Merge tag 'for-linus-6.12-rc1a-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull more xen updates from Juergen Gross:
 "A second round of Xen related changes and features:

   - a small fix of the xen-pciback driver for a warning issued by
     sparse

   - support PCI passthrough when using a PVH dom0

   - enable loading the kernel in PVH mode at arbitrary addresses,
     avoiding conflicts with the memory map when running as a Xen dom0
     using the host memory layout"

* tag 'for-linus-6.12-rc1a-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  x86/pvh: Add 64bit relocation page tables
  x86/kernel: Move page table macros to header
  x86/pvh: Set phys_base when calling xen_prepare_pvh()
  x86/pvh: Make PVH entrypoint PIC for x86-64
  xen: sync elfnote.h from xen tree
  xen/pciback: fix cast to restricted pci_ers_result_t and pci_power_t
  xen/privcmd: Add new syscall to get gsi from dev
  xen/pvh: Setup gsi for passthrough device
  xen/pci: Add a function to reset device for xen

arch/x86/include/asm/pgtable_64.h

@@ -270,5 +270,26 @@ static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
 
 #include <asm/pgtable-invert.h>
 
-#endif /* !__ASSEMBLY__ */
+#else /* __ASSEMBLY__ */
+
+#define l4_index(x)	(((x) >> 39) & 511)
+#define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+
+L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4)
+L4_START_KERNEL = l4_index(__START_KERNEL_map)
+
+L3_START_KERNEL = pud_index(__START_KERNEL_map)
+
+#define SYM_DATA_START_PAGE_ALIGNED(name)			\
+	SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE)
+
+/* Automate the creation of 1 to 1 mapping pmd entries */
+#define PMDS(START, PERM, COUNT)			\
+	i = 0 ;						\
+	.rept (COUNT) ;					\
+	.quad	(START) + (i << PMD_SHIFT) + (PERM) ;	\
+	i = i + 1 ;					\
+	.endr
+
+#endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */

arch/x86/kernel/head_64.S

@@ -32,13 +32,6 @@
  * We are not able to switch in one step to the final KERNEL ADDRESS SPACE
  * because we need identity-mapped pages.
  */
-#define l4_index(x)	(((x) >> 39) & 511)
-#define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
-
-L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4)
-L4_START_KERNEL = l4_index(__START_KERNEL_map)
-
-L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
 	__HEAD
 	.code64
@@ -577,9 +570,6 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb)
 SYM_CODE_END(vc_no_ghcb)
 #endif
 
-#define SYM_DATA_START_PAGE_ALIGNED(name)			\
-	SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE)
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Each PGD needs to be 8k long and 8k aligned.  We do not
@@ -601,14 +591,6 @@ SYM_CODE_END(vc_no_ghcb)
 #define PTI_USER_PGD_FILL	0
 #endif
 
-/* Automate the creation of 1 to 1 mapping pmd entries */
-#define PMDS(START, PERM, COUNT)			\
-	i = 0 ;						\
-	.rept (COUNT) ;					\
-	.quad	(START) + (i << PMD_SHIFT) + (PERM) ;	\
-	i = i + 1 ;					\
-	.endr
-
 	__INITDATA
 	.balign 4
 
@@ -708,8 +690,6 @@ SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt)
 	.endr
 SYM_DATA_END(level1_fixmap_pgt)
 
-#undef PMDS
-
 	.data
 	.align 16
 

arch/x86/platform/pvh/head.S

@@ -7,6 +7,7 @@
 	.code32
 	.text
 #define _pa(x)          ((x) - __START_KERNEL_map)
+#define rva(x)          ((x) - pvh_start_xen)
 
 #include <linux/elfnote.h>
 #include <linux/init.h>
@@ -15,6 +16,7 @@
 #include <asm/segment.h>
 #include <asm/asm.h>
 #include <asm/boot.h>
+#include <asm/pgtable.h>
 #include <asm/processor-flags.h>
 #include <asm/msr.h>
 #include <asm/nospec-branch.h>
@@ -54,7 +56,25 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	UNWIND_HINT_END_OF_STACK
 	cld
 
