
Changes in 5.10.47 module: limit enabling module.sig_enforce Revert "drm/amdgpu/gfx9: fix the doorbell missing when in CGPG issue." Revert "drm/amdgpu/gfx10: enlarge CP_MEC_DOORBELL_RANGE_UPPER to cover full doorbell." drm: add a locked version of drm_is_current_master drm/nouveau: wait for moving fence after pinning v2 drm/radeon: wait for moving fence after pinning drm/amdgpu: wait for moving fence after pinning ARM: 9081/1: fix gcc-10 thumb2-kernel regression mmc: meson-gx: use memcpy_to/fromio for dram-access-quirk MIPS: generic: Update node names to avoid unit addresses arm64: Ignore any DMA offsets in the max_zone_phys() calculation arm64: Force NO_BLOCK_MAPPINGS if crashkernel reservation is required spi: spi-nxp-fspi: move the register operation after the clock enable Revert "PCI: PM: Do not read power state in pci_enable_device_flags()" drm/vc4: hdmi: Move the HSM clock enable to runtime_pm drm/vc4: hdmi: Make sure the controller is powered in detect x86/entry: Fix noinstr fail in __do_fast_syscall_32() x86/xen: Fix noinstr fail in exc_xen_unknown_trap() locking/lockdep: Improve noinstr vs errors perf/x86/lbr: Remove cpuc->lbr_xsave allocation from atomic context perf/x86/intel/lbr: Zero the xstate buffer on allocation dmaengine: zynqmp_dma: Fix PM reference leak in zynqmp_dma_alloc_chan_resourc() dmaengine: stm32-mdma: fix PM reference leak in stm32_mdma_alloc_chan_resourc() dmaengine: xilinx: dpdma: Add missing dependencies to Kconfig dmaengine: xilinx: dpdma: Limit descriptor IDs to 16 bits mac80211: remove warning in ieee80211_get_sband() mac80211_hwsim: drop pending frames on stop cfg80211: call cfg80211_leave_ocb when switching away from OCB dmaengine: rcar-dmac: Fix PM reference leak in rcar_dmac_probe() dmaengine: mediatek: free the proper desc in desc_free handler dmaengine: mediatek: do not issue a new desc if one is still current dmaengine: mediatek: use GFP_NOWAIT instead of GFP_ATOMIC in prep_dma net: ipv4: Remove unneed BUG() function mac80211: drop multicast fragments net: ethtool: clear heap allocations for ethtool function inet: annotate data race in inet_send_prepare() and inet_dgram_connect() ping: Check return value of function 'ping_queue_rcv_skb' net: annotate data race in sock_error() inet: annotate date races around sk->sk_txhash net/packet: annotate data race in packet_sendmsg() net: phy: dp83867: perform soft reset and retain established link riscv32: Use medany C model for modules net: caif: fix memory leak in ldisc_open net/packet: annotate accesses to po->bind net/packet: annotate accesses to po->ifindex r8152: Avoid memcpy() over-reading of ETH_SS_STATS sh_eth: Avoid memcpy() over-reading of ETH_SS_STATS r8169: Avoid memcpy() over-reading of ETH_SS_STATS KVM: selftests: Fix kvm_check_cap() assertion net: qed: Fix memcpy() overflow of qed_dcbx_params() mac80211: reset profile_periodicity/ema_ap mac80211: handle various extensible elements correctly recordmcount: Correct st_shndx handling PCI: Add AMD RS690 quirk to enable 64-bit DMA net: ll_temac: Add memory-barriers for TX BD access net: ll_temac: Avoid ndo_start_xmit returning NETDEV_TX_BUSY perf/x86: Track pmu in per-CPU cpu_hw_events pinctrl: stm32: fix the reported number of GPIO lines per bank i2c: i801: Ensure that SMBHSTSTS_INUSE_STS is cleared when leaving i801_access gpiolib: cdev: zero padding during conversion to gpioline_info_changed scsi: sd: Call sd_revalidate_disk() for ioctl(BLKRRPART) nilfs2: fix memory leak in nilfs_sysfs_delete_device_group s390/stack: fix possible register corruption with stack switch helper KVM: do not allow mapping valid but non-reference-counted pages i2c: robotfuzz-osif: fix control-request directions ceph: must hold snap_rwsem when filling inode for async create kthread_worker: split code for canceling the delayed work timer kthread: prevent deadlock when kthread_mod_delayed_work() races with kthread_cancel_delayed_work_sync() x86/fpu: