summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-05-19 09:21:03 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2024-05-19 09:21:03 -0700
commit61307b7be41a1f1039d1d1368810a1d92cb97b44 (patch)
tree639e233e177f8618cd5f86daeb7efc6b095890f0 /arch/x86
parent0450d2083be6bdcd18c9535ac50c55266499b2df (diff)
parent76edc534cc289308130272a2ac28694fc9b72a03 (diff)
Merge tag 'mm-stable-2024-05-17-19-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull mm updates from Andrew Morton: "The usual shower of singleton fixes and minor series all over MM, documented (hopefully adequately) in the respective changelogs. Notable series include: - Lucas Stach has provided some page-mapping cleanup/consolidation/ maintainability work in the series "mm/treewide: Remove pXd_huge() API". - In the series "Allow migrate on protnone reference with MPOL_PREFERRED_MANY policy", Donet Tom has optimized mempolicy's MPOL_PREFERRED_MANY mode, yielding almost doubled performance in one test. - In their series "Memory allocation profiling" Kent Overstreet and Suren Baghdasaryan have contributed a means of determining (via /proc/allocinfo) whereabouts in the kernel memory is being allocated: number of calls and amount of memory. - Matthew Wilcox has provided the series "Various significant MM patches" which does a number of rather unrelated things, but in largely similar code sites. - In his series "mm: page_alloc: freelist migratetype hygiene" Johannes Weiner has fixed the page allocator's handling of migratetype requests, with resulting improvements in compaction efficiency. - In the series "make the hugetlb migration strategy consistent" Baolin Wang has fixed a hugetlb migration issue, which should improve hugetlb allocation reliability. - Liu Shixin has hit an I/O meltdown caused by readahead in a memory-tight memcg. Addressed in the series "Fix I/O high when memory almost met memcg limit". - In the series "mm/filemap: optimize folio adding and splitting" Kairui Song has optimized pagecache insertion, yielding ~10% performance improvement in one test. - Baoquan He has cleaned up and consolidated the early zone initialization code in the series "mm/mm_init.c: refactor free_area_init_core()". - Baoquan has also redone some MM initializatio code in the series "mm/init: minor clean up and improvement". - MM helper cleanups from Christoph Hellwig in his series "remove follow_pfn". - More cleanups from Matthew Wilcox in the series "Various page->flags cleanups". - Vlastimil Babka has contributed maintainability improvements in the series "memcg_kmem hooks refactoring". - More folio conversions and cleanups in Matthew Wilcox's series: "Convert huge_zero_page to huge_zero_folio" "khugepaged folio conversions" "Remove page_idle and page_young wrappers" "Use folio APIs in procfs" "Clean up __folio_put()" "Some cleanups for memory-failure" "Remove page_mapping()" "More folio compat code removal" - David Hildenbrand chipped in with "fs/proc/task_mmu: convert hugetlb functions to work on folis". - Code consolidation and cleanup work related to GUP's handling of hugetlbs in Peter Xu's series "mm/gup: Unify hugetlb, part 2". - Rick Edgecombe has developed some fixes to stack guard gaps in the series "Cover a guard gap corner case". - Jinjiang Tu has fixed KSM's behaviour after a fork+exec in the series "mm/ksm: fix ksm exec support for prctl". - Baolin Wang has implemented NUMA balancing for multi-size THPs. This is a simple first-cut implementation for now. The series is "support multi-size THP numa balancing". - Cleanups to vma handling helper functions from Matthew Wilcox in the series "Unify vma_address and vma_pgoff_address". - Some selftests maintenance work from Dev Jain in the series "selftests/mm: mremap_test: Optimizations and style fixes". - Improvements to the swapping of multi-size THPs from Ryan Roberts in the series "Swap-out mTHP without splitting". - Kefeng Wang has significantly optimized the handling of arm64's permission page faults in the series "arch/mm/fault: accelerate pagefault when badaccess" "mm: remove arch's private VM_FAULT_BADMAP/BADACCESS" - GUP cleanups from David Hildenbrand in "mm/gup: consistently call it GUP-fast". - hugetlb fault code cleanups from Vishal Moola in "Hugetlb fault path to use struct vm_fault". - selftests build fixes from John Hubbard in the series "Fix selftests/mm build without requiring "make headers"". - Memory tiering fixes/improvements from Ho-Ren (Jack) Chuang in the series "Improved Memory Tier Creation for CPUless NUMA Nodes". Fixes the initialization code so that migration between different memory types works as intended. - David Hildenbrand has improved follow_pte() and fixed an errant driver in the series "mm: follow_pte() improvements and acrn follow_pte() fixes". - David also did some cleanup work on large folio mapcounts in his series "mm: mapcount for large folios + page_mapcount() cleanups". - Folio conversions in KSM in Alex Shi's series "transfer page to folio in KSM". - Barry Song has added some sysfs stats for monitoring multi-size THP's in the series "mm: add per-order mTHP alloc and swpout counters". - Some zswap cleanups from Yosry Ahmed in the series "zswap same-filled and limit checking cleanups". - Matthew Wilcox has been looking at buffer_head code and found the documentation to be lacking. The series is "Improve buffer head documentation". - Multi-size THPs get more work, this time from Lance Yang. His series "mm/madvise: enhance lazyfreeing with mTHP in madvise_free" optimizes the freeing of these things. - Kemeng Shi has added more userspace-visible writeback instrumentation in the series "Improve visibility of writeback". - Kemeng Shi then sent some maintenance work on top in the series "Fix and cleanups to page-writeback". - Matthew Wilcox reduces mmap_lock traffic in the anon vma code in the series "Improve anon_vma scalability for anon VMAs". Intel's test bot reported an improbable 3x improvement in one test. - SeongJae Park adds some DAMON feature work in the series "mm/damon: add a DAMOS filter type for page granularity access recheck" "selftests/damon: add DAMOS quota goal test" - Also some maintenance work in the series "mm/damon/paddr: simplify page level access re-check for pageout" "mm/damon: misc fixes and improvements" - David Hildenbrand has disabled some known-to-fail selftests ni the series "selftests: mm: cow: flag vmsplice() hugetlb tests as XFAIL". - memcg metadata storage optimizations from Shakeel Butt in "memcg: reduce memory consumption by memcg stats". - DAX fixes and maintenance work from Vishal Verma in the series "dax/bus.c: Fixups for dax-bus locking"" * tag 'mm-stable-2024-05-17-19-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (426 commits) memcg, oom: cleanup unused memcg_oom_gfp_mask and memcg_oom_order selftests/mm: hugetlb_madv_vs_map: avoid test skipping by querying hugepage size at runtime mm/hugetlb: add missing VM_FAULT_SET_HINDEX in hugetlb_wp mm/hugetlb: add missing VM_FAULT_SET_HINDEX in hugetlb_fault selftests: cgroup: add tests to verify the zswap writeback path mm: memcg: make alloc_mem_cgroup_per_node_info() return bool mm/damon/core: fix return value from damos_wmark_metric_value mm: do not update memcg stats for NR_{FILE/SHMEM}_PMDMAPPED selftests: cgroup: remove redundant enabling of memory controller Docs/mm/damon/maintainer-profile: allow posting patches based on damon/next tree Docs/mm/damon/maintainer-profile: change the maintainer's timezone from PST to PT Docs/mm/damon/design: use a list for supported filters Docs/admin-guide/mm/damon/usage: fix wrong schemes effective quota update command Docs/admin-guide/mm/damon/usage: fix wrong example of DAMOS filter matching sysfs file selftests/damon: classify tests for functionalities and regressions selftests/damon/_damon_sysfs: use 'is' instead of '==' for 'None' selftests/damon/_damon_sysfs: find sysfs mount point from /proc/mounts selftests/damon/_damon_sysfs: check errors from nr_schemes file reads mm/damon/core: initialize ->esz_bp from damos_quota_init_priv() selftests/damon: add a test for DAMOS quota goal ...