-	lgdt (_pa(gdt))
+	/*
+	 * See the comment for startup_32 for more details.  We need to
+	 * execute a call to get the execution address to be position
+	 * independent, but we don't have a stack.  Save and restore the
+	 * magic field of start_info in ebx, and use that as the stack.
+	 */
+	mov  (%ebx), %eax
+	leal 4(%ebx), %esp
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call 1f
+1:	popl %ebp
+	mov  %eax, (%ebx)
+	subl $rva(1b), %ebp
+	movl $0, %esp
+
+	leal rva(gdt)(%ebp), %eax
+	leal rva(gdt_start)(%ebp), %ecx
+	movl %ecx, 2(%eax)
+	lgdt (%eax)
 
 	mov $PVH_DS_SEL,%eax
 	mov %eax,%ds
@@ -62,14 +82,14 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	mov %eax,%ss
 
 	/* Stash hvm_start_info. */
-	mov $_pa(pvh_start_info), %edi
+	leal rva(pvh_start_info)(%ebp), %edi
 	mov %ebx, %esi
-	mov _pa(pvh_start_info_sz), %ecx
+	movl rva(pvh_start_info_sz)(%ebp), %ecx
 	shr $2,%ecx
 	rep
 	movsl
 
-	mov $_pa(early_stack_end), %esp
+	leal rva(early_stack_end)(%ebp), %esp
 
 	/* Enable PAE mode. */
 	mov %cr4, %eax
@@ -83,31 +103,86 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	btsl $_EFER_LME, %eax
 	wrmsr
 
+	mov %ebp, %ebx
+	subl $_pa(pvh_start_xen), %ebx /* offset */
+	jz .Lpagetable_done
+
+	/* Fixup page-tables for relocation. */
+	leal rva(pvh_init_top_pgt)(%ebp), %edi
+	movl $PTRS_PER_PGD, %ecx
+2:
+	testl $_PAGE_PRESENT, 0x00(%edi)
+	jz 1f
+	addl %ebx, 0x00(%edi)
+1:
+	addl $8, %edi
+	decl %ecx
+	jnz 2b
+
+	/* L3 ident has a single entry. */
+	leal rva(pvh_level3_ident_pgt)(%ebp), %edi
+	addl %ebx, 0x00(%edi)
+
+	leal rva(pvh_level3_kernel_pgt)(%ebp), %edi
+	addl %ebx, (PAGE_SIZE - 16)(%edi)
+	addl %ebx, (PAGE_SIZE - 8)(%edi)
+
+	/* pvh_level2_ident_pgt is fine - large pages */
+
+	/* pvh_level2_kernel_pgt needs adjustment - large pages */
+	leal rva(pvh_level2_kernel_pgt)(%ebp), %edi
+	movl $PTRS_PER_PMD, %ecx
+2:
+	testl $_PAGE_PRESENT, 0x00(%edi)
+	jz 1f
+	addl %ebx, 0x00(%edi)
+1:
+	addl $8, %edi
+	decl %ecx
+	jnz 2b
+
+.Lpagetable_done:
 	/* Enable pre-constructed page tables. */
-	mov $_pa(init_top_pgt), %eax
+	leal rva(pvh_init_top_pgt)(%ebp), %eax
 	mov %eax, %cr3
 	mov $(X86_CR0_PG | X86_CR0_PE), %eax
 	mov %eax, %cr0
 
 	/* Jump to 64-bit mode. */
-	ljmp $PVH_CS_SEL, $_pa(1f)
+	pushl $PVH_CS_SEL
+	leal  rva(1f)(%ebp), %eax
+	pushl %eax
+	lretl
 
 	/* 64-bit entry point. */
 	.code64
 1:
+	UNWIND_HINT_END_OF_STACK
+
 	/* Set base address in stack canary descriptor. */
 	mov $MSR_GS_BASE,%ecx
-	mov $_pa(canary), %eax
+	leal canary(%rip), %eax
 	xor %edx, %edx
 	wrmsr
 
+	/*
+	 * Calculate load offset and store in phys_base.  __pa() needs
+	 * phys_base set to calculate the hypercall page in xen_pvh_init().
+	 */
+	movq %rbp, %rbx
+	subq $_pa(pvh_start_xen), %rbx
+	movq %rbx, phys_base(%rip)
 	call xen_prepare_pvh
+	/*
+	 * Clear phys_base.  __startup_64 will *add* to its value,
+	 * so reset to 0.
+	 */
+	xor  %rbx, %rbx
+	movq %rbx, phys_base(%rip)
 
