linux/kernel/memremap.c

529 lines
15 KiB
C
Raw Normal View History

/*
* Copyright(c) 2015 Intel Corporation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* 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.
*/
#include <linux/radix-tree.h>
#include <linux/device.h>
#include <linux/types.h>
#include <linux/pfn_t.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/memory_hotplug.h>
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.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 23:11:43 +00:00
#include <linux/swap.h>
#include <linux/swapops.h>
#ifndef ioremap_cache
/* temporary while we convert existing ioremap_cache users to memremap */
__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
{
return ioremap(offset, size);
}
#endif
#ifndef arch_memremap_wb
static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
{
return (__force void *)ioremap_cache(offset, size);
}
#endif
x86/mm: Add support to access boot related data in the clear Boot data (such as EFI related data) is not encrypted when the system is booted because UEFI/BIOS does not run with SME active. In order to access this data properly it needs to be mapped decrypted. Update early_memremap() to provide an arch specific routine to modify the pagetable protection attributes before they are applied to the new mapping. This is used to remove the encryption mask for boot related data. Update memremap() to provide an arch specific routine to determine if RAM remapping is allowed. RAM remapping will cause an encrypted mapping to be generated. By preventing RAM remapping, ioremap_cache() will be used instead, which will provide a decrypted mapping of the boot related data. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brijesh Singh <brijesh.singh@amd.com> Cc: Dave Young <dyoung@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Toshimitsu Kani <toshi.kani@hpe.com> Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/81fb6b4117a5df6b9f2eda342f81bbef4b23d2e5.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-07-17 21:10:16 +00:00
#ifndef arch_memremap_can_ram_remap
static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
unsigned long flags)
{
return true;
}
#endif
static void *try_ram_remap(resource_size_t offset, size_t size,
unsigned long flags)
{
unsigned long pfn = PHYS_PFN(offset);
/* In the simple case just return the existing linear address */
x86/mm: Add support to access boot related data in the clear Boot data (such as EFI related data) is not encrypted when the system is booted because UEFI/BIOS does not run with SME active. In order to access this data properly it needs to be mapped decrypted. Update early_memremap() to provide an arch specific routine to modify the pagetable protection attributes before they are applied to the new mapping. This is used to remove the encryption mask for boot related data. Update memremap() to provide an arch specific routine to determine if RAM remapping is allowed. RAM remapping will cause an encrypted mapping to be generated. By preventing RAM remapping, ioremap_cache() will be used instead, which will provide a decrypted mapping of the boot related data. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brijesh Singh <brijesh.singh@amd.com> Cc: Dave Young <dyoung@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Toshimitsu Kani <toshi.kani@hpe.com> Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/81fb6b4117a5df6b9f2eda342f81bbef4b23d2e5.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-07-17 21:10:16 +00:00
if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) &&
arch_memremap_can_ram_remap(offset, size, flags))
return __va(offset);
x86/mm: Add support to access boot related data in the clear Boot data (such as EFI related data) is not encrypted when the system is booted because UEFI/BIOS does not run with SME active. In order to access this data properly it needs to be mapped decrypted. Update early_memremap() to provide an arch specific routine to modify the pagetable protection attributes before they are applied to the new mapping. This is used to remove the encryption mask for boot related data. Update memremap() to provide an arch specific routine to determine if RAM remapping is allowed. RAM remapping will cause an encrypted mapping to be generated. By preventing RAM remapping, ioremap_cache() will be used instead, which will provide a decrypted mapping of the boot related data. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brijesh Singh <brijesh.singh@amd.com> Cc: Dave Young <dyoung@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Toshimitsu Kani <toshi.kani@hpe.com> Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/81fb6b4117a5df6b9f2eda342f81bbef4b23d2e5.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-07-17 21:10:16 +00:00
return NULL; /* fallback to arch_memremap_wb */
}
/**
* memremap() - remap an iomem_resource as cacheable memory
* @offset: iomem resource start address
* @size: size of remap
x86/mm: Add support to access boot related data in the clear Boot data (such as EFI related data) is not encrypted when the system is booted because UEFI/BIOS does not run with SME active. In order to access this data properly it needs to be mapped decrypted. Update early_memremap() to provide an arch specific routine to modify the pagetable protection attributes before they are applied to the new mapping. This is used to remove the encryption mask for boot related data. Update memremap() to provide an arch specific routine to determine if RAM remapping is allowed. RAM remapping will cause an encrypted mapping to be generated. By preventing RAM remapping, ioremap_cache() will be used instead, which will provide a decrypted mapping of the boot related data. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brijesh Singh <brijesh.singh@amd.com> Cc: Dave Young <dyoung@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Toshimitsu Kani <toshi.kani@hpe.com> Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/81fb6b4117a5df6b9f2eda342f81bbef4b23d2e5.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-07-17 21:10:16 +00:00
* @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC,
* MEMREMAP_ENC, MEMREMAP_DEC
*
* memremap() is "ioremap" for cases where it is known that the resource
* being mapped does not have i/o side effects and the __iomem
* annotation is not applicable. In the case of multiple flags, the different
* mapping types will be attempted in the order listed below until one of
* them succeeds.
