linux/mm/hmm.c

600 lines
17 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157 Based on 3 normalized pattern(s): this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [graeme] [gregory] [gg]@[slimlogic] [co] [uk] [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] [based] [on] [twl6030]_[usb] [c] [author] [hema] [hk] [hemahk]@[ti] [com] this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details extracted by the scancode license scanner the SPDX license identifier GPL-2.0-or-later has been chosen to replace the boilerplate/reference in 1105 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Allison Randal <allison@lohutok.net> Reviewed-by: Richard Fontana <rfontana@redhat.com> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190527070033.202006027@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-27 06:55:06 +00:00
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright 2013 Red Hat Inc.
*
* Authors: Jérôme Glisse <jglisse@redhat.com>
*/
/*
* Refer to include/linux/hmm.h for information about heterogeneous memory
* management or HMM for short.
*/
#include <linux/pagewalk.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
mm/hmm/devmem: device memory hotplug using ZONE_DEVICE This introduce a simple struct and associated helpers for device driver to use when hotpluging un-addressable device memory as ZONE_DEVICE. It will find a unuse physical address range and trigger memory hotplug for it which allocates and initialize struct page for the device memory. Device driver should use this helper during device initialization to hotplug the device memory. It should only need to remove the memory once the device is going offline (shutdown or hotremove). There should not be any userspace API to hotplug memory expect maybe for host device driver to allow to add more memory to a guest device driver. Device's memory is manage by the device driver and HMM only provides helpers to that effect. Link: http://lkml.kernel.org/r/20170817000548.32038-12-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:58 +00:00
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
mm/hmm/devmem: device memory hotplug using ZONE_DEVICE This introduce a simple struct and associated helpers for device driver to use when hotpluging un-addressable device memory as ZONE_DEVICE. It will find a unuse physical address range and trigger memory hotplug for it which allocates and initialize struct page for the device memory. Device driver should use this helper during device initialization to hotplug the device memory. It should only need to remove the memory once the device is going offline (shutdown or hotremove). There should not be any userspace API to hotplug memory expect maybe for host device driver to allow to add more memory to a guest device driver. Device's memory is manage by the device driver and HMM only provides helpers to that effect. Link: http://lkml.kernel.org/r/20170817000548.32038-12-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:58 +00:00
#include <linux/memremap.h>
#include <linux/sched/mm.h>
#include <linux/jump_label.h>
#include <linux/dma-mapping.h>
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
#include <linux/mmu_notifier.h>
mm/hmm/devmem: device memory hotplug using ZONE_DEVICE This introduce a simple struct and associated helpers for device driver to use when hotpluging un-addressable device memory as ZONE_DEVICE. It will find a unuse physical address range and trigger memory hotplug for it which allocates and initialize struct page for the device memory. Device driver should use this helper during device initialization to hotplug the device memory. It should only need to remove the memory once the device is going offline (shutdown or hotremove). There should not be any userspace API to hotplug memory expect maybe for host device driver to allow to add more memory to a guest device driver. Device's memory is manage by the device driver and HMM only provides helpers to that effect. Link: http://lkml.kernel.org/r/20170817000548.32038-12-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:58 +00:00
#include <linux/memory_hotplug.h>
struct hmm_vma_walk {
struct hmm_range *range;
unsigned long last;
};
enum {
HMM_NEED_FAULT = 1 << 0,
HMM_NEED_WRITE_FAULT = 1 << 1,
HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT,
};
/*
* hmm_device_entry_from_pfn() - create a valid device entry value from pfn
* @range: range use to encode HMM pfn value
* @pfn: pfn value for which to create the device entry
* Return: valid device entry for the pfn
*/
static uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range,
unsigned long pfn)
{
return (pfn << range->pfn_shift) | range->flags[HMM_PFN_VALID];
}
static int hmm_pfns_fill(unsigned long addr, unsigned long end,
struct hmm_range *range, enum hmm_pfn_value_e value)
{
uint64_t *pfns = range->pfns;
unsigned long i;
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, i++)
pfns[i] = range->values[value];
return 0;
}
/*
* hmm_vma_fault() - fault in a range lacking valid pmd or pte(s)
* @addr: range virtual start address (inclusive)
* @end: range virtual end address (exclusive)
* @required_fault: HMM_NEED_* flags
* @walk: mm_walk structure
* Return: -EBUSY after page fault, or page fault error
*
* This function will be called whenever pmd_none() or pte_none() returns true,
* or whenever there is no page directory covering the virtual address range.