Preserve supervisor states in sanitize_restored_user_xstate() x86/fpu: Make init_fpstate correct with optimized XSAVE mm: add VM_WARN_ON_ONCE_PAGE() macro mm/rmap: remove unneeded semicolon in page_not_mapped() mm/rmap: use page_not_mapped in try_to_unmap() mm, thp: use head page in __migration_entry_wait() mm/thp: fix __split_huge_pmd_locked() on shmem migration entry mm/thp: make is_huge_zero_pmd() safe and quicker mm/thp: try_to_unmap() use TTU_SYNC for safe splitting mm/thp: fix vma_address() if virtual address below file offset mm/thp: fix page_address_in_vma() on file THP tails mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split mm: page_vma_mapped_walk(): use page for pvmw->page mm: page_vma_mapped_walk(): settle PageHuge on entry mm: page_vma_mapped_walk(): use pmde for *pvmw->pmd mm: page_vma_mapped_walk(): prettify PVMW_MIGRATION block mm: page_vma_mapped_walk(): crossing page table boundary mm: page_vma_mapped_walk(): add a level of indentation mm: page_vma_mapped_walk(): use goto instead of while (1) mm: page_vma_mapped_walk(): get vma_address_end() earlier mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk() mm, futex: fix shared futex pgoff on shmem huge page KVM: SVM: Call SEV Guest Decommission if ASID binding fails swiotlb: manipulate orig_addr when tlb_addr has offset netfs: fix test for whether we can skip read when writing beyond EOF Revert "drm: add a locked version of drm_is_current_master" certs: Add EFI_CERT_X509_GUID support for dbx entries certs: Move load_system_certificate_list to a common function certs: Add ability to preload revocation certs integrity: Load mokx variables into the blacklist keyring Linux 5.10.47 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: I68f731ad78a5db003c41093e4faf59f6f9f2e446
312 lines
9.2 KiB
C
312 lines
9.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_RMAP_H
|
|
#define _LINUX_RMAP_H
|
|
/*
|
|
* Declarations for Reverse Mapping functions in mm/rmap.c
|
|
*/
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/highmem.h>
|
|
|
|
/*
|
|
* The anon_vma heads a list of private "related" vmas, to scan if
|
|
* an anonymous page pointing to this anon_vma needs to be unmapped:
|
|
* the vmas on the list will be related by forking, or by splitting.
|
|
*
|
|
* Since vmas come and go as they are split and merged (particularly
|
|
* in mprotect), the mapping field of an anonymous page cannot point
|
|
* directly to a vma: instead it points to an anon_vma, on whose list
|
|
* the related vmas can be easily linked or unlinked.
|
|
*
|
|
* After unlinking the last vma on the list, we must garbage collect
|
|
* the anon_vma object itself: we're guaranteed no page can be
|
|
* pointing to this anon_vma once its vma list is empty.
|
|
*/
|
|
struct anon_vma {
|
|
struct anon_vma *root; /* Root of this anon_vma tree */
|
|
struct rw_semaphore rwsem; /* W: modification, R: walking the list */
|
|
/*
|
|
* The refcount is taken on an anon_vma when there is no
|
|
* guarantee that the vma of page tables will exist for
|
|
* the duration of the operation. A caller that takes
|
|
* the reference is responsible for clearing up the
|
|
* anon_vma if they are the last user on release
|
|
*/
|
|
atomic_t refcount;
|
|
|
|
/*
|
|
* Count of child anon_vmas and VMAs which points to this anon_vma.
|
|
*
|
|
* This counter is used for making decision about reusing anon_vma
|
|
* instead of forking new one. See comments in function anon_vma_clone.
|
|
*/
|
|
unsigned degree;
|
|
|
|
struct anon_vma *parent; /* Parent of this anon_vma */
|
|
|
|
/*
|
|
* NOTE: the LSB of the rb_root.rb_node is set by
|
|
* mm_take_all_locks() _after_ taking the above lock. So the
|
|
* rb_root must only be read/written after taking the above lock
|
|
* to be sure to see a valid next pointer. The LSB bit itself
|
|
* is serialized by a system wide lock only visible to
|
|
* mm_take_all_locks() (mm_all_locks_mutex).