*
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-26 20:57:28 +00:00
* MEMREMAP_WB - matches the default mapping for System RAM on
* the architecture. This is usually a read-allocate write-back cache.
* Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
* memremap() will bypass establishing a new mapping and instead return
* a pointer into the direct map.
*
* MEMREMAP_WT - establish a mapping whereby writes either bypass the
* cache or are written through to memory and never exist in a
* cache-dirty state with respect to program visibility. Attempts to
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-26 20:57:28 +00:00
* map System RAM with this mapping type will fail.
*
* MEMREMAP_WC - establish a writecombine mapping, whereby writes may
* be coalesced together (e.g. in the CPU's write buffers), but is otherwise
* uncached. Attempts to map System RAM with this mapping type will fail.
*/
void *memremap(resource_size_t offset, size_t size, unsigned long flags)
{
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-26 20:57:28 +00:00
int is_ram = region_intersects(offset, size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
void *addr = NULL;
if (!flags)
return NULL;
if (is_ram == REGION_MIXED) {
WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n",
&offset, (unsigned long) size);
return NULL;
}
/* Try all mapping types requested until one returns non-NULL */
if (flags & MEMREMAP_WB) {
/*
* MEMREMAP_WB is special in that it can be satisifed
* from the direct map. Some archs depend on the
* capability of memremap() to autodetect cases where
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-26 20:57:28 +00:00
* the requested range is potentially in System RAM.
*/
if (is_ram == REGION_INTERSECTS)
x86/mm: Add support to access boot related data in the clear Boot data (such as EFI related data) is not encrypted when the system is booted because UEFI/BIOS does not run with SME active. In order to access this data properly it needs to be mapped decrypted. Update early_memremap() to provide an arch specific routine to modify the pagetable protection attributes before they are applied to the new mapping. This is used to remove the encryption mask for boot related data. Update memremap() to provide an arch specific routine to determine if RAM remapping is allowed. RAM remapping will cause an encrypted mapping to be generated. By preventing RAM remapping, ioremap_cache() will be used instead, which will provide a decrypted mapping of the boot related data. Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Matt Fleming <matt@codeblueprint.co.uk> Reviewed-by: Borislav Petkov <bp@suse.de> Cc: Alexander Potapenko <glider@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brijesh Singh <brijesh.singh@amd.com> Cc: Dave Young <dyoung@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Toshimitsu Kani <toshi.kani@hpe.com> Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/81fb6b4117a5df6b9f2eda342f81bbef4b23d2e5.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-07-17 21:10:16 +00:00
addr = try_ram_remap(offset, size, flags);
if (!addr)
addr = arch_memremap_wb(offset, size);
}
/*
* If we don't have a mapping yet and other request flags are
* present then we will be attempting to establish a new virtual
* address mapping. Enforce that this mapping is not aliasing
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-26 20:57:28 +00:00
* System RAM.
*/
if (!addr && is_ram == REGION_INTERSECTS && flags != MEMREMAP_WB) {
WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n",
&offset, (unsigned long) size);
return NULL;
}
if (!addr && (flags & MEMREMAP_WT))
addr = ioremap_wt(offset, size);
if (!addr && (flags & MEMREMAP_WC))
addr = ioremap_wc(offset, size);
return addr;
}
EXPORT_SYMBOL(memremap);
void memunmap(void *addr)
{
if (is_vmalloc_addr(addr))
iounmap((void __iomem *) addr);
}
EXPORT_SYMBOL(memunmap);
static void devm_memremap_release(struct device *dev, void *res)
{
memunmap(*(void **)res);
}
static int devm_memremap_match(struct device *dev, void *res, void *match_data)
{
return *(void **)res == match_data;
}
void *devm_memremap(struct device *dev, resource_size_t offset,
size_t size, unsigned long flags)
{
void **ptr, *addr;
ptr = devres_alloc_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL,
dev_to_node(dev));
if (!ptr)
return ERR_PTR(-ENOMEM);
addr = memremap(offset, size, flags);
if (addr) {
*ptr = addr;
devres_add(dev, ptr);
} else {
devres_free(ptr);
return ERR_PTR(-ENXIO);
}
return addr;
}
EXPORT_SYMBOL(devm_memremap);
void devm_memunmap(struct device *dev, void *addr)
{
WARN_ON(devres_release(dev, devm_memremap_release,
devm_memremap_match, addr));
}
EXPORT_SYMBOL(devm_memunmap);
#ifdef CONFIG_ZONE_DEVICE
static DEFINE_MUTEX(pgmap_lock);
static RADIX_TREE(pgmap_radix, GFP_KERNEL);
#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
struct page_map {
struct resource res;
struct percpu_ref *ref;
struct dev_pagemap pgmap;
struct vmem_altmap altmap;
};
static unsigned long order_at(struct resource *res, unsigned long pgoff)
{
unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
unsigned long nr_pages, mask;
nr_pages = PHYS_PFN(resource_size(res));
if (nr_pages == pgoff)
return ULONG_MAX;
/*
* What is the largest aligned power-of-2 range available from
* this resource pgoff to the end of the resource range,
* considering the alignment of the current pgoff?