*/
static int hmm_vma_fault(unsigned long addr, unsigned long end,
unsigned int required_fault, struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct vm_area_struct *vma = walk->vma;
unsigned int fault_flags = FAULT_FLAG_REMOTE;
WARN_ON_ONCE(!required_fault);
hmm_vma_walk->last = addr;
if (required_fault & HMM_NEED_WRITE_FAULT) {
if (!(vma->vm_flags & VM_WRITE))
return -EPERM;
fault_flags |= FAULT_FLAG_WRITE;
}
for (; addr < end; addr += PAGE_SIZE)
if (handle_mm_fault(vma, addr, fault_flags) & VM_FAULT_ERROR)
return -EFAULT;
return -EBUSY;
}
static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
uint64_t pfns, uint64_t cpu_flags)
{
struct hmm_range *range = hmm_vma_walk->range;
/*
* So we not only consider the individual per page request we also
* consider the default flags requested for the range. The API can
* be used 2 ways. The first one where the HMM user coalesces
* multiple page faults into one request and sets flags per pfn for
* those faults. The second one where the HMM user wants to pre-
* fault a range with specific flags. For the latter one it is a
* waste to have the user pre-fill the pfn arrays with a default
* flags value.
*/
pfns = (pfns & range->pfn_flags_mask) | range->default_flags;
/* We aren't ask to do anything ... */
if (!(pfns & range->flags[HMM_PFN_VALID]))
return 0;
/* Need to write fault ? */
if ((pfns & range->flags[HMM_PFN_WRITE]) &&
!(cpu_flags & range->flags[HMM_PFN_WRITE]))
return HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT;
/* If CPU page table is not valid then we need to fault */
if (!(cpu_flags & range->flags[HMM_PFN_VALID]))
return HMM_NEED_FAULT;
return 0;
}
static unsigned int
hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
const uint64_t *pfns, unsigned long npages,
uint64_t cpu_flags)
{
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault = 0;
unsigned long i;
/*
* If the default flags do not request to fault pages, and the mask does
* not allow for individual pages to be faulted, then
* hmm_pte_need_fault() will always return 0.
*/
if (!((range->default_flags | range->pfn_flags_mask) &
range->flags[HMM_PFN_VALID]))
return 0;
for (i = 0; i < npages; ++i) {
required_fault |=
hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags);
if (required_fault == HMM_NEED_ALL_BITS)
return required_fault;
}
return required_fault;
}
static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
mm: pagewalk: add 'depth' parameter to pte_hole The pte_hole() callback is called at multiple levels of the page tables. Code dumping the kernel page tables needs to know what at what depth the missing entry is. Add this is an extra parameter to pte_hole(). When the depth isn't know (e.g. processing a vma) then -1 is passed. The depth that is reported is the actual level where the entry is missing (ignoring any folding that is in place), i.e. any levels where PTRS_PER_P?D is set to 1 are ignored. Note that depth starts at 0 for a PGD so that PUD/PMD/PTE retain their natural numbers as levels 2/3/4. Link: http://lkml.kernel.org/r/20191218162402.45610-16-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Tested-by: Zong Li <zong.li@sifive.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:36:03 +00:00
__always_unused int depth, struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault;
unsigned long i, npages;
uint64_t *pfns;
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
required_fault = hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0);
if (!walk->vma) {
if (required_fault)
return -EFAULT;
return hmm_pfns_fill(addr, end, range, HMM_PFN_ERROR);
}
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
hmm_vma_walk->last = addr;
return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE);
}
static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
{
if (pmd_protnone(pmd))
return 0;
return pmd_write(pmd) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, uint64_t *pfns, pmd_t pmd)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long pfn, npages, i;
unsigned int required_fault;
uint64_t cpu_flags;
npages = (end - addr) >> PAGE_SHIFT;
cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
required_fault =
hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags);
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
hmm_vma_walk->last = end;
return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
/* stub to allow the code below to compile */
int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, uint64_t *pfns, pmd_t pmd);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline bool hmm_is_device_private_entry(struct hmm_range *range,
swp_entry_t entry)
{
return is_device_private_entry(entry) &&
device_private_entry_to_page(entry)->pgmap->owner ==
range->dev_private_owner;
}
static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
{
if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
return 0;
return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
unsigned long end, pmd_t *pmdp, pte_t *ptep,
uint64_t *pfn)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault;
uint64_t cpu_flags;
pte_t pte = *ptep;
uint64_t orig_pfn = *pfn;
if (pte_none(pte)) {
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
if (required_fault)
goto fault;
*pfn = range->values[HMM_PFN_NONE];
return 0;
}
if (!pte_present(pte)) {
swp_entry_t entry = pte_to_swp_entry(pte);
/*
* Never fault in device private pages pages, but just report
* the PFN even if not present.
