Merge tag 'for-linus-6.12-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - fix a boot problem as a Xen dom0 on some AMD systems

 - fix Xen PVH boot problems with KASAN enabled

 - fix for a build warning

 - fixes to swiotlb-xen

* tag 'for-linus-6.12-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/swiotlb: fix allocated size
  xen/swiotlb: add alignment check for dma buffers
  xen/pci: Avoid -Wflex-array-member-not-at-end warning
  xen/xenbus: Convert to use ERR_CAST()
  xen, pvh: fix unbootable VMs by inlining memset() in xen_prepare_pvh()
  x86/cpu: fix unbootable VMs by inlining memcmp() in hypervisor_cpuid_base()
  xen, pvh: fix unbootable VMs (PVH + KASAN - AMD_MEM_ENCRYPT)
  xen: tolerate ACPI NVS memory overlapping with Xen allocated memory
  xen: allow mapping ACPI data using a different physical address
  xen: add capability to remap non-RAM pages to different PFNs
  xen: move max_pfn in xen_memory_setup() out of function scope
  xen: move checks for e820 conflicts further up
  xen: introduce generic helper checking for memory map conflicts
  xen: use correct end address of kernel for conflict checking

arch/x86/include/asm/acpi.h

@@ -174,6 +174,14 @@ void acpi_generic_reduced_hw_init(void);
 void x86_default_set_root_pointer(u64 addr);
 u64 x86_default_get_root_pointer(void);
 
+#ifdef CONFIG_XEN_PV
+/* A Xen PV domain needs a special acpi_os_ioremap() handling. */
+extern void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys,
+					 acpi_size size);
+void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
+#define acpi_os_ioremap acpi_os_ioremap
+#endif
+
 #else /* !CONFIG_ACPI */
 
 #define acpi_lapic 0

arch/x86/include/asm/cpuid.h

@@ -196,7 +196,12 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 	for_each_possible_hypervisor_cpuid_base(base) {
 		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
 
-		if (!memcmp(sig, signature, 12) &&
+		/*
+		 * This must not compile to "call memcmp" because it's called
+		 * from PVH early boot code before instrumentation is set up
+		 * and memcmp() itself may be instrumented.
+		 */
+		if (!__builtin_memcmp(sig, signature, 12) &&
 		    (leaves == 0 || ((eax - base) >= leaves)))
 			return base;
 	}

arch/x86/kernel/acpi/boot.c

@@ -1778,3 +1778,14 @@ u64 x86_default_get_root_pointer(void)
 {
 	return boot_params.acpi_rsdp_addr;
 }
+
+#ifdef CONFIG_XEN_PV
+void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
+{
+	return ioremap_cache(phys, size);
+}
+
+void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, acpi_size size) =
+	x86_acpi_os_ioremap;
+EXPORT_SYMBOL_GPL(acpi_os_ioremap);
+#endif

arch/x86/kernel/jailhouse.c

@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/reboot.h>
 #include <linux/serial_8250.h>
+#include <linux/acpi.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
 #include <asm/acpi.h>

arch/x86/kernel/mmconf-fam10h_64.c

@@ -9,6 +9,7 @@
 #include <linux/pci.h>
 #include <linux/dmi.h>
 #include <linux/range.h>
+#include <linux/acpi.h>
 
 #include <asm/pci-direct.h>
 #include <linux/sort.h>

arch/x86/kernel/smpboot.c

@@ -60,6 +60,7 @@
 #include <linux/stackprotector.h>
 #include <linux/cpuhotplug.h>
 #include <linux/mc146818rtc.h>
+#include <linux/acpi.h>
 
 #include <asm/acpi.h>
 #include <asm/cacheinfo.h>

arch/x86/kernel/x86_init.c

@@ -8,6 +8,7 @@
 #include <linux/ioport.h>
 #include <linux/export.h>
 #include <linux/pci.h>
+#include <linux/acpi.h>
 