*/
mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
if (!mask)
return ULONG_MAX;
return find_first_bit(&mask, BITS_PER_LONG);
}
#define foreach_order_pgoff(res, order, pgoff) \
for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
pgoff += 1UL << order, order = order_at((res), pgoff))
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.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 23:11:43 +00:00
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
int device_private_entry_fault(struct vm_area_struct *vma,
unsigned long addr,
swp_entry_t entry,
unsigned int flags,
pmd_t *pmdp)
{
struct page *page = device_private_entry_to_page(entry);
/*
* The page_fault() callback must migrate page back to system memory
* so that CPU can access it. This might fail for various reasons
* (device issue, device was unsafely unplugged, ...). When such
* error conditions happen, the callback must return VM_FAULT_SIGBUS.
*
* Note that because memory cgroup charges are accounted to the device
* memory, this should never fail because of memory restrictions (but
* allocation of regular system page might still fail because we are
* out of memory).
*
* There is a more in-depth description of what that callback can and
* cannot do, in include/linux/memremap.h
*/
return page->pgmap->page_fault(vma, addr, page, flags, pmdp);
}
EXPORT_SYMBOL(device_private_entry_fault);
#endif /* CONFIG_DEVICE_PRIVATE */
static void pgmap_radix_release(struct resource *res)
{
unsigned long pgoff, order;
mutex_lock(&pgmap_lock);
foreach_order_pgoff(res, order, pgoff)
radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
mutex_unlock(&pgmap_lock);
synchronize_rcu();
}
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
static unsigned long pfn_first(struct page_map *page_map)
{
struct dev_pagemap *pgmap = &page_map->pgmap;
const struct resource *res = &page_map->res;
struct vmem_altmap *altmap = pgmap->altmap;
unsigned long pfn;
pfn = res->start >> PAGE_SHIFT;
if (altmap)
pfn += vmem_altmap_offset(altmap);
return pfn;
}
static unsigned long pfn_end(struct page_map *page_map)
{
const struct resource *res = &page_map->res;
return (res->start + resource_size(res)) >> PAGE_SHIFT;
}
#define for_each_device_pfn(pfn, map) \
for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++)
static void devm_memremap_pages_release(struct device *dev, void *data)
{
struct page_map *page_map = data;
struct resource *res = &page_map->res;
resource_size_t align_start, align_size;
struct dev_pagemap *pgmap = &page_map->pgmap;
mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash The x86 conversion to the generic GUP code included a small change which causes crashes and data corruption in the pmem code - not good. The root cause is that the /dev/pmem driver code implicitly relies on the x86 get_user_pages() implementation doing a get_page() on the page refcount, because get_page() does a get_zone_device_page() which properly refcounts pmem's separate page struct arrays that are not present in the regular page struct structures. (The pmem driver does this because it can cover huge memory areas.) But the x86 conversion to the generic GUP code changed the get_page() to page_cache_get_speculative() which is faster but doesn't do the get_zone_device_page() call the pmem code relies on. One way to solve the regression would be to change the generic GUP code to use get_page(), but that would slow things down a bit and punish other generic-GUP using architectures for an x86-ism they did not care about. (Arguably the pmem driver was probably not working reliably for them: but nvdimm is an Intel feature, so non-x86 exposure is probably still limited.) So restructure the pmem code's interface with the MM instead: get rid of the get/put_zone_device_page() distinction, integrate put_zone_device_page() into __put_page() and and restructure the pmem completion-wait and teardown machinery: Kirill points out that the calls to {get,put}_dev_pagemap() can be removed from the mm fast path if we take a single get_dev_pagemap() reference to signify that the page is alive and use the final put of the page to drop that reference. This does require some care to make sure that any waits for the percpu_ref to drop to zero occur *after* devm_memremap_page_release(), since it now maintains its own elevated reference. This speeds up things while also making the pmem refcounting more robust going forward. Suggested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/149339998297.24933.1129582806028305912.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-28 17:23:37 +00:00
unsigned long pfn;
for_each_device_pfn(pfn, page_map)
put_page(pfn_to_page(pfn));
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
if (percpu_ref_tryget_live(pgmap->ref)) {
dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
percpu_ref_put(pgmap->ref);
}
/* pages are dead and unused, undo the arch mapping */
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(resource_size(res), SECTION_SIZE);
