From c62da0c35d58518ddb26ff641d2485596567fd96 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Fri, 10 Apr 2020 14:33:05 -0700 Subject: mm/vma: define a default value for VM_DATA_DEFAULT_FLAGS There are many platforms with exact same value for VM_DATA_DEFAULT_FLAGS This creates a default value for VM_DATA_DEFAULT_FLAGS in line with the existing VM_STACK_DEFAULT_FLAGS. While here, also define some more macros with standard VMA access flag combinations that are used frequently across many platforms. Apart from simplification, this reduces code duplication as well. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Acked-by: Geert Uytterhoeven Cc: Richard Henderson Cc: Vineet Gupta Cc: Russell King Cc: Catalin Marinas Cc: Mark Salter Cc: Guo Ren Cc: Yoshinori Sato Cc: Brian Cain Cc: Tony Luck Cc: Michal Simek Cc: Ralf Baechle Cc: Paul Burton Cc: Nick Hu Cc: Ley Foon Tan Cc: Jonas Bonn Cc: "James E.J. Bottomley" Cc: Michael Ellerman Cc: Paul Walmsley Cc: Heiko Carstens Cc: Rich Felker Cc: "David S. Miller" Cc: Guan Xuetao Cc: Thomas Gleixner Cc: Jeff Dike Cc: Chris Zankel Link: http://lkml.kernel.org/r/1583391014-8170-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- arch/s390/include/asm/page.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index f2d4c1bd3429..cc98f9b78fd4 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -181,8 +181,7 @@ int arch_make_page_accessible(struct page *page); #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC #include #include -- cgit v1.2.3 From 6cb4d9a2870d2062e34c93bfef4d52fca3fe42d1 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Fri, 10 Apr 2020 14:33:09 -0700 Subject: mm/vma: introduce VM_ACCESS_FLAGS There are many places where all basic VMA access flags (read, write, exec) are initialized or checked against as a group. One such example is during page fault. Existing vma_is_accessible() wrapper already creates the notion of VMA accessibility as a group access permissions. Hence lets just create VM_ACCESS_FLAGS (VM_READ|VM_WRITE|VM_EXEC) which will not only reduce code duplication but also extend the VMA accessibility concept in general. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Cc: Russell King Cc: Catalin Marinas Cc: Mark Salter Cc: Nick Hu Cc: Ley Foon Tan Cc: Michael Ellerman Cc: Heiko Carstens Cc: Yoshinori Sato Cc: Guan Xuetao Cc: Dave Hansen Cc: Thomas Gleixner Cc: Rob Springer Cc: Greg Kroah-Hartman Cc: Geert Uytterhoeven Link: http://lkml.kernel.org/r/1583391014-8170-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- arch/arm/mm/fault.c | 2 +- arch/arm64/mm/fault.c | 2 +- arch/nds32/mm/fault.c | 2 +- arch/powerpc/mm/book3s64/pkeys.c | 2 +- arch/s390/mm/fault.c | 2 +- arch/unicore32/mm/fault.c | 2 +- arch/x86/mm/pkeys.c | 2 +- drivers/staging/gasket/gasket_core.c | 2 +- include/linux/mm.h | 6 +++++- mm/mmap.c | 2 +- mm/mprotect.c | 4 ++-- 11 files changed, 16 insertions(+), 12 deletions(-) (limited to 'arch/s390') diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index b598e6978b29..2dd5c41cbb8d 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -189,7 +189,7 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs) */ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) { - unsigned int mask = VM_READ | VM_WRITE | VM_EXEC; + unsigned int mask = VM_ACCESS_FLAGS; if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) mask = VM_WRITE; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 1027851d469a..c9cedc0432d2 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -445,7 +445,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, const struct fault_info *inf; struct mm_struct *mm = current->mm; vm_fault_t fault, major = 0; - unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; + unsigned long vm_flags = VM_ACCESS_FLAGS; unsigned int mm_flags = FAULT_FLAG_DEFAULT; if (kprobe_page_fault(regs, esr)) diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c index 0cf0c08c7da2..f331e533edc2 100644 --- a/arch/nds32/mm/fault.c +++ b/arch/nds32/mm/fault.c @@ -79,7 +79,7 @@ void do_page_fault(unsigned long entry, unsigned long addr, struct vm_area_struct *vma; int