|
|
*/
|
|
|
|
/* Interval tree of private "related" vmas */
|
|
struct rb_root_cached rb_root;
|
|
};
|
|
|
|
/*
|
|
* The copy-on-write semantics of fork mean that an anon_vma
|
|
* can become associated with multiple processes. Furthermore,
|
|
* each child process will have its own anon_vma, where new
|
|
* pages for that process are instantiated.
|
|
*
|
|
* This structure allows us to find the anon_vmas associated
|
|
* with a VMA, or the VMAs associated with an anon_vma.
|
|
* The "same_vma" list contains the anon_vma_chains linking
|
|
* all the anon_vmas associated with this VMA.
|
|
* The "rb" field indexes on an interval tree the anon_vma_chains
|
|
* which link all the VMAs associated with this anon_vma.
|
|
*/
|
|
struct anon_vma_chain {
|
|
struct vm_area_struct *vma;
|
|
struct anon_vma *anon_vma;
|
|
struct list_head same_vma; /* locked by mmap_lock & page_table_lock */
|
|
struct rb_node rb; /* locked by anon_vma->rwsem */
|
|
unsigned long rb_subtree_last;
|
|
#ifdef CONFIG_DEBUG_VM_RB
|
|
unsigned long cached_vma_start, cached_vma_last;
|
|
#endif
|
|
};
|
|
|
|
enum ttu_flags {
|
|
TTU_MIGRATION = 0x1, /* migration mode */
|
|
TTU_MUNLOCK = 0x2, /* munlock mode */
|
|
|
|
TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */
|
|
TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */
|
|
TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */
|
|
TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */
|
|
TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible
|
|
* and caller guarantees they will
|
|
* do a final flush if necessary */
|
|
TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock:
|
|
* caller holds it */
|
|
TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */
|
|
};
|
|
|
|
#ifdef CONFIG_MMU
|
|
static inline void get_anon_vma(struct anon_vma *anon_vma)
|
|
{
|
|
atomic_inc(&anon_vma->refcount);
|
|
}
|
|
|
|
void __put_anon_vma(struct anon_vma *anon_vma);
|
|
|
|
static inline void put_anon_vma(struct anon_vma *anon_vma)
|
|
{
|
|
if (atomic_dec_and_test(&anon_vma->refcount))
|
|
__put_anon_vma(anon_vma);
|
|
}
|
|
|
|
static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
|
|
{
|
|
down_write(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
|
|
{
|
|
up_write(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
|
|
{
|
|
down_read(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
|
|
{
|
|
up_read(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
|
|
/*
|
|
* anon_vma helper functions.
|
|
*/
|
|
void anon_vma_init(void); /* create anon_vma_cachep */
|
|
int __anon_vma_prepare(struct vm_area_struct *);
|
|
void unlink_anon_vmas(struct vm_area_struct *);
|
|
int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
|
|
int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
|
|
|
|
static inline int anon_vma_prepare(struct vm_area_struct *vma)
|
|
{
|
|
if (likely(vma->anon_vma))
|
|
return 0;
|
|
|
|
return __anon_vma_prepare(vma);
|
|
}
|
|
|
|
static inline void anon_vma_merge(struct vm_area_struct *vma,
|
|
struct vm_area_struct *next)
|
|
{
|
|
VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma);
|
|
unlink_anon_vmas(next);
|
|
}
|
|
|
|
struct anon_vma *page_get_anon_vma(struct page *page);
|
|
|
|
/* bitflags for do_page_add_anon_rmap() */
|
|
#define RMAP_EXCLUSIVE 0x01
|
|
#define RMAP_COMPOUND 0x02
|
|
|
|
/*
|
|
* rmap interfaces called when adding or removing pte of page
|
|
*/
|
|
void page_move_anon_rmap(struct page *, struct vm_area_struct *);
|
|
void page_add_anon_rmap(struct page *, struct vm_area_struct *,
|
|
unsigned long, bool);
|
|
void do_page_add_anon_rmap(struct page *, struct vm_area_struct *,
|
|
unsigned long, int);
|
|
void __page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma,
|
|
unsigned long address, bool compound);
|
|
static inline void page_add_new_anon_rmap(struct page *page,
|
|
struct vm_area_struct *vma,
|
|