mm: fix devm_memremap_pages crash, use mem_hotplug_{begin, done} Both arch_add_memory() and arch_remove_memory() expect a single threaded context. For example, arch/x86/mm/init_64.c::kernel_physical_mapping_init() does not hold any locks over this check and branch: if (pgd_val(*pgd)) { pud = (pud_t *)pgd_page_vaddr(*pgd); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); continue; } pud = alloc_low_page(); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); The result is that two threads calling devm_memremap_pages() simultaneously can end up colliding on pgd initialization. This leads to crash signatures like the following where the loser of the race initializes the wrong pgd entry: BUG: unable to handle kernel paging request at ffff888ebfff0000 IP: memcpy_erms+0x6/0x10 PGD 2f8e8fc067 PUD 0 /* <---- Invalid PUD */ Oops: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 54 PID: 3818 Comm: systemd-udevd Not tainted 4.6.7+ #13 task: ffff882fac290040 ti: ffff882f887a4000 task.ti: ffff882f887a4000 RIP: memcpy_erms+0x6/0x10 [..] Call Trace: ? pmem_do_bvec+0x205/0x370 [nd_pmem] ? blk_queue_enter+0x3a/0x280 pmem_rw_page+0x38/0x80 [nd_pmem] bdev_read_page+0x84/0xb0 Hold the standard memory hotplug mutex over calls to arch_{add,remove}_memory(). Fixes: 41e94a851304 ("add devm_memremap_pages") Link: http://lkml.kernel.org/r/148357647831.9498.12606007370121652979.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Cc: Christoph Hellwig <hch@lst.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-11 00:57:36 +00:00
mem_hotplug_begin();
arch_remove_memory(align_start, align_size);
mm: fix devm_memremap_pages crash, use mem_hotplug_{begin, done} Both arch_add_memory() and arch_remove_memory() expect a single threaded context. For example, arch/x86/mm/init_64.c::kernel_physical_mapping_init() does not hold any locks over this check and branch: if (pgd_val(*pgd)) { pud = (pud_t *)pgd_page_vaddr(*pgd); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); continue; } pud = alloc_low_page(); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); The result is that two threads calling devm_memremap_pages() simultaneously can end up colliding on pgd initialization. This leads to crash signatures like the following where the loser of the race initializes the wrong pgd entry: BUG: unable to handle kernel paging request at ffff888ebfff0000 IP: memcpy_erms+0x6/0x10 PGD 2f8e8fc067 PUD 0 /* <---- Invalid PUD */ Oops: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 54 PID: 3818 Comm: systemd-udevd Not tainted 4.6.7+ #13 task: ffff882fac290040 ti: ffff882f887a4000 task.ti: ffff882f887a4000 RIP: memcpy_erms+0x6/0x10 [..] Call Trace: ? pmem_do_bvec+0x205/0x370 [nd_pmem] ? blk_queue_enter+0x3a/0x280 pmem_rw_page+0x38/0x80 [nd_pmem] bdev_read_page+0x84/0xb0 Hold the standard memory hotplug mutex over calls to arch_{add,remove}_memory(). Fixes: 41e94a851304 ("add devm_memremap_pages") Link: http://lkml.kernel.org/r/148357647831.9498.12606007370121652979.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Cc: Christoph Hellwig <hch@lst.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-11 00:57:36 +00:00
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
pgmap_radix_release(res);
dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
"%s: failed to free all reserved pages\n", __func__);
}
/* assumes rcu_read_lock() held at entry */
struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
{
struct page_map *page_map;
WARN_ON_ONCE(!rcu_read_lock_held());
page_map = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
return page_map ? &page_map->pgmap : NULL;
}
/**
* devm_memremap_pages - remap and provide memmap backing for the given resource
* @dev: hosting device for @res
* @res: "host memory" address range
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
* @ref: a live per-cpu reference count
* @altmap: optional descriptor for allocating the memmap from @res
*
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
* Notes:
* 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time
mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash The x86 conversion to the generic GUP code included a small change which causes crashes and data corruption in the pmem code - not good. The root cause is that the /dev/pmem driver code implicitly relies on the x86 get_user_pages() implementation doing a get_page() on the page refcount, because get_page() does a get_zone_device_page() which properly refcounts pmem's separate page struct arrays that are not present in the regular page struct structures. (The pmem driver does this because it can cover huge memory areas.) But the x86 conversion to the generic GUP code changed the get_page() to page_cache_get_speculative() which is faster but doesn't do the get_zone_device_page() call the pmem code relies on. One way to solve the regression would be to change the generic GUP code to use get_page(), but that