*/
if (hmm_is_device_private_entry(range, entry)) {
*pfn = hmm_device_entry_from_pfn(range,
device_private_entry_to_pfn(entry));
*pfn |= range->flags[HMM_PFN_VALID];
if (is_write_device_private_entry(entry))
*pfn |= range->flags[HMM_PFN_WRITE];
return 0;
}
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
if (!required_fault) {
*pfn = range->values[HMM_PFN_NONE];
return 0;
}
if (!non_swap_entry(entry))
goto fault;
if (is_migration_entry(entry)) {
pte_unmap(ptep);
hmm_vma_walk->last = addr;
migration_entry_wait(walk->mm, pmdp, addr);
return -EBUSY;
}
/* Report error for everything else */
pte_unmap(ptep);
return -EFAULT;
}
cpu_flags = pte_to_hmm_pfn_flags(range, pte);
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags);
if (required_fault)
goto fault;
/*
* Since each architecture defines a struct page for the zero page, just
* fall through and treat it like a normal page.
*/
if (pte_special(pte) && !is_zero_pfn(pte_pfn(pte))) {
if (hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0)) {
pte_unmap(ptep);
return -EFAULT;
}
*pfn = range->values[HMM_PFN_SPECIAL];
return 0;
}
*pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
return 0;
fault:
pte_unmap(ptep);
/* Fault any virtual address we were asked to fault */
return hmm_vma_fault(addr, end, required_fault, walk);
}
static int hmm_vma_walk_pmd(pmd_t *pmdp,
unsigned long start,
unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = &range->pfns[(start - range->start) >> PAGE_SHIFT];
unsigned long npages = (end - start) >> PAGE_SHIFT;
unsigned long addr = start;
pte_t *ptep;
pmd_t pmd;
again:
pmd = READ_ONCE(*pmdp);
if (pmd_none(pmd))
mm: pagewalk: add 'depth' parameter to pte_hole The pte_hole() callback is called at multiple levels of the page tables. Code dumping the kernel page tables needs to know what at what depth the missing entry is. Add this is an extra parameter to pte_hole(). When the depth isn't know (e.g. processing a vma) then -1 is passed. The depth that is reported is the actual level where the entry is missing (ignoring any folding that is in place), i.e. any levels where PTRS_PER_P?D is set to 1 are ignored. Note that depth starts at 0 for a PGD so that PUD/PMD/PTE retain their natural numbers as levels 2/3/4. Link: http://lkml.kernel.org/r/20191218162402.45610-16-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Tested-by: Zong Li <zong.li@sifive.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:36:03 +00:00
return hmm_vma_walk_hole(start, end, -1, walk);
if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0)) {
hmm_vma_walk->last = addr;
pmd_migration_entry_wait(walk->mm, pmdp);
return -EBUSY;
}
return hmm_pfns_fill(start, end, range, HMM_PFN_NONE);
}
if (!pmd_present(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0))
return -EFAULT;
return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
}
if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
/*
* No need to take pmd_lock here, even if some other thread
* is splitting the huge pmd we will get that event through
* mmu_notifier callback.
*
* So just read pmd value and check again it's a transparent
* huge or device mapping one and compute corresponding pfn
* values.
*/
pmd = pmd_read_atomic(pmdp);
barrier();
if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
goto again;
return hmm_vma_handle_pmd(walk, addr, end, pfns, pmd);
}
/*
* We have handled all the valid cases above ie either none, migration,
* huge or transparent huge. At this point either it is a valid pmd
* entry pointing to pte directory or it is a bad pmd that will not
* recover.