unsigned long address, bool compound)
|
|
{
|
|
VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
|
|
__page_add_new_anon_rmap(page, vma, address, compound);
|
|
}
|
|
|
|
void page_add_file_rmap(struct page *, bool);
|
|
void page_remove_rmap(struct page *, bool);
|
|
|
|
void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
|
|
unsigned long);
|
|
void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *,
|
|
unsigned long);
|
|
|
|
static inline void page_dup_rmap(struct page *page, bool compound)
|
|
{
|
|
atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount);
|
|
}
|
|
|
|
/*
|
|
* Called from mm/vmscan.c to handle paging out
|
|
*/
|
|
int page_referenced(struct page *, int is_locked,
|
|
struct mem_cgroup *memcg, unsigned long *vm_flags);
|
|
|
|
bool try_to_unmap(struct page *, enum ttu_flags flags);
|
|
|
|
/* Avoid racy checks */
|
|
#define PVMW_SYNC (1 << 0)
|
|
/* Look for migarion entries rather than present PTEs */
|
|
#define PVMW_MIGRATION (1 << 1)
|
|
|
|
struct page_vma_mapped_walk {
|
|
struct page *page;
|
|
struct vm_area_struct *vma;
|
|
unsigned long address;
|
|
pmd_t *pmd;
|
|
pte_t *pte;
|
|
spinlock_t *ptl;
|
|
unsigned int flags;
|
|
};
|
|
|
|
static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw)
|
|
{
|
|
/* HugeTLB pte is set to the relevant page table entry without pte_mapped. */
|
|
if (pvmw->pte && !PageHuge(pvmw->page))
|
|
pte_unmap(pvmw->pte);
|
|
if (pvmw->ptl)
|
|
spin_unlock(pvmw->ptl);
|
|
}
|
|
|
|
bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw);
|
|
|
|
/*
|
|
* Used by swapoff to help locate where page is expected in vma.
|
|
*/
|
|
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
|
|
|
|
/*
|
|
* Cleans the PTEs of shared mappings.
|
|
* (and since clean PTEs should also be readonly, write protects them too)
|
|
*
|
|
* returns the number of cleaned PTEs.
|
|
*/
|
|
int page_mkclean(struct page *);
|
|
|
|
/*
|
|
* called in munlock()/munmap() path to check for other vmas holding
|
|
* the page mlocked.
|
|
*/
|
|
void try_to_munlock(struct page *);
|
|
|
|
void remove_migration_ptes(struct page *old, struct page *new, bool locked);
|
|
|
|
/*
|
|
* Called by memory-failure.c to kill processes.
|
|
*/
|
|
struct anon_vma *page_lock_anon_vma_read(struct page *page);
|
|
void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
|
|
int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
|
|
|
|
/*
|
|
* rmap_walk_control: To control rmap traversing for specific needs
|
|
*
|
|
* arg: passed to rmap_one() and invalid_vma()
|
|
* rmap_one: executed on each vma where page is mapped
|
|
* done: for checking traversing termination condition
|
|
* anon_lock: for getting anon_lock by optimized way rather than default
|
|
* invalid_vma: for skipping uninterested vma
|
|
*/
|
|
struct rmap_walk_control {
|
|
void *arg;
|
|
/*
|
|
* Return false if page table scanning in rmap_walk should be stopped.
|
|
* Otherwise, return true.
|
|
*/
|
|
bool (*rmap_one)(struct page *page, struct vm_area_struct *vma,
|
|
unsigned long addr, void *arg);
|
|
int (*done)(struct page *page);
|
|
struct anon_vma *(*anon_lock)(struct page *page);
|
|
bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
|
|
};
|
|
|
|
void rmap_walk(struct page *page, struct rmap_walk_control *rwc);
|
|
void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc);
|
|
|
|
#else /* !CONFIG_MMU */
|
|
|
|
#define anon_vma_init() do {} while (0)
|
|
#define anon_vma_prepare(vma) (0)
|
|
#define anon_vma_link(vma) do {} while (0)
|
|
|
|
static inline int page_referenced(struct page *page, int is_locked,
|
|
struct mem_cgroup *memcg,
|
|
unsigned long *vm_flags)
|
|
{
|
|
*vm_flags = 0;
|
|
return 0;
|
|
}
|
|
|
|
#define try_to_unmap(page, refs) false
|
|
|
|
static inline int page_mkclean(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
|
|
#endif /* CONFIG_MMU */
|
|
|
|
#endif /* _LINUX_RMAP_H */
|