summaryrefslogtreecommitdiffstats
path: root/include/asm-generic/pgalloc.h
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2026-08-30 09:22:00 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2026-08-30 09:22:00 -0700
commit034dd340b08be1f2f0477ad16131d609f9dbd53c (patch)
tree2536f4b2d7893ccd916b5abdf3c454ad6edc03c2 /include/asm-generic/pgalloc.h
downloadlinux-stable-034dd340b08be1f2f0477ad16131d609f9dbd53c.tar.gz
linux-stable-034dd340b08be1f2f0477ad16131d609f9dbd53c.zip
Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted
Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure
Diffstat (limited to 'include/asm-generic/pgalloc.h')
-rw-r--r--include/asm-generic/pgalloc.h315
1 files changed, 315 insertions, 0 deletions
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
new file mode 100644
index 000000000..051aa1331
--- /dev/null
+++ b/include/asm-generic/pgalloc.h
@@ -0,0 +1,315 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_PGALLOC_H
+#define __ASM_GENERIC_PGALLOC_H
+
+#ifdef CONFIG_MMU
+
+#define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO | __GFP_SKIP_KASAN)
+#define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT)
+
+/**
+ * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table
+ * @mm: the mm_struct of the current context
+ *
+ * This function is intended for architectures that need
+ * anything beyond simple page allocation.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
+{
+ struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL, 0);
+
+ if (!ptdesc)
+ return NULL;
+ if (!pagetable_pte_ctor(mm, ptdesc)) {
+ pagetable_free(ptdesc);
+ return NULL;
+ }
+
+ ptdesc_set_kernel(ptdesc);
+
+ return ptdesc_address(ptdesc);
+}
+#define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+/**
+ * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table
+ * @mm: the mm_struct of the current context
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm)
+{
+ return __pte_alloc_one_kernel_noprof(mm);
+}
+#define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__))
+#endif
+
+/**
+ * pte_free_kernel - free PTE-level kernel page table memory
+ * @mm: the mm_struct of the current context
+ * @pte: pointer to the memory containing the page table
+ */
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ pagetable_dtor_free(virt_to_ptdesc(pte));
+}
+
+/**
+ * __pte_alloc_one - allocate memory for a PTE-level user page table
+ * @mm: the mm_struct of the current context
+ * @gfp: GFP flags to use for the allocation
+ *
+ * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor().
+ *
+ * This function is intended for architectures that need
+ * anything beyond simple page allocation or must have custom GFP flags.
+ *
+ * Return: `struct page` referencing the ptdesc or %NULL on error
+ */
+static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
+{
+ struct ptdesc *ptdesc;
+
+ ptdesc = pagetable_alloc_noprof(gfp, 0);
+ if (!ptdesc)
+ return NULL;
+ if (!pagetable_pte_ctor(mm, ptdesc)) {
+ pagetable_free(ptdesc);
+ return NULL;
+ }
+
+ return ptdesc_page(ptdesc);
+}
+#define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_PTE_ALLOC_ONE
+/**
+ * pte_alloc_one - allocate a page for PTE-level user page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor().
+ *
+ * Return: `struct page` referencing the ptdesc or %NULL on error
+ */
+static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm)
+{
+ return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER);
+}
+#define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+/*
+ * Should really implement gc for free page table pages. This could be
+ * done with a reference count in struct page.
+ */
+
+/**
+ * pte_free - free PTE-level user page table memory
+ * @mm: the mm_struct of the current context
+ * @pte_page: the `struct page` referencing the ptdesc
+ */
+static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
+{
+ struct ptdesc *ptdesc = page_ptdesc(pte_page);
+
+ pagetable_dtor_free(ptdesc);
+}
+
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+#ifndef __HAVE_ARCH_PMD_ALLOC_ONE
+/**
+ * pmd_alloc_one - allocate memory for a PMD-level page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor().
