mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Alistair Popple](/assets/img/avatar_default.png)
Patch series "Add support for SVM atomics in Nouveau", v11. Introduction ============ Some devices have features such as atomic PTE bits that can be used to implement atomic access to system memory. To support atomic operations to a shared virtual memory page such a device needs access to that page which is exclusive of the CPU. This series introduces a mechanism to temporarily unmap pages granting exclusive access to a device. These changes are required to support OpenCL atomic operations in Nouveau to shared virtual memory (SVM) regions allocated with the CL_MEM_SVM_ATOMICS clSVMAlloc flag. A more complete description of the OpenCL SVM feature is available at https://www.khronos.org/registry/OpenCL/specs/3.0-unified/html/ OpenCL_API.html#_shared_virtual_memory . Implementation ============== Exclusive device access is implemented by adding a new swap entry type (SWAP_DEVICE_EXCLUSIVE) which is similar to a migration entry. The main difference is that on fault the original entry is immediately restored by the fault handler instead of waiting. Restoring the entry triggers calls to MMU notifers which allows a device driver to revoke the atomic access permission from the GPU prior to the CPU finalising the entry. Patches ======= Patches 1 & 2 refactor existing migration and device private entry functions. Patches 3 & 4 rework try_to_unmap_one() by splitting out unrelated functionality into separate functions - try_to_migrate_one() and try_to_munlock_one(). Patch 5 renames some existing code but does not introduce functionality. Patch 6 is a small clean-up to swap entry handling in copy_pte_range(). Patch 7 contains the bulk of the implementation for device exclusive memory. Patch 8 contains some additions to the HMM selftests to ensure everything works as expected. Patch 9 is a cleanup for the Nouveau SVM implementation. Patch 10 contains the implementation of atomic access for the Nouveau driver. Testing ======= This has been tested with upstream Mesa 21.1.0 and a simple OpenCL program which checks that GPU atomic accesses to system memory are atomic. Without this series the test fails as there is no way of write-protecting the page mapping which results in the device clobbering CPU writes. For reference the test is available at https://ozlabs.org/~apopple/opencl_svm_atomics/ Further testing has been performed by adding support for testing exclusive access to the hmm-tests kselftests. This patch (of 10): Remove multiple similar inline functions for dealing with different types of special swap entries. Both migration and device private swap entries use the swap offset to store a pfn. Instead of multiple inline functions to obtain a struct page for each swap entry type use a common function pfn_swap_entry_to_page(). Also open-code the various entry_to_pfn() functions as this results is shorter code that is easier to understand. Link: https://lkml.kernel.org/r/20210616105937.23201-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20210616105937.23201-2-apopple@nvidia.com Signed-off-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
358 lines
8.6 KiB
C
358 lines
8.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SWAPOPS_H
|
|
#define _LINUX_SWAPOPS_H
|
|
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/mm_types.h>
|
|
|
|
#ifdef CONFIG_MMU
|
|
|
|
/*
|
|
* swapcache pages are stored in the swapper_space radix tree. We want to
|
|
* get good packing density in that tree, so the index should be dense in
|
|
* the low-order bits.
|
|
*
|
|
* We arrange the `type' and `offset' fields so that `type' is at the seven
|
|
* high-order bits of the swp_entry_t and `offset' is right-aligned in the
|
|
* remaining bits. Although `type' itself needs only five bits, we allow for
|
|
* shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry().
|
|
*
|
|
* swp_entry_t's are *never* stored anywhere in their arch-dependent format.
|
|
*/
|
|
#define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
|
|
#define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1)
|
|
|
|
/* Clear all flags but only keep swp_entry_t related information */
|
|
static inline pte_t pte_swp_clear_flags(pte_t pte)
|
|
{
|
|
if (pte_swp_soft_dirty(pte))
|
|
pte = pte_swp_clear_soft_dirty(pte);
|
|
if (pte_swp_uffd_wp(pte))
|
|
pte = pte_swp_clear_uffd_wp(pte);
|
|
return pte;
|
|
}
|
|
|
|
/*
|
|
* Store a type+offset into a swp_entry_t in an arch-independent format
|
|
*/
|
|
static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
|
|
{
|
|
swp_entry_t ret;
|
|
|
|
ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Extract the `type' field from a swp_entry_t. The swp_entry_t is in
|
|
* arch-independent format
|
|
*/
|
|
static inline unsigned swp_type(swp_entry_t entry)
|
|
{
|
|
return (entry.val >> SWP_TYPE_SHIFT);
|
|
}
|
|
|
|
/*
|
|
* Extract the `offset' field from a swp_entry_t. The swp_entry_t is in
|
|
* arch-independent format
|
|
*/
|
|
static inline pgoff_t swp_offset(swp_entry_t entry)
|
|
{
|
|
return entry.val & SWP_OFFSET_MASK;
|
|
}
|
|
|
|
/* check whether a pte points to a swap entry */
|
|
static inline int is_swap_pte(pte_t pte)
|
|
{
|
|
return !pte_none(pte) && !pte_present(pte);
|
|
}
|
|
|
|
/*
|
|
* Convert the arch-dependent pte representation of a swp_entry_t into an
|
|
* arch-independent swp_entry_t.