si_code; vm_fault_t fault; - unsigned int mask = VM_READ | VM_WRITE | VM_EXEC; + unsigned int mask = VM_ACCESS_FLAGS; unsigned int flags = FAULT_FLAG_DEFAULT; error_code = error_code & (ITYPE_mskINST | ITYPE_mskETYPE); diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 07527f1ed108..1199fc2bfaec 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -315,7 +315,7 @@ int __execute_only_pkey(struct mm_struct *mm) static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) { /* Do this check first since the vm_flags should be hot */ - if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC) + if ((vma->vm_flags & VM_ACCESS_FLAGS) != VM_EXEC) return false; return (vma_pkey(vma) == vma->vm_mm->context.execute_only_pkey); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index d56f67745e3e..9822a1fd1c6b 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -580,7 +580,7 @@ void do_dat_exception(struct pt_regs *regs) int access; vm_fault_t fault; - access = VM_READ | VM_EXEC | VM_WRITE; + access = VM_ACCESS_FLAGS; fault = do_exception(regs, access); if (unlikely(fault)) do_fault_error(regs, access, fault); diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c index a9bd08fbe588..3022104aa613 100644 --- a/arch/unicore32/mm/fault.c +++ b/arch/unicore32/mm/fault.c @@ -149,7 +149,7 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs) */ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) { - unsigned int mask = VM_READ | VM_WRITE | VM_EXEC; + unsigned int mask = VM_ACCESS_FLAGS; if (!(fsr ^ 0x12)) /* write? */ mask = VM_WRITE; diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index c6f84c0b5d7a..8873ed1438a9 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -63,7 +63,7 @@ int __execute_only_pkey(struct mm_struct *mm) static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma) { /* Do this check first since the vm_flags should be hot */ - if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC) + if ((vma->vm_flags & VM_ACCESS_FLAGS) != VM_EXEC) return false; if (vma_pkey(vma) != vma->vm_mm->context.execute_only_pkey) return false; diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index cd181a64f737..8e0575fcb4c8 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -689,7 +689,7 @@ static bool gasket_mmap_has_permissions(struct gasket_dev *gasket_dev, /* Make sure that no wrong flags are set. */ requested_permissions = - (vma->vm_flags & (VM_WRITE | VM_READ | VM_EXEC)); + (vma->vm_flags & VM_ACCESS_FLAGS); if (requested_permissions & ~(bar_permissions)) { dev_dbg(gasket_dev->dev, "Attempting to map a region with requested permissions 0x%x, but region has permissions 0x%x.\n", diff --git a/include/linux/mm.h b/include/linux/mm.h index 33076fa149c8..4db1522d7c48 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -369,6 +369,10 @@ extern unsigned int kobjsize(const void *objp); #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) +/* VMA basic access permission flags */ +#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) + + /* * Special vmas that are non-mergable, non-mlock()able. */ @@ -646,7 +650,7 @@ static inline bool vma_is_foreign(struct vm_area_struct *vma) static inline bool vma_is_accessible(struct vm_area_struct *vma) { - return vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC); + return vma->vm_flags & VM_ACCESS_FLAGS; } #ifdef CONFIG_SHMEM diff --git a/mm/mmap.c b/mm/mmap.c index de07bbc0e21f..f609e9ec4a25 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1224,7 +1224,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && - !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC|VM_SOFTDIRTY)) && + !