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/include/asm/io.h1
-rw-r--r--arch/x86/include/asm/pgtable.h20
-rw-r--r--arch/x86/include/asm/pgtable_64.h1
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/cpu/sgx/driver.c2
-rw-r--r--arch/x86/kernel/cpu/sgx/main.c1
-rw-r--r--arch/x86/kernel/irq_64.c1
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/sys_x86_64.c42
-rw-r--r--arch/x86/mm/fault.c24
-rw-r--r--arch/x86/mm/hugetlbpage.c35
-rw-r--r--arch/x86/mm/init.c47
-rw-r--r--arch/x86/mm/mmap.c4
-rw-r--r--arch/x86/mm/numa_32.c1
-rw-r--r--arch/x86/mm/pat/memtype.c26
-rw-r--r--arch/x86/mm/pgtable.c6
17 files changed, 91 insertions, 126 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bc47bc9841ff..671bc6fd557c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -224,7 +224,7 @@ config X86
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_EISA
select HAVE_EXIT_THREAD
- select HAVE_FAST_GUP
+ select HAVE_GUP_FAST
select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 4b99ed326b17..1d60427379c9 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -42,6 +42,7 @@
#include <asm/early_ioremap.h>
#include <asm/pgtable_types.h>
#include <asm/shared/io.h>
+#include <asm/special_insns.h>
#define build_mmio_read(name, size, type, reg, barrier) \
static inline type name(const volatile void __iomem *addr) \
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 315535ffb258..65b8e5bb902c 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -234,6 +234,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
}
+#define pud_pfn pud_pfn
static inline unsigned long pud_pfn(pud_t pud)
{
phys_addr_t pfn = pud_val(pud);
@@ -387,23 +388,7 @@ static inline pte_t pte_wrprotect(pte_t pte)
#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
static inline int pte_uffd_wp(pte_t pte)
{
- bool wp = pte_flags(pte) & _PAGE_UFFD_WP;
-
-#ifdef CONFIG_DEBUG_VM
- /*
- * Having write bit for wr-protect-marked present ptes is fatal,
- * because it means the uffd-wp bit will be ignored and write will
- * just go through.
- *
- * Use any chance of pgtable walking to verify this (e.g., when
- * page swapped out or being migrated for all purposes). It means
- * something is already wrong. Tell the admin even before the
- * process crashes. We also nail it with wrong pgtable setup.
- */
- WARN_ON_ONCE(wp && pte_write(pte));
-#endif
-
- return wp;
+ return pte_flags(pte) & _PAGE_UFFD_WP;
}
static inline pte_t pte_mkuffd_wp(pte_t pte)
@@ -1200,7 +1185,6 @@ static inline int pgd_none(pgd_t pgd)
extern int direct_gbpages;
void init_mem_mapping(void);
void early_alloc_pgt_buf(void);
-extern void memblock_find_dma_reserve(void);
void __init poking_init(void);
unsigned long init_memory_mapping(unsigned long start,
unsigned long end, pgprot_t prot);
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 7e9db77231ac..3c4407271d08 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -245,6 +245,7 @@ extern void cleanup_highmap(void);
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS
#define PAGE_AGP PAGE_KERNEL_NOCACHE
#define HAVE_PAGE_AGP 1
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 2ae98f754e59..c884deca839b 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -676,7 +676,7 @@ static const struct dma_map_ops gart_dma_ops = {
.get_sgtable = dma_common_get_sgtable,
.dma_supported = dma_direct_supported,
.get_required_mask = dma_direct_get_required_mask,
- .alloc_pages = dma_direct_alloc_pages,
+ .alloc_pages_op = dma_direct_alloc_pages,
.free_pages = dma_direct_free_pages,
};
diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index 262f5fb18d74..22b65a5f5ec6 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -113,7 +113,7 @@ static unsigned long sgx_get_unmapped_area(struct file *file,
if (flags & MAP_FIXED)
return addr;
- return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+ return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags);
}
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 166692f2d501..27892e57c4ef 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -13,6 +13,7 @@
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
#include <asm/sgx.h>
#include "driver.h"
#include "encl.h"
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index fe0c859873d1..ade0043ce56e 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,6 +18,7 @@
#include <linux/uaccess.h>
#include <linux/smp.h>
#include <linux/sched/task_stack.h>
+#include <linux/vmalloc.h>
#include <asm/cpu_entry_area.h>
#include <asm/softirq_stack.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 55a1fc332e20..05c5aa951da7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1108,8 +1108,6 @@ void __init setup_arch(char **cmdline_p)
*/
arch_reserve_crashkernel();
- memblock_find_dma_reserve();
-
if (!early_xdbc_setup_hardware())
early_xdbc_register_console();