 	/* startup_64 expects boot_params in %rsi. */
-	mov $_pa(pvh_bootparams), %rsi
-	mov $_pa(startup_64), %rax
-	ANNOTATE_RETPOLINE_SAFE
-	jmp *%rax
+	lea pvh_bootparams(%rip), %rsi
+	jmp startup_64
 
 #else /* CONFIG_X86_64 */
 
@@ -143,7 +218,7 @@ SYM_CODE_END(pvh_start_xen)
 	.balign 8
 SYM_DATA_START_LOCAL(gdt)
 	.word gdt_end - gdt_start
-	.long _pa(gdt_start)
+	.long _pa(gdt_start) /* x86-64 will overwrite if relocated. */
 	.word 0
 SYM_DATA_END(gdt)
 SYM_DATA_START_LOCAL(gdt_start)
@@ -163,5 +238,67 @@ SYM_DATA_START_LOCAL(early_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
 
+#ifdef CONFIG_X86_64
+/*
+ * Xen PVH needs a set of identity mapped and kernel high mapping
+ * page tables.  pvh_start_xen starts running on the identity mapped
+ * page tables, but xen_prepare_pvh calls into the high mapping.
+ * These page tables need to be relocatable and are only used until
+ * startup_64 transitions to init_top_pgt.
+ */
+SYM_DATA_START_PAGE_ALIGNED(pvh_init_top_pgt)
+	.quad   pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.org    pvh_init_top_pgt + L4_PAGE_OFFSET * 8, 0
+	.quad   pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.org    pvh_init_top_pgt + L4_START_KERNEL * 8, 0
+	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
+	.quad   pvh_level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+SYM_DATA_END(pvh_init_top_pgt)
+
+SYM_DATA_START_PAGE_ALIGNED(pvh_level3_ident_pgt)
+	.quad	pvh_level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.fill	511, 8, 0
+SYM_DATA_END(pvh_level3_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(pvh_level2_ident_pgt)
+	/*
+	 * Since I easily can, map the first 1G.
+	 * Don't set NX because code runs from these pages.
+	 *
+	 * Note: This sets _PAGE_GLOBAL despite whether
+	 * the CPU supports it or it is enabled.  But,
+	 * the CPU should ignore the bit.
+	 */
+	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
+SYM_DATA_END(pvh_level2_ident_pgt)
+SYM_DATA_START_PAGE_ALIGNED(pvh_level3_kernel_pgt)
+	.fill	L3_START_KERNEL, 8, 0
+	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
+	.quad	pvh_level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.quad	0 /* no fixmap */
+SYM_DATA_END(pvh_level3_kernel_pgt)
+
+SYM_DATA_START_PAGE_ALIGNED(pvh_level2_kernel_pgt)
+	/*
+	 * Kernel high mapping.
+	 *
+	 * The kernel code+data+bss must be located below KERNEL_IMAGE_SIZE in
+	 * virtual address space, which is 1 GiB if RANDOMIZE_BASE is enabled,
+	 * 512 MiB otherwise.
+	 *
+	 * (NOTE: after that starts the module area, see MODULES_VADDR.)
+	 *
+	 * This table is eventually used by the kernel during normal runtime.
+	 * Care must be taken to clear out undesired bits later, like _PAGE_RW
+	 * or _PAGE_GLOBAL in some cases.
+	 */
+	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE / PMD_SIZE)
+SYM_DATA_END(pvh_level2_kernel_pgt)
+
+	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_RELOC,
+		     .long CONFIG_PHYSICAL_ALIGN;
+		     .long LOAD_PHYSICAL_ADDR;
+		     .long KERNEL_IMAGE_SIZE - 1)
+#endif
+
 	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,
 	             _ASM_PTR (pvh_start_xen - __START_KERNEL_map))

arch/x86/xen/enlighten_pvh.c

@@ -4,6 +4,7 @@
 #include <linux/mm.h>
 
 #include <xen/hvc-console.h>
+#include <xen/acpi.h>
 
 #include <asm/bootparam.h>
 #include <asm/io_apic.h>
@@ -28,6 +29,28 @@
 bool __ro_after_init xen_pvh;
 EXPORT_SYMBOL_GPL(xen_pvh);
 
