Merge: Backport huge pfnmap support for significantly faster large mmap'd PCI device BARs

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6638

Backport huge pfnmap support for significantly faster large mmap'd PCI device BARs

JIRA: https://issues.redhat.com/browse/RHEL-73613

 Mapping and unmapping PCI BARs into VM va-space is a common VFIO function when assigning
 a PCIe device to a VM.
 Currently, the mapping requires setting up the BAR-mappings at a native pagesize level,
 e.g., 4K on x86, 64K possible on ARM64.  This is done using PFNMAP support in the kernel,
 as these device pages are not backed by the standard page-struct that system memory is
 mapped under.
 For relatively small to medium sized BARs, the mapping performance isn't too noticeable;
 but with vGPUs and BARs in the gigabyte-size ranges, the map time can become a signficant
 amount of the VM startup time (minutes).

 Upstream resolved this issue by providing huge PFNMAP support -- superpage PFNMAPs;
 2MB, and even 1GB(on x86) pages vs 4K page mappings yields three to ten orders of magnitude speed
 up in the mapping operation, which is quite visible to the VM user of assigned GPUs in
 the guest VM.

 This series backports the core of what upstream did:
   https://lore.kernel.org/all/20240826204353.2228736-1-peterx@redhat.com/
 along with a couple of prior upstream commits which allow these to apply cleanly to RHEL9,
 as well as a couple bug fixes that patchreview identified, and one related commit
 the kernel-mm team requested.

The code can be tested by doing the following (thanks to AlexW for providing this info):
 # echo "func vfio_pci_mmap_huge_fault +p" > /proc/dynamic_debug/control

 Then you'll see things in dmesg like:

 vfio-pci 0000:5e:00.0: vfio_pci_mmap_huge_fault(,order = 9) BAR 0 page offset 0x0: 0x100
 vfio-pci 0000:5e:00.0: vfio_pci_mmap_huge_fault(,order = 9) BAR 0 page offset 0x200: 0x100
 vfio-pci 0000:5e:00.0: vfio_pci_mmap_huge_fault(,order = 9) BAR 0 page offset 0x400: 0x100

 Here we know order 9 is a 2MB PMD mapping on x86.  BAR0 on this device
 is 16MB, so 2MB mappings is the best we can get.  If you have a device
 with at least a 1GB BAR, you should also see:

 vfio-pci 0000:5e:00.0: vfio_pci_mmap_huge_fault(,order = 18) BAR 1 page offset 0x240000: 0x100
 vfio-pci 0000:5e:00.0: vfio_pci_mmap_huge_fault(,order = 18) BAR 1 page offset 0x280000: 0x100
 vfio-pci 0000:5e:00.0: vfio_pci_mmap_huge_fault(,order = 18) BAR 1 page offset 0x2c0000: 0x100

 Again here we know order 18 is 1GB PUD mappings and BAR1 of this device
 is 32GB (NVIDIA A10).

 You'll need to be running at least QEMU 9.2 to get reliable alignment
 for PUD mappings (which neither RHEL-9 or RHEL-10 has atm; they have QEMU-9.1)
 If you see order = 0 mappings for BARs that are at least 2MB, something is wrong.

Omitted-fix: 7223769 ("mm/memory.c: simplify pfnmap_lockdep_assert")

Signed-off-by: Donald Dutile <ddutile@redhat.com>

Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: David Arcari <darcari@redhat.com>
Approved-by: Alex Williamson <alex.williamson@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>
Approved-by: David Hildenbrand <david@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

arch/arm64/Kconfig

@@ -97,6 +97,7 @@ config ARM64
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_RT
 	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT

arch/arm64/include/asm/pgtable.h

@@ -354,6 +354,7 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages)
 /*
  * Select all bits except the pfn
  */
+#define pte_pgprot pte_pgprot
 static inline pgprot_t pte_pgprot(pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
@@ -527,6 +528,14 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 	return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP)));
 }
 