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index cb9fa1d5c66f..01d7cd85ef97 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -112,13 +112,21 @@ static void find_start_end(unsigned long addr, unsigned long flags,
*end = task_size_64bit(addr > DEFAULT_MAP_WINDOW);
}
+static inline unsigned long stack_guard_placement(vm_flags_t vm_flags)
+{
+ if (vm_flags & VM_SHADOW_STACK)
+ return PAGE_SIZE;
+
+ return 0;
+}
+
unsigned long
-arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff, unsigned long flags)
+arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
unsigned long begin, end;
if (flags & MAP_FIXED)
@@ -137,12 +145,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
return addr;
}
- info.flags = 0;
info.length = len;
info.low_limit = begin;
info.high_limit = end;
- info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
+ info.start_gap = stack_guard_placement(vm_flags);
if (filp) {
info.align_mask = get_align_mask();
info.align_offset += get_align_bits();
@@ -151,14 +158,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
}
unsigned long
-arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- const unsigned long len, const unsigned long pgoff,
- const unsigned long flags)
+arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags, vm_flags_t vm_flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
/* requested length too big for entire address space */
if (len > TASK_SIZE)
@@ -192,6 +199,7 @@ get_unmapped_area:
info.low_limit = PAGE_SIZE;
info.high_limit = get_mmap_base(0);
+ info.start_gap = stack_guard_placement(vm_flags);
/*
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
@@ -203,7 +211,6 @@ get_unmapped_area:
if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
- info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (filp) {
info.align_mask = get_align_mask();
@@ -223,3 +230,18 @@ bottomup:
*/
return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}
+
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0);
+}
+
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
+ const unsigned long len, const unsigned long pgoff,
+ const unsigned long flags)
+{
+ return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0);
+}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f26ecabc9424..e6c469b323cc 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -20,6 +20,7 @@
#include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/
#include <linux/mm_types.h>
#include <linux/mm.h> /* find_and_lock_vma() */
+#include <linux/vmalloc.h>
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
#include <asm/traps.h> /* dotraplinkage, ... */
@@ -835,14 +836,17 @@ bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
static void
__bad_area(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, u32 pkey, int si_code)
+ unsigned long address, struct mm_struct *mm,
+ struct vm_area_struct *vma, u32 pkey, int si_code)
{
- struct mm_struct *mm = current->mm;
/*
* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
- mmap_read_unlock(mm);
+ if (mm)
+ mmap_read_unlock(mm);
+ else
+ vma_end_read(vma);
__bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
}
@@ -866,7 +870,8 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code,
static noinline void
bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma)
+ unsigned long address, struct mm_struct *mm,
+ struct vm_area_struct *vma)
{
/*
* This OSPKE check is not strictly necessary at runtime.
@@ -896,9 +901,9 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
*/
u32 pkey = vma_pkey(vma);
- __bad_area(regs, error_code, address, pkey, SEGV_PKUERR);
+ __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR);
} else {
- __bad_area(regs, error_code, address, 0, SEGV_ACCERR);
+ __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR);
}
}
@@ -1326,8 +1331,9 @@ void do_user_addr_fault(struct pt_regs *regs,
goto lock_mmap;
if (unlikely(access_error(error_code, vma))) {
- vma_end_read(vma);
- goto lock_mmap;
+ bad_area_access_error(regs, error_code, address, NULL, vma);
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ return;
}
fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
@@ -1363,7 +1369,7 @@ retry:
* we can handle it..
*/
if (unlikely(access_error(error_code, vma))) {
- bad_area_access_error(regs, error_code, address, vma);
+ bad_area_access_error(regs, error_code, address, mm, vma);
return;
}
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 5804bbae4f01..807a5859a3c4 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -19,41 +19,14 @@
#include <asm/tlbflush.h>
#include <asm/elf.h>
-/*
- * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
- * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
- * Otherwise, returns 0.
- */
-int pmd_huge(pmd_t pmd)
-{
- return !pmd_none(pmd) &&
- (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
-}
-
-/*
- * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal
- * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
- * Otherwise, returns 0.