 #include <asm/acpi.h>
 #include <asm/bios_ebda.h>

arch/x86/platform/pvh/Makefile

 # SPDX-License-Identifier: GPL-2.0
 OBJECT_FILES_NON_STANDARD_head.o := y
+KASAN_SANITIZE := n
 
 obj-$(CONFIG_PVH) += enlighten.o
 obj-$(CONFIG_PVH) += head.o

arch/x86/platform/pvh/enlighten.c

@@ -130,7 +130,11 @@ void __init xen_prepare_pvh(void)
 		BUG();
 	}
 
-	memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
+	/*
+	 * This must not compile to "call memset" because memset() may be
+	 * instrumented.
+	 */
+	__builtin_memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
 
 	hypervisor_specific_init(xen_guest);
 

arch/x86/xen/mmu_pv.c

@@ -2018,10 +2018,7 @@ void __init xen_reserve_special_pages(void)
 
 void __init xen_pt_check_e820(void)
 {
-	if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) {
-		xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n");
-		BUG();
-	}
+	xen_chk_is_e820_usable(xen_pt_base, xen_pt_size, "page table");
 }
 
 static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;

arch/x86/xen/p2m.c

@@ -70,6 +70,7 @@
 #include <linux/memblock.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/acpi.h>
 
 #include <asm/cache.h>
 #include <asm/setup.h>
@@ -80,6 +81,7 @@
 #include <asm/xen/hypervisor.h>
 #include <xen/balloon.h>
 #include <xen/grant_table.h>
+#include <xen/hvc-console.h>
 
 #include "xen-ops.h"
 
@@ -792,6 +794,102 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 	return ret;
 }
 
+/* Remapped non-RAM areas */
+#define NR_NONRAM_REMAP 4
+static struct nonram_remap {
+	phys_addr_t maddr;
+	phys_addr_t paddr;
+	size_t size;
+} xen_nonram_remap[NR_NONRAM_REMAP] __ro_after_init;
+static unsigned int nr_nonram_remap __ro_after_init;
+
+/*
+ * Do the real remapping of non-RAM regions as specified in the
+ * xen_nonram_remap[] array.
+ * In case of an error just crash the system.
+ */
+void __init xen_do_remap_nonram(void)
+{
+	unsigned int i;
+	unsigned int remapped = 0;
+	const struct nonram_remap *remap = xen_nonram_remap;
+	unsigned long pfn, mfn, end_pfn;
+
+	for (i = 0; i < nr_nonram_remap; i++) {
+		end_pfn = PFN_UP(remap->paddr + remap->size);
+		pfn = PFN_DOWN(remap->paddr);
+		mfn = PFN_DOWN(remap->maddr);
+		while (pfn < end_pfn) {
+			if (!set_phys_to_machine(pfn, mfn))
+				panic("Failed to set p2m mapping for pfn=%lx mfn=%lx\n",
+				       pfn, mfn);
+
+			pfn++;
+			mfn++;
+			remapped++;
+		}
+
+		remap++;
+	}
+
+	pr_info("Remapped %u non-RAM page(s)\n", remapped);
+}
+
+#ifdef CONFIG_ACPI
+/*
+ * Xen variant of acpi_os_ioremap() taking potentially remapped non-RAM
+ * regions into account.
+ * Any attempt to map an area crossing a remap boundary will produce a
+ * WARN() splat.
+ * phys is related to remap->maddr on input and will be rebased to remap->paddr.
+ */
+static void __iomem *xen_acpi_os_ioremap(acpi_physical_address phys,
+					 acpi_size size)
+{
+	unsigned int i;
+	const struct nonram_remap *remap = xen_nonram_remap;
+
+	for (i = 0; i < nr_nonram_remap; i++) {
+		if (phys + size > remap->maddr &&
+		    phys < remap->maddr + remap->size) {
+			WARN_ON(phys < remap->maddr ||
+				phys + size > remap->maddr + remap->size);
+			phys += remap->paddr - remap->maddr;
+			break;
+		}
+	}
+
+	return x86_acpi_os_ioremap(phys, size);
+}
+#endif /* CONFIG_ACPI */
+
+/*
+ * Add a new non-RAM remap entry.
+ * In case of no free entry found, just crash the system.
+ */
+void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr,
+				 unsigned long size)
+{
+	BUG_ON((maddr & ~PAGE_MASK) != (paddr & ~PAGE_MASK));
+
+	if (nr_nonram_remap == NR_NONRAM_REMAP) {
+		xen_raw_console_write("Number of required E820 entry remapping actions exceed maximum value\n");
+		BUG();
+	}
+
+#ifdef CONFIG_ACPI
+	/* Switch to the Xen acpi_os_ioremap() variant. */
+	if (nr_nonram_remap == 0)
+		acpi_os_ioremap = xen_acpi_os_ioremap;
+#endif
+
+	xen_nonram_remap[nr_nonram_remap].maddr = maddr;
+	xen_nonram_remap[nr_nonram_remap].paddr = paddr;
+	xen_nonram_remap[nr_nonram_remap].size = size;
+
+	nr_nonram_remap++;
+}
+
 #ifdef CONFIG_XEN_DEBUG_FS
 #include <linux/debugfs.h>
 static int p2m_dump_show(struct seq_file *m, void *v)