*/
if (pmd_bad(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0))
return -EFAULT;
return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
}
ptep = pte_offset_map(pmdp, addr);
for (; addr < end; addr += PAGE_SIZE, ptep++, pfns++) {
int r;
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, pfns);
if (r) {
/* hmm_vma_handle_pte() did pte_unmap() */
hmm_vma_walk->last = addr;
return r;
}
}
pte_unmap(ptep - 1);
hmm_vma_walk->last = addr;
return 0;
}
#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
{
if (!pud_present(pud))
return 0;
return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
unsigned long addr = start;
pud_t pud;
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
int ret = 0;
spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);
if (!ptl)
return 0;
/* Normally we don't want to split the huge page */
walk->action = ACTION_CONTINUE;
pud = READ_ONCE(*pudp);
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
if (pud_none(pud)) {
spin_unlock(ptl);
return hmm_vma_walk_hole(start, end, -1, walk);
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
}
if (pud_huge(pud) && pud_devmap(pud)) {
unsigned long i, npages, pfn;
unsigned int required_fault;
uint64_t *pfns, cpu_flags;
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
if (!pud_present(pud)) {
spin_unlock(ptl);
return hmm_vma_walk_hole(start, end, -1, walk);
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
}
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
cpu_flags = pud_to_hmm_pfn_flags(range, pud);
required_fault = hmm_range_need_fault(hmm_vma_walk, pfns,
npages, cpu_flags);
if (required_fault) {
spin_unlock(ptl);
return hmm_vma_fault(addr, end, required_fault, walk);
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
}
pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
for (i = 0; i < npages; ++i, ++pfn)
pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
hmm_vma_walk->last = end;
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
goto out_unlock;
}
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
/* Ask for the PUD to be split */
walk->action = ACTION_SUBTREE;
mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Zong Li <zong.li@sifive.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:45 +00:00
out_unlock:
spin_unlock(ptl);
return ret;
}
#else
#define hmm_vma_walk_pud NULL
#endif
#ifdef CONFIG_HUGETLB_PAGE
static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
unsigned long start, unsigned long end,
struct mm_walk *walk)
{
unsigned long addr = start, i, pfn;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
uint64_t orig_pfn, cpu_flags;
unsigned int required_fault;
spinlock_t *ptl;
pte_t entry;
ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
entry = huge_ptep_get(pte);
i = (start - range->start) >> PAGE_SHIFT;
orig_pfn = range->pfns[i];
cpu_flags = pte_to_hmm_pfn_flags(range, entry);
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags);
if (required_fault) {
spin_unlock(ptl);
return hmm_vma_fault(addr, end, required_fault, walk);
}
pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
hmm_vma_walk->last = end;
spin_unlock(ptl);
return 0;
}
#else
#define hmm_vma_walk_hugetlb_entry NULL
#endif /* CONFIG_HUGETLB_PAGE */
static int hmm_vma_walk_test(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP | VM_MIXEDMAP)) &&
vma->vm_flags & VM_READ)
return 0;
/*
* vma ranges that don't have struct page backing them or map I/O
* devices directly cannot be handled by hmm_range_fault().
*
* If the vma does not allow read access, then assume that it does not
* allow write access either. HMM does not support architectures that
* allow write without read.
*
* If a fault is requested for an unsupported range then it is a hard
* failure.
*/
if (hmm_range_need_fault(hmm_vma_walk,
range->pfns +
((start - range->start) >> PAGE_SHIFT),
(end - start) >> PAGE_SHIFT, 0))
return -EFAULT;
hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
hmm_vma_walk->last = end;
/* Skip this vma and continue processing the next vma. */
return 1;
}
static const struct mm_walk_ops hmm_walk_ops = {
.pud_entry = hmm_vma_walk_pud,
.pmd_entry = hmm_vma_walk_pmd,
.pte_hole = hmm_vma_walk_hole,
.hugetlb_entry = hmm_vma_walk_hugetlb_entry,
.test_walk = hmm_vma_walk_test,
};
/**
* hmm_range_fault - try to fault some address in a virtual address range
* @range: argument structure
*
* Return: the number of valid pages in range->pfns[] (from range start
* address), which may be zero. On error one of the following status codes
* can be returned:
*
* -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma
* (e.g., device file vma).
* -ENOMEM: Out of memory.
* -EPERM: Invalid permission (e.g., asking for write and range is read
* only).
* -EBUSY: The range has been invalidated and the caller needs to wait for
* the invalidation to finish.
* -EFAULT: A page was requested to be valid and could not be made valid
* ie it has no backing VMA or it is illegal to access
*
* This is similar to get_user_pages(), except that it can read the page tables
* without mutating them (ie causing faults).
*/
long hmm_range_fault(struct hmm_range *range)
{
struct hmm_vma_walk hmm_vma_walk = {
.range = range,
.last = range->start,
};
struct mm_struct *mm = range->notifier->mm;
int ret;
lockdep_assert_held(&mm->mmap_sem);
do {
/* If range is no longer valid force retry. */
if (mmu_interval_check_retry(range->notifier,
range->notifier_seq))
return -EBUSY;
ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
&hmm_walk_ops, &hmm_vma_walk);
} while (ret == -EBUSY);
if (ret)
return ret;
return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
EXPORT_SYMBOL(hmm_range_fault);