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 1d823b050329..494192ca954b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -419,7 +419,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, */ if (arch_has_pfn_modify_check() && (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && - (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) { + (newflags & VM_ACCESS_FLAGS) == 0) { pgprot_t new_pgprot = vm_get_page_prot(newflags); error = walk_page_range(current->mm, start, end, @@ -598,7 +598,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, newflags |= (vma->vm_flags & ~mask_off_old_flags); /* newflags >> 4 shift VM_MAY% in place of VM_% */ - if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) { + if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) { error = -EACCES; goto out; } -- cgit v1.2.3 From f5637d3b42ab0465ef71d5fb8461bce97fba95e8 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 10 Apr 2020 14:33:21 -0700 Subject: mm/memory_hotplug: rename mhp_restrictions to mhp_params The mhp_restrictions struct really doesn't specify anything resembling a restriction anymore so rename it to be mhp_params as it is a list of extended parameters. Signed-off-by: Logan Gunthorpe Signed-off-by: Andrew Morton Reviewed-by: David Hildenbrand Reviewed-by: Dan Williams Acked-by: Michal Hocko Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Dave Hansen Cc: Eric Badger Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/20200306170846.9333-3-logang@deltatee.com Signed-off-by: Linus Torvalds --- arch/arm64/mm/mmu.c | 4 ++-- arch/ia64/mm/init.c | 4 ++-- arch/powerpc/mm/mem.c | 4 ++-- arch/s390/mm/init.c | 6 +++--- arch/sh/mm/init.c | 4 ++-- arch/x86/mm/init_32.c | 4 ++-- arch/x86/mm/init_64.c | 8 ++++---- include/linux/memory_hotplug.h | 16 ++++++++-------- mm/memory_hotplug.c | 8 ++++---- mm/memremap.c | 8 ++++---- 10 files changed, 33 insertions(+), 33 deletions(-) (limited to 'arch/s390') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9b08f7c7e6f0..6d4e9c2b4ed0 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1374,7 +1374,7 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) } int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { int ret, flags = 0; @@ -1387,7 +1387,7 @@ int arch_add_memory(int nid, u64 start, u64 size, memblock_clear_nomap(start, size); ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, - restrictions); + params); if (ret) __remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index b01d68a2d5d9..97bbc23ea1e3 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -670,13 +670,13 @@ mem_init (void) #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; - ret = __add_pages(nid, start_pfn, nr_pages, restrictions); + ret = __add_pages(nid, start_pfn, nr_pages, params); if (ret) printk("%s: Problem encountered in __add_pages() as ret=%d\n", __func__, ret); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9b4f5fb719e0..e1cc58115816 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -122,7 +122,7 @@ static void flush_dcache_range_chunked(unsigned long start, unsigned long stop, } int __ref arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; @@ -138,7 +138,7 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, return -EFAULT; } - return __add_pages(nid, start_pfn, nr_pages, restrictions); + return __add_pages(nid, start_pfn, nr_pages, params); } void __ref arch_remove_memory(int nid, u64 start, u64 size, diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index ac44bd76db4b..e9e4a7abd0cc 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -268,20 +268,20 @@ device_initcall(s390_cma_mem_init); #endif /* CONFIG_CMA */ int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = PFN_DOWN(start); unsigned long size_pages = PFN_DOWN(size); int rc; - if (WARN_ON_ONCE(restrictions->altmap)) + if (WARN_ON_ONCE(params->altmap)) return -EINVAL; rc = vmem_add_mapping(start, size); if (rc) return rc; - rc = __add_pages(nid, start_pfn, size_pages, restrictions); + rc = __add_pages(nid, start_pfn, size_pages, params); if (rc) vmem_remove_mapping(start, size); return rc; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index d1b1ff2be17a..e5114c053364 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -406,14 +406,14 @@ void __init mem_init(void) #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = PFN_DOWN(start); unsigned long nr_pages = size >> PAGE_SHIFT; int ret; /* We only have ZONE_NORMAL, so this is easy.. */ - ret = __add_pages(nid, start_pfn, nr_pages, restrictions); + ret = __add_pages(nid, start_pfn, nr_pages, params); if (unlikely(ret)) printk("%s: Failed, __add_pages() == %d\n", __func__, ret); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index de73992b8432..d736c8625503 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -819,12 +819,12 @@ void __init mem_init(void) #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - return __add_pages(nid, start_pfn, nr_pages, restrictions); + return __add_pages(nid, start_pfn, nr_pages, params); } void arch_remove_memory(int nid, u64 start, u64 size, diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 0a14711d3a93..faa86a9a3b0d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -843,11 +843,11 @@ static void update_end_of_memory_vars(u64 start, u64 size) } int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { int ret; - ret = __add_pages(nid, start_pfn, nr_pages, restrictions); + ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); /* update max_pfn, max_low_pfn and high_memory */ @@ -858,14 +858,14 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, } int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; init_memory_mapping(start, start + size); - return add_pages(nid, start_pfn, nr_pages, restrictions); + return add_pages(nid, start_pfn, nr_pages, params); } #define PAGE_INUSE 0xFD diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7c1bcff11672..75f0f6304735 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -58,10 +58,10 @@ enum { }; /* - * Restrictions for the memory hotplug: - * altmap: alternative allocator for memmap array + * Extended parameters for memory hotplug: + * altmap: alternative allocator for memmap array (optional) */ -struct mhp_restrictions { +struct mhp_params { struct vmem_altmap *altmap; }; @@ -112,7 +112,7 @@ extern int restore_online_page_callback(online_page_callback_t callback); extern int try_online_node(int nid); extern int arch_add_memory(int nid, u64 start, u64 size, - struct mhp_restrictions *restrictions); + struct mhp_params *params); extern u64 max_mem_size; extern int memhp_online_type_from_str(const char *str); @@ -133,17 +133,17 @@ extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages, /* reasonably generic interface to expand the physical pages */ extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, - struct mhp_restrictions *restrictions); + struct mhp_params *params); #ifndef CONFIG_ARCH_HAS_ADD_PAGES static inline int add_pages(int nid, unsigned long start_pfn, - unsigned long nr_pages, struct mhp_restrictions *restrictions) + unsigned long nr_pages, struct mhp_params *params) { - return __add_pages(nid, start_pfn, nr_pages, restrictions); + return __add_pages(nid, start_pfn, nr_pages, params); } #else /* ARCH_HAS_ADD_PAGES */ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, - struct mhp_restrictions *restrictions); + struct mhp_params *params); #endif /* ARCH_HAS_ADD_PAGES */ #ifdef CONFIG_NUMA diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 635e8e286598..fbfe7b40f552 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -304,12 +304,12 @@ static int check_hotplug_memory_addressable(unsigned long pfn, * add the new pages. */ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, - struct mhp_restrictions *restrictions) + struct mhp_params *params) { const unsigned long end_pfn = pfn + nr_pages; unsigned long cur_nr_pages; int err; - struct vmem_altmap *altmap = restrictions->altmap; + struct vmem_altmap *altmap = params->altmap; err = check_hotplug_memory_addressable(pfn, nr_pages); if (err) @@ -1002,7 +1002,7 @@ static int online_memory_block(struct memory_block *mem, void *arg) */ int __ref add_memory_resource(int nid, struct resource *res) { - struct mhp_restrictions restrictions = {}; + struct mhp_params params = {}; u64 start, size; bool new_node = false; int ret; @@ -1030,7 +1030,7 @@ int __ref add_memory_resource(int nid, struct resource *res) new_node = ret; /* call arch's memory hotadd */ - ret = arch_add_memory(nid, start, size, &restrictions); + ret = arch_add_memory(nid, start, size, ¶ms); if (ret < 0) goto error; diff --git a/mm/memremap.c b/mm/memremap.c index bbf457c4f166..b0b5170843ff 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -184,7 +184,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) { struct resource *res = &pgmap->res; struct dev_pagemap *conflict_pgmap; - struct mhp_restrictions restrictions = { + struct mhp_params params = { /* * We do not want any optional features only our own memmap */ @@ -302,7 +302,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) */ if (pgmap->type == MEMORY_DEVICE_PRIVATE) { error = add_pages(nid, PHYS_PFN(res->start), - PHYS_PFN(resource_size(res)), &restrictions); + PHYS_PFN(resource_size(res)), ¶ms); } else { error = kasan_add_zero_shadow(__va(res->start), resource_size(res)); if (error) { @@ -311,7 +311,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) } error = arch_add_memory(nid, res->start, resource_size(res), - &restrictions); + ¶ms); } if (!error) { @@ -319,7 +319,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; move_pfn_range_to_zone(zone, PHYS_PFN(res->start), - PHYS_PFN(resource_size(res)), restrictions.altmap); + PHYS_PFN(resource_size(res)), params.altmap); } mem_hotplug_done(); -- cgit v1.2.3 From bfeb022f8fe4c5afdcfd7a3d868fac9765f9bcad Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 10 Apr 2020 14:33:36 -0700 Subject: mm/memory_hotplug: add pgprot_t to mhp_params devm_memremap_pages() is currently used by the PCI P2PDMA code to create struct page mappings for IO memory. At present, these mappings are created with PAGE_KERNEL which implies setting the PAT bits to be WB. However, on x86, an mtrr register will typically override this and force the cache type to be UC-. In the case firmware doesn't set this register it is effectively WB and will typically result in a machine check exception when it's accessed. Other arches are not currently likely to function correctly seeing they don't have any MTRR registers to fall back on. To solve this, provide a way to specify the pgprot value explicitly to arch_add_memory(). Of the arches that support MEMORY_HOTPLUG: x86_64, and arm64 need a simple change to pass the pgprot_t down to their respective functions which set up the page tables. For x86_32, set the page tables explicitly using _set_memory_prot() (seeing they are already mapped). For ia64, s390 and sh, reject anything but PAGE_KERNEL settings -- this should be fine, for now, seeing these architectures don't support ZONE_DEVICE. A check in __add_pages() is also added to ensure the pgprot parameter was set for all arches. Signed-off-by: Logan Gunthorpe Signed-off-by: Andrew Morton Acked-by: David Hildenbrand Acked-by: Michal Hocko Acked-by: Dan Williams Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christoph Hellwig Cc: Dave Hansen Cc: Eric Badger Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/20200306170846.9333-7-logang@deltatee.com Signed-off-by: Linus Torvalds --- arch/arm64/mm/mmu.c | 3 ++- arch/ia64/mm/init.c | 3 +++ arch/powerpc/mm/mem.c | 3 ++- arch/s390/mm/init.c | 3 +++ arch/sh/mm/init.c | 3 +++ arch/x86/mm/init_32.c | 12 ++++++++++++ arch/x86/mm/init_64.c | 2 +- include/linux/memory_hotplug.h | 3 +++ mm/memory_hotplug.c | 5 ++++- mm/memremap.c | 6 +++--- 10 files changed, 36 insertions(+), 7 deletions(-) (limited to 'arch/s390') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 6d4e9c2b4ed0..a374e4f51a62 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1382,7 +1382,8 @@ int arch_add_memory(int nid, u64 start, u64 size, flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), - size, PAGE_KERNEL, __pgd_pgtable_alloc, flags); + size, params->pgprot, __pgd_pgtable_alloc, + flags); memblock_clear_nomap(start, size); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 97bbc23ea1e3..d637b4ea3147 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -676,6 +676,9 @@ int arch_add_memory(int nid, u64 start, u64 size, unsigned long nr_pages = size >> PAGE_SHIFT; int ret; + if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot)) + return -EINVAL; + ret = __add_pages(nid, start_pfn, nr_pages, params); if (ret) printk("%s: Problem encountered in __add_pages() as ret=%d\n", diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index bf63ab04db63..041ed7cfd341 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -132,7 +132,8 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, resize_hpt_for_hotplug(memblock_phys_mem_size()); start = (unsigned long)__va(start); - rc = create_section_mapping(start, start + size, nid, PAGE_KERNEL); + rc = create_section_mapping(start, start + size, nid, + params->pgprot); if (rc) { pr_warn("Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n", start, start + size, rc); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index e9e4a7abd0cc..87b2d024e75a 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -277,6 +277,9 @@ int arch_add_memory(int nid, u64 start, u64 size, if (WARN_ON_ONCE(params->altmap)) return -EINVAL; + if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot)) + return -EINVAL; + rc = vmem_add_mapping(start, size); if (rc) return rc; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index e5114c053364..b9de2d4fa57e 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -412,6 +412,9 @@ int arch_add_memory(int nid, u64 start, u64 size, unsigned long nr_pages = size >> PAGE_SHIFT; int ret; + if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot) + return -EINVAL; + /* We only have ZONE_NORMAL, so this is easy.. */ ret = __add_pages(nid, start_pfn, nr_pages, params); if (unlikely(ret)) diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ac75a8397804..4222a010057a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -824,6 +824,18 @@ int arch_add_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + int ret; + + /* + * The page tables were already mapped at boot so if the caller + * requests a different mapping type then we must change all the + * pages with __set_memory_prot(). + */ + if (params->pgprot.pgprot != PAGE_KERNEL.pgprot) { + ret = __set_memory_prot(start, nr_pages, params->pgprot); + if (ret) + return ret; + } return __add_pages(nid, start_pfn, nr_pages, params); } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7480de743105..3b289c2f75cd 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -867,7 +867,7 @@ int arch_add_memory(int nid, u64 start, u64 size, unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - init_memory_mapping(start, start + size, PAGE_KERNEL); + init_memory_mapping(start, start + size, params->pgprot); return add_pages(nid, start_pfn, nr_pages, params); } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 75f0f6304735..93d9ada74ddd 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -60,9 +60,12 @@ enum { /* * Extended parameters for memory hotplug: * altmap: alternative allocator for memmap array (optional) + * pgprot: page protection flags to apply to newly created page tables + * (required) */ struct mhp_params { struct vmem_altmap *altmap; + pgprot_t pgprot; }; /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fbfe7b40f552..fc0aad0bc1f5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -311,6 +311,9 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, int err; struct vmem_altmap *altmap = params->altmap; + if (WARN_ON_ONCE(!params->pgprot.pgprot)) + return -EINVAL; + err = check_hotplug_memory_addressable(pfn, nr_pages); if (err) return err; @@ -1002,7 +1005,7 @@ static int online_memory_block(struct memory_block *mem, void *arg) */ int __ref add_memory_resource(int nid, struct resource *res) { - struct mhp_params params = {}; + struct mhp_params params = { .pgprot = PAGE_KERNEL }; u64 start, size; bool new_node = false; int ret; diff --git a/mm/memremap.c b/mm/memremap.c index b0b5170843ff..bc167cde3237 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -189,8 +189,8 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) * We do not want any optional features only our own memmap */ .altmap = pgmap_altmap(pgmap), + .pgprot = PAGE_KERNEL, }; - pgprot_t pgprot = PAGE_KERNEL; int error, is_ram; bool need_devmap_managed = true; @@ -282,8 +282,8 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) if (nid < 0) nid = numa_mem_id(); - error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0, - resource_size(res)); + error = track_pfn_remap(NULL, ¶ms.pgprot, PHYS_PFN(res->start), + 0, resource_size(res)); if (error) goto err_pfn_remap; -- cgit v1.2.3