arch/x86/xen/xen-ops.h

@@ -47,8 +47,12 @@ void xen_mm_unpin_all(void);
 #ifdef CONFIG_X86_64
 void __init xen_relocate_p2m(void);
 #endif
+void __init xen_do_remap_nonram(void);
+void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr,
+				 unsigned long size);
 
-bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size);
+void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size,
+				   const char *component);
 unsigned long __ref xen_chk_extra_mem(unsigned long pfn);
 void __init xen_inv_extra_mem(void);
 void __init xen_remap_memory(void);

drivers/xen/pci.c

@@ -44,15 +44,11 @@ static int xen_add_device(struct device *dev)
 	}
 #endif
 	if (pci_seg_supported) {
-		struct {
-			struct physdev_pci_device_add add;
-			uint32_t pxm;
-		} add_ext = {
-			.add.seg = pci_domain_nr(pci_dev->bus),
-			.add.bus = pci_dev->bus->number,
-			.add.devfn = pci_dev->devfn
-		};
-		struct physdev_pci_device_add *add = &add_ext.add;
+		DEFINE_RAW_FLEX(struct physdev_pci_device_add, add, optarr, 1);
+
+		add->seg = pci_domain_nr(pci_dev->bus);
+		add->bus = pci_dev->bus->number;
+		add->devfn = pci_dev->devfn;
 
 #ifdef CONFIG_ACPI
 		acpi_handle handle;

drivers/xen/swiotlb-xen.c

@@ -78,9 +78,15 @@ static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
 {
 	unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p);
 	unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size);
+	phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT);
 
 	next_bfn = pfn_to_bfn(xen_pfn);
 
+	/* If buffer is physically aligned, ensure DMA alignment. */
+	if (IS_ALIGNED(p, algn) &&
+	    !IS_ALIGNED((phys_addr_t)next_bfn << XEN_PAGE_SHIFT, algn))
+		return 1;
+
 	for (i = 1; i < nr_pages; i++)
 		if (pfn_to_bfn(++xen_pfn) != ++next_bfn)
 			return 1;
@@ -141,7 +147,7 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size,
 	void *ret;
 
 	/* Align the allocation to the Xen page size */
-	size = 1UL << (order + XEN_PAGE_SHIFT);
+	size = ALIGN(size, XEN_PAGE_SIZE);
 
 	ret = (void *)__get_free_pages(flags, get_order(size));
 	if (!ret)
@@ -173,7 +179,7 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr,
 	int order = get_order(size);
 
 	/* Convert the size to actually allocated. */
-	size = 1UL << (order + XEN_PAGE_SHIFT);
+	size = ALIGN(size, XEN_PAGE_SIZE);
 
 	if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) ||
 	    WARN_ON_ONCE(range_straddles_page_boundary(phys, size)))

drivers/xen/xenbus/xenbus_xs.c

@@ -427,12 +427,12 @@ char **xenbus_directory(struct xenbus_transaction t,
 
 	path = join(dir, node);
 	if (IS_ERR(path))
-		return (char **)path;
+		return ERR_CAST(path);
 
 	strings = xs_single(t, XS_DIRECTORY, path, &len);
 	kfree(path);
 	if (IS_ERR(strings))
-		return (char **)strings;
+		return ERR_CAST(strings);
 
 	return split(strings, len, num);
 }
@@ -465,7 +465,7 @@ void *xenbus_read(struct xenbus_transaction t,
 
 	path = join(dir, node);
 	if (IS_ERR(path))
-		return (void *)path;
+		return ERR_CAST(path);
 
 	ret = xs_single(t, XS_READ, path, len);
 	kfree(path);