+#ifdef CONFIG_XEN_DOM0
+int xen_pvh_setup_gsi(int gsi, int trigger, int polarity)
+{
+	int ret;
+	struct physdev_setup_gsi setup_gsi;
+
+	setup_gsi.gsi = gsi;
+	setup_gsi.triggering = (trigger == ACPI_EDGE_SENSITIVE ? 0 : 1);
+	setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+
+	ret = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi);
+	if (ret == -EEXIST) {
+		xen_raw_printk("Already setup the GSI :%d\n", gsi);
+		ret = 0;
+	} else if (ret)
+		xen_raw_printk("Fail to setup GSI (%d)!\n", gsi);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_pvh_setup_gsi);
+#endif
+
 /*
  * Reserve e820 UNUSABLE regions to inflate the memory balloon.
  *

drivers/acpi/pci_irq.c

@@ -288,7 +288,7 @@ static int acpi_reroute_boot_interrupt(struct pci_dev *dev,
 }
 #endif /* CONFIG_X86_IO_APIC */
 
-static struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin)
+struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin)
 {
 	struct acpi_prt_entry *entry = NULL;
 	struct pci_dev *bridge;

drivers/xen/Kconfig

@@ -261,6 +261,7 @@ config XEN_SCSI_BACKEND
 config XEN_PRIVCMD
 	tristate "Xen hypercall passthrough driver"
 	depends on XEN
+	imply CONFIG_XEN_PCIDEV_BACKEND
 	default m
 	help
 	  The hypercall passthrough driver allows privileged user programs to

drivers/xen/acpi.c

@@ -30,6 +30,7 @@
  * IN THE SOFTWARE.
  */
 
+#include <linux/pci.h>
 #include <xen/acpi.h>
 #include <xen/interface/platform.h>
 #include <asm/xen/hypercall.h>
@@ -75,3 +76,52 @@ int xen_acpi_notify_hypervisor_extended_sleep(u8 sleep_state,
 	return xen_acpi_notify_hypervisor_state(sleep_state, val_a,
 						val_b, true);
 }
+
+struct acpi_prt_entry {
+	struct acpi_pci_id      id;
+	u8                      pin;
+	acpi_handle             link;
+	u32                     index;
+};
+
+int xen_acpi_get_gsi_info(struct pci_dev *dev,
+						  int *gsi_out,
+						  int *trigger_out,
+						  int *polarity_out)
+{
+	int gsi;
+	u8 pin;
+	struct acpi_prt_entry *entry;
+	int trigger = ACPI_LEVEL_SENSITIVE;
+	int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ?
+				      ACPI_ACTIVE_HIGH : ACPI_ACTIVE_LOW;
+
+	if (!dev || !gsi_out || !trigger_out || !polarity_out)
+		return -EINVAL;
+
+	pin = dev->pin;
+	if (!pin)
+		return -EINVAL;
+
+	entry = acpi_pci_irq_lookup(dev, pin);
+	if (entry) {
+		if (entry->link)
+			gsi = acpi_pci_link_allocate_irq(entry->link,
+							 entry->index,
+							 &trigger, &polarity,
+							 NULL);
+		else
+			gsi = entry->index;
+	} else
+		gsi = -1;
+
+	if (gsi < 0)
+		return -EINVAL;
+
+	*gsi_out = gsi;
+	*trigger_out = trigger;
+	*polarity_out = polarity;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_acpi_get_gsi_info);

drivers/xen/pci.c

@@ -173,6 +173,19 @@ static int xen_remove_device(struct device *dev)
 	return r;
 }
 
+int xen_reset_device(const struct pci_dev *dev)
+{
+	struct pci_device_reset device = {
+		.dev.seg = pci_domain_nr(dev->bus),
+		.dev.bus = dev->bus->number,
+		.dev.devfn = dev->devfn,
+		.flags = PCI_DEVICE_RESET_FLR,
+	};
+
+	return HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_reset, &device);
+}
+EXPORT_SYMBOL_GPL(xen_reset_device);
+
 static int xen_pci_notifier(struct notifier_block *nb,
 			    unsigned long action, void *data)
 {

drivers/xen/privcmd.c

@@ -46,6 +46,9 @@
 #include <xen/page.h>
 #include <xen/xen-ops.h>
 #include <xen/balloon.h>
+#ifdef CONFIG_XEN_ACPI
+#include <xen/acpi.h>
+#endif
 
 #include "privcmd.h"
 
@@ -844,6 +847,31 @@ static long privcmd_ioctl_mmap_resource(struct file *file,
 	return rc;
 }
 