would slow things down a bit and punish other generic-GUP using architectures for an x86-ism they did not care about. (Arguably the pmem driver was probably not working reliably for them: but nvdimm is an Intel feature, so non-x86 exposure is probably still limited.) So restructure the pmem code's interface with the MM instead: get rid of the get/put_zone_device_page() distinction, integrate put_zone_device_page() into __put_page() and and restructure the pmem completion-wait and teardown machinery: Kirill points out that the calls to {get,put}_dev_pagemap() can be removed from the mm fast path if we take a single get_dev_pagemap() reference to signify that the page is alive and use the final put of the page to drop that reference. This does require some care to make sure that any waits for the percpu_ref to drop to zero occur *after* devm_memremap_page_release(), since it now maintains its own elevated reference. This speeds up things while also making the pmem refcounting more robust going forward. Suggested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/149339998297.24933.1129582806028305912.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-28 17:23:37 +00:00
* (or devm release event). The expected order of events is that @ref has
* been through percpu_ref_kill() before devm_memremap_pages_release(). The
* wait for the completion of all references being dropped and
* percpu_ref_exit() must occur after devm_memremap_pages_release().
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
*
* 2/ @res is expected to be a host memory range that could feasibly be
* treated as a "System RAM" range, i.e. not a device mmio range, but
* this is not enforced.
*/
void *devm_memremap_pages(struct device *dev, struct resource *res,
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
struct percpu_ref *ref, struct vmem_altmap *altmap)
{
resource_size_t align_start, align_size, align_end;
unsigned long pfn, pgoff, order;
pgprot_t pgprot = PAGE_KERNEL;
struct dev_pagemap *pgmap;
struct page_map *page_map;
int error, nid, is_ram, i = 0;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start;
Merge branch 'core-resources-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull ram resource handling changes from Ingo Molnar: "Core kernel resource handling changes to support NVDIMM error injection. This tree introduces a new I/O resource type, IORESOURCE_SYSTEM_RAM, for System RAM while keeping the current IORESOURCE_MEM type bit set for all memory-mapped ranges (including System RAM) for backward compatibility. With this resource flag it no longer takes a strcmp() loop through the resource tree to find "System RAM" resources. The new resource type is then used to extend ACPI/APEI error injection facility to also support NVDIMM" * 'core-resources-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: ACPI/EINJ: Allow memory error injection to NVDIMM resource: Kill walk_iomem_res() x86/kexec: Remove walk_iomem_res() call with GART type x86, kexec, nvdimm: Use walk_iomem_res_desc() for iomem search resource: Add walk_iomem_res_desc() memremap: Change region_intersects() to take @flags and @desc arm/samsung: Change s3c_pm_run_res() to use System RAM type resource: Change walk_system_ram() to use System RAM type drivers: Initialize resource entry to zero xen, mm: Set IORESOURCE_SYSTEM_RAM to System RAM kexec: Set IORESOURCE_SYSTEM_RAM for System RAM arch: Set IORESOURCE_SYSTEM_RAM flag for System RAM ia64: Set System RAM type and descriptor x86/e820: Set System RAM type and descriptor resource: Add I/O resource descriptor resource: Handle resource flags properly resource: Add System RAM resource type
2016-03-14 22:15:51 +00:00
is_ram = region_intersects(align_start, align_size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
if (is_ram == REGION_MIXED) {
WARN_ONCE(1, "%s attempted on mixed region %pr\n",
__func__, res);
return ERR_PTR(-ENXIO);
}
if (is_ram == REGION_INTERSECTS)
return __va(res->start);
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
if (!ref)
return ERR_PTR(-EINVAL);
page_map = devres_alloc_node(devm_memremap_pages_release,
sizeof(*page_map), GFP_KERNEL, dev_to_node(dev));
if (!page_map)
return ERR_PTR(-ENOMEM);
pgmap = &page_map->pgmap;
memcpy(&page_map->res, res, sizeof(*res));
pgmap->dev = dev;
if (altmap) {
memcpy(&page_map->altmap, altmap, sizeof(*altmap));
pgmap->altmap = &page_map->altmap;
}
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
pgmap->ref = ref;
pgmap->res = &page_map->res;
mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.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 23:11:43 +00:00
pgmap->type = MEMORY_DEVICE_HOST;
pgmap->page_fault = NULL;
pgmap->page_free = NULL;
pgmap->data = NULL;
mutex_lock(&pgmap_lock);
error = 0;
align_end = align_start + align_size - 1;
foreach_order_pgoff(res, order, pgoff) {
struct dev_pagemap *dup;
rcu_read_lock();
dup = find_dev_pagemap(res->start + PFN_PHYS(pgoff));
rcu_read_unlock();