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+#define pmd_special(pte)	(!!((pmd_val(pte) & PTE_SPECIAL)))
+static inline pmd_t pmd_mkspecial(pmd_t pmd)
+{
+	return set_pmd_bit(pmd, __pgprot(PTE_SPECIAL));
+}
+#endif
+
 #define __pmd_to_phys(pmd)	__pte_to_phys(pmd_pte(pmd))
 #define __phys_to_pmd_val(phys)	__phys_to_pte_val(phys)
 #define pmd_pfn(pmd)		((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
@@ -544,6 +553,27 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 #define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
 #define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
+#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
+#define pud_special(pte)	pte_special(pud_pte(pud))
+#define pud_mkspecial(pte)	pte_pud(pte_mkspecial(pud_pte(pud)))
+#endif
+
+#define pmd_pgprot pmd_pgprot
+static inline pgprot_t pmd_pgprot(pmd_t pmd)
+{
+	unsigned long pfn = pmd_pfn(pmd);
+
+	return __pgprot(pmd_val(pfn_pmd(pfn, __pgprot(0))) ^ pmd_val(pmd));
+}
+
+#define pud_pgprot pud_pgprot
+static inline pgprot_t pud_pgprot(pud_t pud)
+{
+	unsigned long pfn = pud_pfn(pud);
+
+	return __pgprot(pud_val(pfn_pud(pfn, __pgprot(0))) ^ pud_val(pud));
+}
+
 static inline void __set_pte_at(struct mm_struct *mm,
 				unsigned long __always_unused addr,
 				pte_t *ptep, pte_t pte, unsigned int nr)

arch/powerpc/include/asm/pgtable.h

@@ -44,6 +44,7 @@ static inline unsigned long pte_pfn(pte_t pte)
 /*
  * Select all bits except the pfn
  */
+#define pte_pgprot pte_pgprot
 static inline pgprot_t pte_pgprot(pte_t pte)
 {
 	unsigned long pte_flags;

arch/s390/include/asm/pgtable.h

@@ -941,6 +941,7 @@ static inline int pte_unused(pte_t pte)
  * young/old accounting is not supported, i.e _PAGE_PROTECT and _PAGE_INVALID
  * must not be set.
  */
+#define pte_pgprot pte_pgprot
 static inline pgprot_t pte_pgprot(pte_t pte)
 {
 	unsigned long pte_flags = pte_val(pte) & _PAGE_CHG_MASK;

arch/s390/pci/pci_mmio.c

@@ -118,12 +118,11 @@ static inline int __memcpy_toio_inuser(void __iomem *dst,
 SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 		const void __user *, user_buffer, size_t, length)
 {
+	struct follow_pfnmap_args args = { };
 	u8 local_buf[64];
 	void __iomem *io_addr;
 	void *buf;
 	struct vm_area_struct *vma;
-	pte_t *ptep;
-	spinlock_t *ptl;
 	long ret;
 
 	if (!zpci_is_enabled())
@@ -169,19 +168,21 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 	if (!(vma->vm_flags & VM_WRITE))
 		goto out_unlock_mmap;
 
-	ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl);
+	args.address = mmio_addr;
+	args.vma = vma;
+	ret = follow_pfnmap_start(&args);
 	if (ret)
 		goto out_unlock_mmap;
 
-	io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) |
+	io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) |
 			(mmio_addr & ~PAGE_MASK));
 
 	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
 		goto out_unlock_pt;
 
 	ret = zpci_memcpy_toio(io_addr, buf, length);
 out_unlock_pt:
-	pte_unmap_unlock(ptep, ptl);
+	follow_pfnmap_end(&args);
 out_unlock_mmap:
 	mmap_read_unlock(current->mm);
 out_free:
@@ -260,12 +261,11 @@ static inline int __memcpy_fromio_inuser(void __user *dst,
 SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 		void __user *, user_buffer, size_t, length)
 {
+	struct follow_pfnmap_args args = { };
 	u8 local_buf[64];
 	void __iomem *io_addr;
 	void *buf;
 	struct vm_area_struct *vma;
-	pte_t *ptep;
-	spinlock_t *ptl;
 	long ret;
 
 	if (!zpci_is_enabled())
@@ -308,11 +308,13 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 	if (!(vma->vm_flags & VM_WRITE))
 		goto out_unlock_mmap;
 
-	ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl);
+	args.vma = vma;
+	args.address = mmio_addr;
+	ret = follow_pfnmap_start(&args);
 	if (ret)
 		goto out_unlock_mmap;
 