+static long privcmd_ioctl_pcidev_get_gsi(struct file *file, void __user *udata)
+{
+#if defined(CONFIG_XEN_ACPI)
+	int rc = -EINVAL;
+	struct privcmd_pcidev_get_gsi kdata;
+
+	if (copy_from_user(&kdata, udata, sizeof(kdata)))
+		return -EFAULT;
+
+	if (IS_REACHABLE(CONFIG_XEN_PCIDEV_BACKEND))
+		rc = pcistub_get_gsi_from_sbdf(kdata.sbdf);
+
+	if (rc < 0)
+		return rc;
+
+	kdata.gsi = rc;
+	if (copy_to_user(udata, &kdata, sizeof(kdata)))
+		return -EFAULT;
+
+	return 0;
+#else
+	return -EINVAL;
+#endif
+}
+
 #ifdef CONFIG_XEN_PRIVCMD_EVENTFD
 /* Irqfd support */
 static struct workqueue_struct *irqfd_cleanup_wq;
@@ -1543,6 +1571,10 @@ static long privcmd_ioctl(struct file *file,
 		ret = privcmd_ioctl_ioeventfd(file, udata);
 		break;
 
+	case IOCTL_PRIVCMD_PCIDEV_GET_GSI:
+		ret = privcmd_ioctl_pcidev_get_gsi(file, udata);
+		break;
+
 	default:
 		break;
 	}

drivers/xen/xen-pciback/conf_space_capability.c

@@ -122,7 +122,7 @@ static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value,
 	if (err)
 		goto out;
 
-	new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK);
+	new_state = (__force pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK);
 
 	new_value &= PM_OK_BITS;
 	if ((old_value & PM_OK_BITS) != new_value) {

drivers/xen/xen-pciback/pci_stub.c

@@ -21,6 +21,9 @@
 #include <xen/events.h>
 #include <xen/pci.h>
 #include <xen/xen.h>
+#ifdef CONFIG_XEN_ACPI
+#include <xen/acpi.h>
+#endif
 #include <asm/xen/hypervisor.h>
 #include <xen/interface/physdev.h>
 #include "pciback.h"
@@ -53,6 +56,9 @@ struct pcistub_device {
 
 	struct pci_dev *dev;
 	struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */
+#ifdef CONFIG_XEN_ACPI
+	int gsi;
+#endif
 };
 
 /* Access to pcistub_devices & seized_devices lists and the initialize_devices
@@ -85,10 +91,23 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev)
 
 	kref_init(&psdev->kref);
 	spin_lock_init(&psdev->lock);
+#ifdef CONFIG_XEN_ACPI
+	psdev->gsi = -1;
+#endif
 
 	return psdev;
 }
 
+static int pcistub_reset_device_state(struct pci_dev *dev)
+{
+	__pci_reset_function_locked(dev);
+
+	if (!xen_pv_domain())
+		return xen_reset_device(dev);
+	else
+		return 0;
+}
+
 /* Don't call this directly as it's called by pcistub_device_put */
 static void pcistub_device_release(struct kref *kref)
 {
@@ -107,7 +126,7 @@ static void pcistub_device_release(struct kref *kref)
 	/* Call the reset function which does not take lock as this
 	 * is called from "unbind" which takes a device_lock mutex.
 	 */
-	__pci_reset_function_locked(dev);
+	pcistub_reset_device_state(dev);
 	if (dev_data &&
 	    pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state))
 		dev_info(&dev->dev, "Could not reload PCI state\n");
@@ -207,6 +226,25 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev,
 	return pci_dev;
 }
 
+#ifdef CONFIG_XEN_ACPI
+int pcistub_get_gsi_from_sbdf(unsigned int sbdf)
+{
+	struct pcistub_device *psdev;
+	int domain = (sbdf >> 16) & 0xffff;
+	int bus = PCI_BUS_NUM(sbdf);
+	int slot = PCI_SLOT(sbdf);
+	int func = PCI_FUNC(sbdf);
+
+	psdev = pcistub_device_find(domain, bus, slot, func);
+
+	if (!psdev)
+		return -ENODEV;
+
+	return psdev->gsi;
+}
+EXPORT_SYMBOL_GPL(pcistub_get_gsi_from_sbdf);
+#endif
+
 struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev,
 					    int domain, int bus,
 					    int slot, int func)
@@ -284,7 +322,7 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	 * (so it's ready for the next domain)
 	 */
 	device_lock_assert(&dev->dev);
-	__pci_reset_function_locked(dev);
+	pcistub_reset_device_state(dev);
 
 	dev_data = pci_get_drvdata(dev);
 	ret = pci_load_saved_state(dev, dev_data->pci_saved_state);
@@ -354,11 +392,20 @@ static int pcistub_match(struct pci_dev *dev)
 	return found;
 }
 