if (dup) {
dev_err(dev, "%s: %pr collides with mapping for %s\n",
__func__, res, dev_name(dup->dev));
error = -EBUSY;
break;
}
error = __radix_tree_insert(&pgmap_radix,
PHYS_PFN(res->start) + pgoff, order, page_map);
if (error) {
dev_err(dev, "%s: failed: %d\n", __func__, error);
break;
}
}
mutex_unlock(&pgmap_lock);
if (error)
goto err_radix;
nid = dev_to_node(dev);
if (nid < 0)
nid = numa_mem_id();
error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
align_size);
if (error)
goto err_pfn_remap;
mm: fix devm_memremap_pages crash, use mem_hotplug_{begin, done} Both arch_add_memory() and arch_remove_memory() expect a single threaded context. For example, arch/x86/mm/init_64.c::kernel_physical_mapping_init() does not hold any locks over this check and branch: if (pgd_val(*pgd)) { pud = (pud_t *)pgd_page_vaddr(*pgd); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); continue; } pud = alloc_low_page(); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); The result is that two threads calling devm_memremap_pages() simultaneously can end up colliding on pgd initialization. This leads to crash signatures like the following where the loser of the race initializes the wrong pgd entry: BUG: unable to handle kernel paging request at ffff888ebfff0000 IP: memcpy_erms+0x6/0x10 PGD 2f8e8fc067 PUD 0 /* <---- Invalid PUD */ Oops: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 54 PID: 3818 Comm: systemd-udevd Not tainted 4.6.7+ #13 task: ffff882fac290040 ti: ffff882f887a4000 task.ti: ffff882f887a4000 RIP: memcpy_erms+0x6/0x10 [..] Call Trace: ? pmem_do_bvec+0x205/0x370 [nd_pmem] ? blk_queue_enter+0x3a/0x280 pmem_rw_page+0x38/0x80 [nd_pmem] bdev_read_page+0x84/0xb0 Hold the standard memory hotplug mutex over calls to arch_{add,remove}_memory(). Fixes: 41e94a851304 ("add devm_memremap_pages") Link: http://lkml.kernel.org/r/148357647831.9498.12606007370121652979.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Cc: Christoph Hellwig <hch@lst.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-11 00:57:36 +00:00
mem_hotplug_begin();
mm, memory_hotplug: replace for_device by want_memblock in arch_add_memory arch_add_memory gets for_device argument which then controls whether we want to create memblocks for created memory sections. Simplify the logic by telling whether we want memblocks directly rather than going through pointless negation. This also makes the api easier to understand because it is clear what we want rather than nothing telling for_device which can mean anything. This shouldn't introduce any functional change. Link: http://lkml.kernel.org/r/20170515085827.16474-13-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Reza Arbab <arbab@linux.vnet.ibm.com> Cc: Tobias Regnery <tobias.regnery@gmail.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-06 22:38:21 +00:00
error = arch_add_memory(nid, align_start, align_size, false);
mm, memory_hotplug: do not associate hotadded memory to zones until online The current memory hotplug implementation relies on having all the struct pages associate with a zone/node during the physical hotplug phase (arch_add_memory->__add_pages->__add_section->__add_zone). In the vast majority of cases this means that they are added to ZONE_NORMAL. This has been so since 9d99aaa31f59 ("[PATCH] x86_64: Support memory hotadd without sparsemem") and it wasn't a big deal back then because movable onlining didn't exist yet. Much later memory hotplug wanted to (ab)use ZONE_MOVABLE for movable onlining 511c2aba8f07 ("mm, memory-hotplug: dynamic configure movable memory and portion memory") and then things got more complicated. Rather than reconsidering the zone association which was no longer needed (because the memory hotplug already depended on SPARSEMEM) a convoluted semantic of zone shifting has been developed. Only the currently last memblock or the one adjacent to the zone_movable can be onlined movable. This essentially means that the online type changes as the new memblocks are added. Let's simulate memory hot online manually $ echo 0x100000000 > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory32/valid_zones Normal Movable $ echo $((0x100000000+(128<<20))) > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal Movable $ echo $((0x100000000+2*(128<<20))) > /sys/devices/system/memory/probe $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal /sys/devices/system/memory/memory34/valid_zones:Normal Movable $ echo online_movable > /sys/devices/system/memory/memory34/state $ grep . /sys/devices/system/memory/memory3?