-	io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) |
+	io_addr = (void __iomem *)((args.pfn << PAGE_SHIFT) |
 			(mmio_addr & ~PAGE_MASK));
 
 	if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) {
@@ -322,7 +324,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 	ret = zpci_memcpy_fromio(buf, io_addr, length);
 
 out_unlock_pt:
-	pte_unmap_unlock(ptep, ptl);
+	follow_pfnmap_end(&args);
 out_unlock_mmap:
 	mmap_read_unlock(current->mm);
 

arch/sparc/include/asm/pgtable_64.h

@@ -782,6 +782,7 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 
+#define pmd_pgprot pmd_pgprot
 static inline pgprot_t pmd_pgprot(pmd_t entry)
 {
 	unsigned long val = pmd_val(entry);

arch/x86/Kconfig

@@ -28,6 +28,7 @@ config X86_64
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_SUPPORTS_PER_VMA_LOCK
+	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_RT
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA

arch/x86/include/asm/pgtable.h

@@ -121,6 +121,34 @@ extern pmdval_t early_pmd_flags;
 #define arch_end_context_switch(prev)	do {} while(0)
 #endif	/* CONFIG_PARAVIRT_XXL */
 
+static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
+{
+	pmdval_t v = native_pmd_val(pmd);
+
+	return native_make_pmd(v | set);
+}
+
+static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
+{
+	pmdval_t v = native_pmd_val(pmd);
+
+	return native_make_pmd(v & ~clear);
+}
+
+static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return native_make_pud(v | set);
+}
+
+static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return native_make_pud(v & ~clear);
+}
+
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
@@ -310,6 +338,30 @@ static inline int pud_devmap(pud_t pud)
 }
 #endif
 
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+static inline bool pmd_special(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_SPECIAL;
+}
+
+static inline pmd_t pmd_mkspecial(pmd_t pmd)
+{
+	return pmd_set_flags(pmd, _PAGE_SPECIAL);
+}
+#endif	/* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */
+
+#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
+static inline bool pud_special(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_SPECIAL;
+}
+
+static inline pud_t pud_mkspecial(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_SPECIAL);
+}
+#endif	/* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */
+
 static inline int pgd_devmap(pgd_t pgd)
 {
 	return 0;
@@ -480,20 +532,6 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP);
 }
 
-static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
-{
-	pmdval_t v = native_pmd_val(pmd);
-
-	return native_make_pmd(v | set);
-}
-
-static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
-{
-	pmdval_t v = native_pmd_val(pmd);
-
-	return native_make_pmd(v & ~clear);
-}
-
 /* See comments above mksaveddirty_shift() */
 static inline pmd_t pmd_mksaveddirty(pmd_t pmd)
 {
@@ -588,20 +626,6 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
 pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 #define pmd_mkwrite pmd_mkwrite
 
-static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
-{
-	pudval_t v = native_pud_val(pud);
-
-	return native_make_pud(v | set);
-}
-
-static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
-{
-	pudval_t v = native_pud_val(pud);
-
-	return native_make_pud(v & ~clear);
-}
-
 /* See comments above mksaveddirty_shift() */
 static inline pud_t pud_mksaveddirty(pud_t pud)
 {

arch/x86/mm/pat/memtype.c

@@ -39,6 +39,7 @@
 #include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 #include <linux/fs.h>
 #include <linux/rbtree.h>
 
@@ -947,6 +948,26 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 		memtype_free(paddr, paddr + size);
 }
 
+static int follow_phys(struct vm_area_struct *vma, unsigned long *prot,
+		resource_size_t *phys)
+{
+	struct follow_pfnmap_args args = { .vma = vma, .address = vma->vm_start };
+
+	if (follow_pfnmap_start(&args))
+		return -EINVAL;
+
+	/* Never return PFNs of anon folios in COW mappings. */
+	if (!args.special) {
+		follow_pfnmap_end(&args);
+		return -EINVAL;
+	}
+
+	*prot = pgprot_val(args.pgprot);
+	*phys = (resource_size_t)args.pfn << PAGE_SHIFT;
+	follow_pfnmap_end(&args);
+	return 0;
+}
+
 static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
 		pgprot_t *pgprot)
 {
@@ -964,7 +985,7 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
 	 * detect the PFN. If we need the cachemode as well, we're out of luck
 	 * for now and have to fail fork().
 	 */
-	if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+	if (!follow_phys(vma, &prot, paddr)) {
 		if (pgprot)
 			*pgprot = __pgprot(prot);
 		return 0;