-static int pcistub_init_device(struct pci_dev *dev)
+static int pcistub_init_device(struct pcistub_device *psdev)
 {
 	struct xen_pcibk_dev_data *dev_data;
+	struct pci_dev *dev;
+#ifdef CONFIG_XEN_ACPI
+	int gsi, trigger, polarity;
+#endif
 	int err = 0;
 
+	if (!psdev)
+		return -EINVAL;
+
+	dev = psdev->dev;
+
 	dev_dbg(&dev->dev, "initializing...\n");
 
 	/* The PCI backend is not intended to be a module (or to work with
@@ -420,9 +467,26 @@ static int pcistub_init_device(struct pci_dev *dev)
 		dev_err(&dev->dev, "Could not store PCI conf saved state!\n");
 	else {
 		dev_dbg(&dev->dev, "resetting (FLR, D3, etc) the device\n");
-		__pci_reset_function_locked(dev);
+		err = pcistub_reset_device_state(dev);
+		if (err)
+			goto config_release;
 		pci_restore_state(dev);
 	}
+
+#ifdef CONFIG_XEN_ACPI
+	if (xen_initial_domain() && xen_pvh_domain()) {
+		err = xen_acpi_get_gsi_info(dev, &gsi, &trigger, &polarity);
+		if (err) {
+			dev_err(&dev->dev, "Fail to get gsi info!\n");
+			goto config_release;
+		}
+		err = xen_pvh_setup_gsi(gsi, trigger, polarity);
+		if (err)
+			goto config_release;
+		psdev->gsi = gsi;
+	}
+#endif
+
 	/* Now disable the device (this also ensures some private device
 	 * data is setup before we export)
 	 */
@@ -462,7 +526,7 @@ static int __init pcistub_init_devices_late(void)
 
 		spin_unlock_irqrestore(&pcistub_devices_lock, flags);
 
-		err = pcistub_init_device(psdev->dev);
+		err = pcistub_init_device(psdev);
 		if (err) {
 			dev_err(&psdev->dev->dev,
 				"error %d initializing device\n", err);
@@ -532,7 +596,7 @@ static int pcistub_seize(struct pci_dev *dev,
 		spin_unlock_irqrestore(&pcistub_devices_lock, flags);
 
 		/* don't want irqs disabled when calling pcistub_init_device */
-		err = pcistub_init_device(psdev->dev);
+		err = pcistub_init_device(psdev);
 
 		spin_lock_irqsave(&pcistub_devices_lock, flags);
 
@@ -757,7 +821,7 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev,
 	}
 	clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags);
 
-	res = (pci_ers_result_t)aer_op->err;
+	res = (__force pci_ers_result_t)aer_op->err;
 	return res;
 }
 

include/linux/acpi.h

@@ -363,6 +363,7 @@ void acpi_unregister_gsi (u32 gsi);
 
 struct pci_dev;
 
+struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin);
 int acpi_pci_irq_enable (struct pci_dev *dev);
 void acpi_penalize_isa_irq(int irq, int active);
 bool acpi_isa_irq_available(int irq);

include/uapi/xen/privcmd.h

@@ -126,6 +126,11 @@ struct privcmd_ioeventfd {
 	__u8 pad[2];
 };
 
+struct privcmd_pcidev_get_gsi {
+	__u32 sbdf;
+	__u32 gsi;
+};
+
 /*
  * @cmd: IOCTL_PRIVCMD_HYPERCALL
  * @arg: &privcmd_hypercall_t
@@ -157,5 +162,7 @@ struct privcmd_ioeventfd {
 	_IOW('P', 8, struct privcmd_irqfd)
 #define IOCTL_PRIVCMD_IOEVENTFD					\
 	_IOW('P', 9, struct privcmd_ioeventfd)
+#define IOCTL_PRIVCMD_PCIDEV_GET_GSI				\
+	_IOC(_IOC_NONE, 'P', 10, sizeof(struct privcmd_pcidev_get_gsi))
 