|
|
*/
|
|
static inline swp_entry_t pte_to_swp_entry(pte_t pte)
|
|
{
|
|
swp_entry_t arch_entry;
|
|
|
|
pte = pte_swp_clear_flags(pte);
|
|
arch_entry = __pte_to_swp_entry(pte);
|
|
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
|
|
}
|
|
|
|
/*
|
|
* Convert the arch-independent representation of a swp_entry_t into the
|
|
* arch-dependent pte representation.
|
|
*/
|
|
static inline pte_t swp_entry_to_pte(swp_entry_t entry)
|
|
{
|
|
swp_entry_t arch_entry;
|
|
|
|
arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
|
|
return __swp_entry_to_pte(arch_entry);
|
|
}
|
|
|
|
static inline swp_entry_t radix_to_swp_entry(void *arg)
|
|
{
|
|
swp_entry_t entry;
|
|
|
|
entry.val = xa_to_value(arg);
|
|
return entry;
|
|
}
|
|
|
|
static inline void *swp_to_radix_entry(swp_entry_t entry)
|
|
{
|
|
return xa_mk_value(entry.val);
|
|
}
|
|
|
|
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
|
|
static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
|
|
{
|
|
return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ,
|
|
page_to_pfn(page));
|
|
}
|
|
|
|
static inline bool is_device_private_entry(swp_entry_t entry)
|
|
{
|
|
int type = swp_type(entry);
|
|
return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE;
|
|
}
|
|
|
|
static inline void make_device_private_entry_read(swp_entry_t *entry)
|
|
{
|
|
*entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry));
|
|
}
|
|
|
|
static inline bool is_write_device_private_entry(swp_entry_t entry)
|
|
{
|
|
return unlikely(swp_type(entry) == SWP_DEVICE_WRITE);
|
|
}
|
|
#else /* CONFIG_DEVICE_PRIVATE */
|
|
static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
|
|
{
|
|
return swp_entry(0, 0);
|
|
}
|
|
|
|
static inline void make_device_private_entry_read(swp_entry_t *entry)
|
|
{
|
|
}
|
|
|
|
static inline bool is_device_private_entry(swp_entry_t entry)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool is_write_device_private_entry(swp_entry_t entry)
|
|
{
|
|
return false;
|
|
}
|
|
#endif /* CONFIG_DEVICE_PRIVATE */
|
|
|
|
#ifdef CONFIG_MIGRATION
|
|
static inline swp_entry_t make_migration_entry(struct page *page, int write)
|
|
{
|
|
BUG_ON(!PageLocked(compound_head(page)));
|
|
|
|
return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ,
|
|
page_to_pfn(page));
|
|
}
|
|
|
|
static inline int is_migration_entry(swp_entry_t entry)
|
|
{
|
|
return unlikely(swp_type(entry) == SWP_MIGRATION_READ ||
|
|
swp_type(entry) == SWP_MIGRATION_WRITE);
|
|
}
|
|
|
|
static inline int is_write_migration_entry(swp_entry_t entry)
|
|
{
|
|
return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
|
|
}
|
|
|
|
static inline void make_migration_entry_read(swp_entry_t *entry)
|
|
{
|
|
*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
|
|
}
|
|
|
|
extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
|
|
spinlock_t *ptl);
|
|
extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
|
|
unsigned long address);
|
|
extern void migration_entry_wait_huge(struct vm_area_struct *vma,
|
|
struct mm_struct *mm, pte_t *pte);
|
|
#else
|
|
|
|
#define make_migration_entry(page, write) swp_entry(0, 0)
|
|
static inline int is_migration_entry(swp_entry_t swp)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void make_migration_entry_read(swp_entry_t *entryp) { }
|
|
static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
|
|
spinlock_t *ptl) { }
|
|
static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
|
|
unsigned long address) { }
|
|
static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
|
|
struct mm_struct *mm, pte_t *pte) { }
|
|
static inline int is_write_migration_entry(swp_entry_t entry)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif
|
|
|
|
static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
|
|
{
|
|
struct page *p = pfn_to_page(swp_offset(entry));
|
|
|
|
/*
|
|
* Any use of migration entries may only occur while the
|
|
* corresponding page is locked
|
|
*/
|
|
BUG_ON(is_migration_entry(entry) && !PageLocked(p));
|
|
|
|
return p;
|
|
}
|
|
|
|
/*
|
|
* A pfn swap entry is a special type of swap entry that always has a pfn stored
|
|
* in the swap offset. They are used to represent unaddressable device memory
|
|
* and to restrict access to a page undergoing migration.