- */
-int pud_huge(pud_t pud)
-{
-#if CONFIG_PGTABLE_LEVELS > 2
- return !pud_none(pud) &&
- (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
-#else
- return 0;
-#endif
-}
-
#ifdef CONFIG_HUGETLB_PAGE
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
- info.flags = 0;
info.length = len;
info.low_limit = get_mmap_base(1);
@@ -65,7 +38,6 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW);
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
return vm_unmapped_area(&info);
}
@@ -74,7 +46,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
@@ -89,7 +61,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
addr = vm_unmapped_area(&info);
/*
@@ -141,7 +112,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
}
get_unmapped_area:
- if (mm->get_unmapped_area == arch_get_unmapped_area)
+ if (!test_bit(MMF_TOPDOWN, &mm->flags))
return hugetlb_get_unmapped_area_bottomup(file, addr, len,
pgoff, flags);
else
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a51f22c90a7a..eb503f53c319 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -987,53 +987,6 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
}
#endif
-/*
- * Calculate the precise size of the DMA zone (first 16 MB of RAM),
- * and pass it to the MM layer - to help it set zone watermarks more
- * accurately.
- *
- * Done on 64-bit systems only for the time being, although 32-bit systems
- * might benefit from this as well.
- */
-void __init memblock_find_dma_reserve(void)
-{
-#ifdef CONFIG_X86_64
- u64 nr_pages = 0, nr_free_pages = 0;
- unsigned long start_pfn, end_pfn;
- phys_addr_t start_addr, end_addr;
- int i;
- u64 u;
-
- /*
- * Iterate over all memory ranges (free and reserved ones alike),
- * to calculate the total number of pages in the first 16 MB of RAM:
- */
- nr_pages = 0;
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
- start_pfn = min(start_pfn, MAX_DMA_PFN);
- end_pfn = min(end_pfn, MAX_DMA_PFN);
-
- nr_pages += end_pfn - start_pfn;
- }
-
- /*
- * Iterate over free memory ranges to calculate the number of free
- * pages in the DMA zone, while not counting potential partial
- * pages at the beginning or the end of the range:
- */
- nr_free_pages = 0;
- for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
- start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
- end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);
-
- if (start_pfn < end_pfn)
- nr_free_pages += end_pfn - start_pfn;
- }
-
- set_dma_reserve(nr_pages - nr_free_pages);
-#endif
-}
-
void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index c90c20904a60..a2cabb1c81e1 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -129,9 +129,9 @@ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
if (mmap_is_legacy())
- mm->get_unmapped_area = arch_get_unmapped_area;
+ clear_bit(MMF_TOPDOWN, &mm->flags);
else
- mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+ set_bit(MMF_TOPDOWN, &mm->flags);
arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
arch_rnd(mmap64_rnd_bits), task_size_64bit(0),
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 025fd7ea5d69..65fda406e6f2 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
#include <linux/memblock.h>
#include <linux/init.h>
+#include <linux/vmalloc.h>
#include <asm/pgtable_areas.h>
#include "numa_internal.h"
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 36b603d0cdde..bdc2a240c2aa 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/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 +948,29 @@ 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)
+{
+ pte_t *ptep, pte;
+ spinlock_t *ptl;
+
+ if (follow_pte(vma, vma->vm_start, &ptep, &ptl))
+ return -EINVAL;
+
+ pte = ptep_get(ptep);
+
+ /* Never return PFNs of anon folios in COW mappings. */
+ if (vm_normal_folio(vma, vma->vm_start, pte)) {
+ pte_unmap_unlock(ptep, ptl);
+ return -EINVAL;
+ }
+
+ *prot = pgprot_val(pte_pgprot(pte));
+ *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
+ pte_unmap_unlock(ptep, ptl);
+ return 0;
+}
+
static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
pgprot_t *pgprot)
{
@@ -964,7 +988,7 @@ 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;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index d007591b8059..93e54ba91fbf 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
+ VM_WARN_ON_ONCE(!pmd_present(*pmdp));
+
/*
* No flush is necessary. Once an invalid PTE is established, the PTE's
* access and dirty bits cannot be updated.
@@ -731,7 +733,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
return 0;
/* Bail out if we are we on a populated non-leaf entry: */
- if (pud_present(*pud) && !pud_huge(*pud))
+ if (pud_present(*pud) && !pud_leaf(*pud))
return 0;
set_pte((pte_t *)pud, pfn_pte(
@@ -760,7 +762,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
}
/* Bail out if we are we on a populated non-leaf entry: */
- if (pmd_present(*pmd) && !pmd_huge(*pmd))
+ if (pmd_present(*pmd) && !pmd_leaf(*pmd))
return 0;
set_pte((pte_t *)pmd, pfn_pte(