/valid_zones /sys/devices/system/memory/memory32/valid_zones:Normal /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Movable Normal This is an awkward semantic because an udev event is sent as soon as the block is onlined and an udev handler might want to online it based on some policy (e.g. association with a node) but it will inherently race with new blocks showing up. This patch changes the physical online phase to not associate pages with any zone at all. All the pages are just marked reserved and wait for the onlining phase to be associated with the zone as per the online request. There are only two requirements - existing ZONE_NORMAL and ZONE_MOVABLE cannot overlap - ZONE_NORMAL precedes ZONE_MOVABLE in physical addresses the latter one is not an inherent requirement and can be changed in the future. It preserves the current behavior and made the code slightly simpler. This is subject to change in future. This means that the same physical online steps as above will lead to the following state: Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Normal Movable /sys/devices/system/memory/memory32/valid_zones:Normal Movable /sys/devices/system/memory/memory33/valid_zones:Normal Movable /sys/devices/system/memory/memory34/valid_zones:Movable Implementation: The current move_pfn_range is reimplemented to check the above requirements (allow_online_pfn_range) and then updates the respective zone (move_pfn_range_to_zone), the pgdat and links all the pages in the pfn range with the zone/node. __add_pages is updated to not require the zone and only initializes sections in the range. This allowed to simplify the arch_add_memory code (s390 could get rid of quite some of code). devm_memremap_pages is the only user of arch_add_memory which relies on the zone association because it only hooks into the memory hotplug only half way. It uses it to associate the new memory with ZONE_DEVICE but doesn't allow it to be {on,off}lined via sysfs. This means that this particular code path has to call move_pfn_range_to_zone explicitly. The original zone shifting code is kept in place and will be removed in the follow up patch for an easier review. Please note that this patch also changes the original behavior when offlining a memory block adjacent to another zone (Normal vs. Movable) used to allow to change its movable type. This will be handled later. [richard.weiyang@gmail.com: simplify zone_intersects()] Link: http://lkml.kernel.org/r/20170616092335.5177-1-richard.weiyang@gmail.com [richard.weiyang@gmail.com: remove duplicate call for set_page_links] Link: http://lkml.kernel.org/r/20170616092335.5177-2-richard.weiyang@gmail.com [akpm@linux-foundation.org: remove unused local `i'] Link: http://lkml.kernel.org/r/20170515085827.16474-12-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Wei Yang <richard.weiyang@gmail.com> Tested-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Reza Arbab <arbab@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # For s390 bits Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Daniel Kiper <daniel.kiper@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Igor Mammedov <imammedo@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Tobias Regnery <tobias.regnery@gmail.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-06 22:38:11 +00:00
if (!error)
move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
align_start >> PAGE_SHIFT,
align_size >> PAGE_SHIFT);
mm: fix devm_memremap_pages crash, use mem_hotplug_{begin, done} Both arch_add_memory() and arch_remove_memory() expect a single threaded context. For example, arch/x86/mm/init_64.c::kernel_physical_mapping_init() does not hold any locks over this check and branch: if (pgd_val(*pgd)) { pud = (pud_t *)pgd_page_vaddr(*pgd); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); continue; } pud = alloc_low_page(); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); The result is that two threads calling devm_memremap_pages() simultaneously can end up colliding on pgd initialization. This leads to crash signatures like the following where the loser of the race initializes the wrong pgd entry: BUG: unable to handle kernel paging request at ffff888ebfff0000 IP: memcpy_erms+0x6/0x10 PGD 2f8e8fc067 PUD 0 /* <---- Invalid PUD */ Oops: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 54 PID: 3818 Comm: systemd-udevd Not tainted 4.6.7+ #13 task: ffff882fac290040 ti: ffff882f887a4000 task.ti: ffff882f887a4000 RIP: memcpy_erms+0x6/0x10 [..] Call Trace: ? pmem_do_bvec+0x205/0x370 [nd_pmem] ? blk_queue_enter+0x3a/0x280 pmem_rw_page+0x38/0x80 [nd_pmem] bdev_read_page+0x84/0xb0 Hold the standard memory hotplug mutex over calls to arch_{add,remove}_memory(). Fixes: 41e94a851304 ("add devm_memremap_pages") Link: http://lkml.kernel.org/r/148357647831.9498.12606007370121652979.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com> Cc: Christoph Hellwig <hch@lst.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-11 00:57:36 +00:00
mem_hotplug_done();
if (error)
goto err_add_memory;
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
for_each_device_pfn(pfn, page_map) {
struct page *page = pfn_to_page(pfn);
/*
* ZONE_DEVICE pages union ->lru with a ->pgmap back
* pointer. It is a bug if a ZONE_DEVICE page is ever
* freed or placed on a driver-private list. Seed the
* storage with LIST_POISON* values.
