalloc(kdata.num, sizeof(*xbufs), GFP_KERNEL);
+	if (!xbufs) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	rc = lock_pages(kbufs, kdata.num, pages, nr_pages);
+	if (rc)
+		goto out;
+
+	for (i = 0; i < kdata.num; i++) {
+		set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
+		xbufs[i].size = kbufs[i].size;
+	}
+
+	xen_preemptible_hcall_begin();
+	rc = HYPERVISOR_dm_op(kdata.dom, kdata.num, xbufs);
+	xen_preemptible_hcall_end();
+
+out:
+	unlock_pages(pages, nr_pages);
+	kfree(xbufs);
+	kfree(pages);
+	kfree(kbufs);
+
+	return rc;
+}
+
 static long privcmd_ioctl(struct file *file,
 			  unsigned int cmd, unsigned long data)
 {
@@ -571,6 +706,10 @@ static long privcmd_ioctl(struct file *file,
 		ret = privcmd_ioctl_mmap_batch(udata, 2);
 		break;
 
+	case IOCTL_PRIVCMD_DM_OP:
+		ret = privcmd_ioctl_dm_op(udata);
+		break;
+
 	default:
 		break;
 	}
diff --git a/include/uapi/xen/privcmd.h b/include/uapi/xen/privcmd.h
index 7ddeeda93809..f8c5d75b99e1 100644
--- a/include/uapi/xen/privcmd.h
+++ b/include/uapi/xen/privcmd.h
@@ -77,6 +77,17 @@ struct privcmd_mmapbatch_v2 {
 	int __user *err;  /* array of error codes */
 };
 
+struct privcmd_dm_op_buf {
+	void __user *uptr;
+	size_t size;
+};
+
+struct privcmd_dm_op {
+	domid_t dom;
+	__u16 num;
+	const struct privcmd_dm_op_buf __user *ubufs;
+};
+
 /*
  * @cmd: IOCTL_PRIVCMD_HYPERCALL
  * @arg: &privcmd_hypercall_t
@@ -98,5 +109,7 @@ struct privcmd_mmapbatch_v2 {
 	_IOC(_IOC_NONE, 'P', 3, sizeof(struct privcmd_mmapbatch))
 #define IOCTL_PRIVCMD_MMAPBATCH_V2				\
 	_IOC(_IOC_NONE, 'P', 4, sizeof(struct privcmd_mmapbatch_v2))
+#define IOCTL_PRIVCMD_DM_OP					\
+	_IOC(_IOC_NONE, 'P', 5, sizeof(struct privcmd_dm_op))
 
 #endif /* __LINUX_PUBLIC_PRIVCMD_H__ */
diff --git a/include/xen/arm/hypercall.h b/include/xen/arm/hypercall.h
index 9d874db13c0e..73db4b2eeb89 100644
--- a/include/xen/arm/hypercall.h
+++ b/include/xen/arm/hypercall.h
@@ -53,6 +53,7 @@ int HYPERVISOR_physdev_op(int cmd, void *arg);
 int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
 int HYPERVISOR_tmem_op(void *arg);
 int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type);
+int HYPERVISOR_dm_op(domid_t domid, unsigned int nr_bufs, void *bufs);
 int HYPERVISOR_platform_op_raw(void *arg);
 static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
 {
diff --git a/include/xen/interface/hvm/dm_op.h b/include/xen/interface/hvm/dm_op.h
new file mode 100644
index 000000000000..ee9e480bc559
--- /dev/null
+++ b/include/xen/interface/hvm/dm_op.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (c) 2016, Citrix Systems Inc
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef __XEN_PUBLIC_HVM_DM_OP_H__
+#define __XEN_PUBLIC_HVM_DM_OP_H__
+
+struct xen_dm_op_buf {
+	GUEST_HANDLE(void) h;
+	xen_ulong_t size;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_dm_op_buf);
+
+#endif /* __XEN_PUBLIC_HVM_DM_OP_H__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 1b0d189cd3d3..4f4830ef8f93 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -81,6 +81,7 @@
 #define __HYPERVISOR_tmem_op              38
 #define __HYPERVISOR_xc_reserved_op       39 /* reserved for XenClient */
 #define __HYPERVISOR_xenpmu_op            40
+#define __HYPERVISOR_dm_op                41
 
 /* Architecture-specific hypercall definitions. */
 #define __HYPERVISOR_arch_0               48
-- 
cgit v1.2.3