|
|
*/
|
|
static inline bool is_pfn_swap_entry(swp_entry_t entry)
|
|
{
|
|
return is_migration_entry(entry) || is_device_private_entry(entry);
|
|
}
|
|
|
|
struct page_vma_mapped_walk;
|
|
|
|
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
|
|
extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
|
|
struct page *page);
|
|
|
|
extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
|
|
struct page *new);
|
|
|
|
extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd);
|
|
|
|
static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)
|
|
{
|
|
swp_entry_t arch_entry;
|
|
|
|
if (pmd_swp_soft_dirty(pmd))
|
|
pmd = pmd_swp_clear_soft_dirty(pmd);
|
|
if (pmd_swp_uffd_wp(pmd))
|
|
pmd = pmd_swp_clear_uffd_wp(pmd);
|
|
arch_entry = __pmd_to_swp_entry(pmd);
|
|
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
|
|
}
|
|
|
|
static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
|
|
{
|
|
swp_entry_t arch_entry;
|
|
|
|
arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
|
|
return __swp_entry_to_pmd(arch_entry);
|
|
}
|
|
|
|
static inline int is_pmd_migration_entry(pmd_t pmd)
|
|
{
|
|
return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
|
|
}
|
|
#else
|
|
static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
|
|
struct page *page)
|
|
{
|
|
BUILD_BUG();
|
|
}
|
|
|
|
static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
|
|
struct page *new)
|
|
{
|
|
BUILD_BUG();
|
|
}
|
|
|
|
static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { }
|
|
|
|
static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)
|
|
{
|
|
return swp_entry(0, 0);
|
|
}
|
|
|
|
static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
|
|
{
|
|
return __pmd(0);
|
|
}
|
|
|
|
static inline int is_pmd_migration_entry(pmd_t pmd)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
|
|
extern atomic_long_t num_poisoned_pages __read_mostly;
|
|
|
|
/*
|
|
* Support for hardware poisoned pages
|
|
*/
|
|
static inline swp_entry_t make_hwpoison_entry(struct page *page)
|
|
{
|
|
BUG_ON(!PageLocked(page));
|
|
return swp_entry(SWP_HWPOISON, page_to_pfn(page));
|
|
}
|
|
|
|
static inline int is_hwpoison_entry(swp_entry_t entry)
|
|
{
|
|
return swp_type(entry) == SWP_HWPOISON;
|
|
}
|
|
|
|
static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry)
|
|
{
|
|
return swp_offset(entry);
|
|
}
|
|
|
|
static inline void num_poisoned_pages_inc(void)
|
|
{
|
|
atomic_long_inc(&num_poisoned_pages);
|
|
}
|
|
|
|
static inline void num_poisoned_pages_dec(void)
|
|
{
|
|
atomic_long_dec(&num_poisoned_pages);
|
|
}
|
|
|
|
#else
|
|
|
|
static inline swp_entry_t make_hwpoison_entry(struct page *page)
|
|
{
|
|
return swp_entry(0, 0);
|
|
}
|
|
|
|
static inline int is_hwpoison_entry(swp_entry_t swp)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void num_poisoned_pages_inc(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \
|
|
defined(CONFIG_DEVICE_PRIVATE)
|
|
static inline int non_swap_entry(swp_entry_t entry)
|
|
{
|
|
return swp_type(entry) >= MAX_SWAPFILES;
|
|
}
|
|
#else
|
|
static inline int non_swap_entry(swp_entry_t entry)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#endif /* CONFIG_MMU */
|
|
#endif /* _LINUX_SWAPOPS_H */
|