+ *
+ * Allocations use %GFP_PGTABLE_USER in user context and
+ * %GFP_PGTABLE_KERNEL in kernel context.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+ struct ptdesc *ptdesc;
+ gfp_t gfp = GFP_PGTABLE_USER;
+
+ if (mm == &init_mm)
+ gfp = GFP_PGTABLE_KERNEL;
+ ptdesc = pagetable_alloc_noprof(gfp, 0);
+ if (!ptdesc)
+ return NULL;
+ if (!pagetable_pmd_ctor(mm, ptdesc)) {
+ pagetable_free(ptdesc);
+ return NULL;
+ }
+
+ if (mm == &init_mm)
+ ptdesc_set_kernel(ptdesc);
+
+ return ptdesc_address(ptdesc);
+}
+#define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+#ifndef __HAVE_ARCH_PMD_FREE
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
+
+ BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+ pagetable_dtor_free(ptdesc);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 2 */
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+ gfp_t gfp = GFP_PGTABLE_USER;
+ struct ptdesc *ptdesc;
+
+ if (mm == &init_mm)
+ gfp = GFP_PGTABLE_KERNEL;
+
+ ptdesc = pagetable_alloc_noprof(gfp, 0);
+ if (!ptdesc)
+ return NULL;
+
+ pagetable_pud_ctor(ptdesc);
+
+ if (mm == &init_mm)
+ ptdesc_set_kernel(ptdesc);
+
+ return ptdesc_address(ptdesc);
+}
+#define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_PUD_ALLOC_ONE
+/**
+ * pud_alloc_one - allocate memory for a PUD-level page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocate memory for a page table using %GFP_PGTABLE_USER for user context
+ * and %GFP_PGTABLE_KERNEL for kernel context.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+ return __pud_alloc_one_noprof(mm, addr);
+}
+#define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
+{
+ struct ptdesc *ptdesc = virt_to_ptdesc(pud);
+
+ BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+ pagetable_dtor_free(ptdesc);
+}
+
+#ifndef __HAVE_ARCH_PUD_FREE
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+ __pud_free(mm, pud);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 3 */
+
+#if CONFIG_PGTABLE_LEVELS > 4
+
+static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+ gfp_t gfp = GFP_PGTABLE_USER;
+ struct ptdesc *ptdesc;
+
+ if (mm == &init_mm)
+ gfp = GFP_PGTABLE_KERNEL;
+
+ ptdesc = pagetable_alloc_noprof(gfp, 0);
+ if (!ptdesc)
+ return NULL;
+
+ pagetable_p4d_ctor(ptdesc);
+
+ if (mm == &init_mm)
+ ptdesc_set_kernel(ptdesc);
+
+ return ptdesc_address(ptdesc);
+}
+#define __p4d_alloc_one(...) alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_P4D_ALLOC_ONE
+static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+ return __p4d_alloc_one_noprof(mm, addr);
+}
+#define p4d_alloc_one(...) alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+ struct ptdesc *ptdesc = virt_to_ptdesc(p4d);
+
+ BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
+ pagetable_dtor_free(ptdesc);
+}
+
+#ifndef __HAVE_ARCH_P4D_FREE
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+ if (!mm_p4d_folded(mm))
+ __p4d_free(mm, p4d);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 4 */
+
+static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order)
+{
+ gfp_t gfp = GFP_PGTABLE_USER;
+ struct ptdesc *ptdesc;
+
+ if (mm == &init_mm)
+ gfp = GFP_PGTABLE_KERNEL;
+
+ ptdesc = pagetable_alloc_noprof(gfp, order);
+ if (!ptdesc)
+ return NULL;
+
+ pagetable_pgd_ctor(ptdesc);
+
+ if (mm == &init_mm)
+ ptdesc_set_kernel(ptdesc);
+
+ return ptdesc_address(ptdesc);
+}
+#define __pgd_alloc(...) alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__))
+
+static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
+
+ BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+ pagetable_dtor_free(ptdesc);
+}
+
+#ifndef __HAVE_ARCH_PGD_FREE
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ __pgd_free(mm, pgd);
+}
+#endif
+
+#endif /* CONFIG_MMU */
+
+#endif /* __ASM_GENERIC_PGALLOC_H */