 #endif /* __LINUX_PUBLIC_PRIVCMD_H__ */

include/xen/acpi.h

@@ -67,10 +67,37 @@ static inline void xen_acpi_sleep_register(void)
 		acpi_suspend_lowlevel = xen_acpi_suspend_lowlevel;
 	}
 }
+int xen_pvh_setup_gsi(int gsi, int trigger, int polarity);
+int xen_acpi_get_gsi_info(struct pci_dev *dev,
+						  int *gsi_out,
+						  int *trigger_out,
+						  int *polarity_out);
 #else
 static inline void xen_acpi_sleep_register(void)
 {
 }
+
+static inline int xen_pvh_setup_gsi(int gsi, int trigger, int polarity)
+{
+	return -1;
+}
+
+static inline int xen_acpi_get_gsi_info(struct pci_dev *dev,
+						  int *gsi_out,
+						  int *trigger_out,
+						  int *polarity_out)
+{
+	return -1;
+}
+#endif
+
+#ifdef CONFIG_XEN_PCI_STUB
+int pcistub_get_gsi_from_sbdf(unsigned int sbdf);
+#else
+static inline int pcistub_get_gsi_from_sbdf(unsigned int sbdf)
+{
+	return -1;
+}
 #endif
 
 #endif	/* _XEN_ACPI_H */

include/xen/interface/elfnote.h

@@ -11,7 +11,9 @@
 #define __XEN_PUBLIC_ELFNOTE_H__
 
 /*
- * The notes should live in a SHT_NOTE segment and have "Xen" in the
+ * `incontents 200 elfnotes ELF notes
+ *
+ * The notes should live in a PT_NOTE segment and have "Xen" in the
  * name field.
  *
  * Numeric types are either 4 or 8 bytes depending on the content of
@@ -22,6 +24,8 @@
  *
  * String values (for non-legacy) are NULL terminated ASCII, also known
  * as ASCIZ type.
+ *
+ * Xen only uses ELF Notes contained in x86 binaries.
  */
 
 /*
@@ -52,7 +56,7 @@
 #define XEN_ELFNOTE_VIRT_BASE      3
 
 /*
- * The offset of the ELF paddr field from the acutal required
+ * The offset of the ELF paddr field from the actual required
  * pseudo-physical address (numeric).
  *
  * This is used to maintain backwards compatibility with older kernels
@@ -92,7 +96,12 @@
 #define XEN_ELFNOTE_LOADER         8
 
 /*
- * The kernel supports PAE (x86/32 only, string = "yes" or "no").
+ * The kernel supports PAE (x86/32 only, string = "yes", "no" or
+ * "bimodal").
+ *
+ * For compatibility with Xen 3.0.3 and earlier the "bimodal" setting
+ * may be given as "yes,bimodal" which will cause older Xen to treat
+ * this kernel as PAE.
  *
  * LEGACY: PAE (n.b. The legacy interface included a provision to
  * indicate 'extended-cr3' support allowing L3 page tables to be
@@ -149,7 +158,9 @@
  * The (non-default) location the initial phys-to-machine map should be
  * placed at by the hypervisor (Dom0) or the tools (DomU).
  * The kernel must be prepared for this mapping to be established using
- * large pages, despite such otherwise not being available to guests.
+ * large pages, despite such otherwise not being available to guests. Note
+ * that these large pages may be misaligned in PFN space (they'll obviously
+ * be aligned in MFN and virtual address spaces).
  * The kernel must also be able to handle the page table pages used for
  * this mapping not being accessible through the initial mapping.
  * (Only x86-64 supports this at present.)
@@ -185,9 +196,81 @@
  */
 #define XEN_ELFNOTE_PHYS32_ENTRY 18
 
+/*
+ * Physical loading constraints for PVH kernels
+ *
+ * The presence of this note indicates the kernel supports relocating itself.
+ *
+ * The note may include up to three 32bit values to place constraints on the
+ * guest physical loading addresses and alignment for a PVH kernel.  Values
+ * are read in the following order:
+ *  - a required start alignment (default 0x200000)
+ *  - a minimum address for the start of the image (default 0; see below)
+ *  - a maximum address for the last byte of the image (default 0xffffffff)
+ *
+ * When this note specifies an alignment value, it is used.  Otherwise the
+ * maximum p_align value from loadable ELF Program Headers is used, if it is
+ * greater than or equal to 4k (0x1000).  Otherwise, the default is used.
+ */
+#define XEN_ELFNOTE_PHYS32_RELOC 19
+
 /*
  * The number of the highest elfnote defined.
  */
-#define XEN_ELFNOTE_MAX XEN_ELFNOTE_PHYS32_ENTRY
+#define XEN_ELFNOTE_MAX XEN_ELFNOTE_PHYS32_RELOC
+
+/*
+ * System information exported through crash notes.
+ *
+ * The kexec / kdump code will create one XEN_ELFNOTE_CRASH_INFO
+ * note in case of a system crash. This note will contain various
+ * information about the system, see xen/include/xen/elfcore.h.
+ */
+#define XEN_ELFNOTE_CRASH_INFO 0x1000001
+
+/*
+ * System registers exported through crash notes.
+ *
+ * The kexec / kdump code will create one XEN_ELFNOTE_CRASH_REGS
+ * note per cpu in case of a system crash. This note is architecture
+ * specific and will contain registers not saved in the "CORE" note.
+ * See xen/include/xen/elfcore.h for more information.
+ */
+#define XEN_ELFNOTE_CRASH_REGS 0x1000002
+
+
+/*
+ * xen dump-core none note.
+ * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_NONE
+ * in its dump file to indicate that the file is xen dump-core
+ * file. This note doesn't have any other information.
+ * See tools/libxc/xc_core.h for more information.
+ */
+#define XEN_ELFNOTE_DUMPCORE_NONE               0x2000000
+
+/*
+ * xen dump-core header note.
+ * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_HEADER
+ * in its dump file.
+ * See tools/libxc/xc_core.h for more information.
+ */
+#define XEN_ELFNOTE_DUMPCORE_HEADER             0x2000001
+
+/*
+ * xen dump-core xen version note.
+ * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_XEN_VERSION
+ * in its dump file. It contains the xen version obtained via the
+ * XENVER hypercall.
+ * See tools/libxc/xc_core.h for more information.
+ */
+#define XEN_ELFNOTE_DUMPCORE_XEN_VERSION        0x2000002
+
+/*
+ * xen dump-core format version note.
+ * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_FORMAT_VERSION
+ * in its dump file. It contains a format version identifier.
+ * See tools/libxc/xc_core.h for more information.
+ */
+#define XEN_ELFNOTE_DUMPCORE_FORMAT_VERSION     0x2000003
 
 #endif /* __XEN_PUBLIC_ELFNOTE_H__ */

include/xen/interface/physdev.h

@@ -256,6 +256,13 @@ struct physdev_pci_device_add {
  */
 #define PHYSDEVOP_prepare_msix          30
 #define PHYSDEVOP_release_msix          31
+/*
+ * Notify the hypervisor that a PCI device has been reset, so that any
+ * internally cached state is regenerated.  Should be called after any
+ * device reset performed by the hardware domain.
+ */
+#define PHYSDEVOP_pci_device_reset      32
+
 struct physdev_pci_device {
     /* IN */
     uint16_t seg;
@@ -263,6 +270,16 @@ struct physdev_pci_device {
     uint8_t devfn;
 };
 
+struct pci_device_reset {
+    struct physdev_pci_device dev;
+#define PCI_DEVICE_RESET_COLD 0x0
+#define PCI_DEVICE_RESET_WARM 0x1
+#define PCI_DEVICE_RESET_HOT  0x2
+#define PCI_DEVICE_RESET_FLR  0x3
+#define PCI_DEVICE_RESET_MASK 0x3
+    uint32_t flags;
+};
+
 #define PHYSDEVOP_DBGP_RESET_PREPARE    1
 #define PHYSDEVOP_DBGP_RESET_DONE       2
 

include/xen/pci.h

@@ -4,10 +4,16 @@
 #define __XEN_PCI_H__
 
 #if defined(CONFIG_XEN_DOM0)
+int xen_reset_device(const struct pci_dev *dev);
 int xen_find_device_domain_owner(struct pci_dev *dev);
 int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
 int xen_unregister_device_domain_owner(struct pci_dev *dev);
 #else
+static inline int xen_reset_device(const struct pci_dev *dev)
+{
+	return -1;
+}
+
 static inline int xen_find_device_domain_owner(struct pci_dev *dev)
 {
 	return -1;