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

Author: torvalds

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>
@@ -54,22 +56,40 @@ 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
 	mov %eax,%es
 	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