*/
list_del(&page->lru);
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
page->pgmap = pgmap;
mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash The x86 conversion to the generic GUP code included a small change which causes crashes and data corruption in the pmem code - not good. The root cause is that the /dev/pmem driver code implicitly relies on the x86 get_user_pages() implementation doing a get_page() on the page refcount, because get_page() does a get_zone_device_page() which properly refcounts pmem's separate page struct arrays that are not present in the regular page struct structures. (The pmem driver does this because it can cover huge memory areas.) But the x86 conversion to the generic GUP code changed the get_page() to page_cache_get_speculative() which is faster but doesn't do the get_zone_device_page() call the pmem code relies on. One way to solve the regression would be to change the generic GUP code to use get_page(), but that would slow things down a bit and punish other generic-GUP using architectures for an x86-ism they did not care about. (Arguably the pmem driver was probably not working reliably for them: but nvdimm is an Intel feature, so non-x86 exposure is probably still limited.) So restructure the pmem code's interface with the MM instead: get rid of the get/put_zone_device_page() distinction, integrate put_zone_device_page() into __put_page() and and restructure the pmem completion-wait and teardown machinery: Kirill points out that the calls to {get,put}_dev_pagemap() can be removed from the mm fast path if we take a single get_dev_pagemap() reference to signify that the page is alive and use the final put of the page to drop that reference. This does require some care to make sure that any waits for the percpu_ref to drop to zero occur *after* devm_memremap_page_release(), since it now maintains its own elevated reference. This speeds up things while also making the pmem refcounting more robust going forward. Suggested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/149339998297.24933.1129582806028305912.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-28 17:23:37 +00:00
percpu_ref_get(ref);
if (!(++i % 1024))
cond_resched();
mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Cc: Dave Hansen <dave@sr71.net> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:56:49 +00:00
}
devres_add(dev, page_map);
return __va(res->start);
err_add_memory:
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
err_pfn_remap:
err_radix:
pgmap_radix_release(res);
devres_free(page_map);
return ERR_PTR(error);
}
EXPORT_SYMBOL(devm_memremap_pages);
unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
{
/* number of pfns from base where pfn_to_page() is valid */
return altmap->reserve + altmap->free;
}
void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
{
altmap->alloc -= nr_pfns;
}
struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
{
/*
* 'memmap_start' is the virtual address for the first "struct
* page" in this range of the vmemmap array. In the case of
* CONFIG_SPARSEMEM_VMEMMAP a page_to_pfn conversion is simple
* pointer arithmetic, so we can perform this to_vmem_altmap()
* conversion without concern for the initialization state of
* the struct page fields.
*/
struct page *page = (struct page *) memmap_start;
struct dev_pagemap *pgmap;
/*
* Unconditionally retrieve a dev_pagemap associated with the
* given physical address, this is only for use in the
* arch_{add|remove}_memory() for setting up and tearing down
* the memmap.
*/
rcu_read_lock();
pgmap = find_dev_pagemap(__pfn_to_phys(page_to_pfn(page)));
rcu_read_unlock();
return pgmap ? pgmap->altmap : NULL;
}
#endif /* CONFIG_ZONE_DEVICE */
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC)
void put_zone_device_private_or_public_page(struct page *page)
{
int count = page_ref_dec_return(page);
/*
* If refcount is 1 then page is freed and refcount is stable as nobody
* holds a reference on the page.
*/
if (count == 1) {
/* Clear Active bit in case of parallel mark_page_accessed */
__ClearPageActive(page);
__ClearPageWaiters(page);
page->mapping = NULL;
mem_cgroup_uncharge(page);
page->pgmap->page_free(page, page->pgmap->data);
} else if (!count)
__put_page(page);
}
EXPORT_SYMBOL(put_zone_device_private_or_public_page);
#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */