From 577706de69c1e53bc23893953770d829a2242c38 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 2 Sep 2021 14:49:58 -0700 Subject: ia64: fix typo in a comment s/when when/when/ Link: https://lkml.kernel.org/r/20210817112500.12848-1-wangborong@cdjrlc.com Signed-off-by: Jason Wang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index e2af6b172200..96d13cb7c19f 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -906,6 +906,6 @@ EXPORT_SYMBOL(acpi_unregister_ioapic); /* * acpi_suspend_lowlevel() - save kernel state and suspend. * - * TBD when when IA64 starts to support suspend... + * TBD when IA64 starts to support suspend... */ int acpi_suspend_lowlevel(void) { return 0; } -- cgit v1.2.3 From 1d1f4bf845d36d73b27ed37790cae0da3112ca77 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 2 Sep 2021 14:50:01 -0700 Subject: ia64: fix #endif comment for reserve_elfcorehdr() Patch series "ia64: Miscellaneous fixes and cleanups". This patch series contains some miscellaneous fixes and cleanups for ia64. The second patch fixes a naming conflict triggered by a patch for the FDT code. This patch (of 3): The definition of reserve_elfcorehdr() depends on CONFIG_CRASH_DUMP, not CONFIG_PROC_VMCORE. Link: https://lkml.kernel.org/r/cover.1629884459.git.geert+renesas@glider.be Link: https://lkml.kernel.org/r/77b4c0648f200cab7e1c2c5171c06763e09362aa.1629884459.git.geert+renesas@glider.be Fixes: d9a9855d0b06ca6d ("always reserve elfcore header memory in crash kernel") Fixes: 17c1f07ed70afa4f ("[IA64] Reserve elfcorehdr memory in CONFIG_CRASH_DUMP") Signed-off-by: Geert Uytterhoeven Cc: Simon Horman Cc: Tony Luck Cc: Jay Lan Cc: Magnus Damm Cc: Mike Rapoport Cc: Rob Herring Cc: Frank Rowand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index dd595fbd8006..fbd931f1eb27 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -546,7 +546,7 @@ int __init reserve_elfcorehdr(u64 *start, u64 *end) return 0; } -#endif /* CONFIG_PROC_VMCORE */ +#endif /* CONFIG_CRASH_DUMP */ void __init setup_arch (char **cmdline_p) -- cgit v1.2.3 From 70b2e9912a018e9fddb3a1e0cbb397d4d3c0e98f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 2 Sep 2021 14:50:04 -0700 Subject: ia64: make reserve_elfcorehdr() static There never was a reason for reserve_elfcorehdr() to be global. Make the function static, and move it before its sole caller. Link: https://lkml.kernel.org/r/fe236cd73b64abc4abd03dd808cb015c907f4c8c.1629884459.git.geert+renesas@glider.be Fixes: cee87af2a5f75713 ("[IA64] kexec: Use EFI_LOADER_DATA for ELF core header") Signed-off-by: Geert Uytterhoeven Cc: Frank Rowand Cc: Jay Lan Cc: Magnus Damm Cc: Mike Rapoport Cc: Rob Herring Cc: Simon Horman Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/meminit.h | 1 - arch/ia64/kernel/setup.c | 51 ++++++++++++++++++++--------------------- 2 files changed, 25 insertions(+), 27 deletions(-) (limited to 'arch') diff --git a/arch/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h index 6c47a239fc26..2738f62b5f98 100644 --- a/arch/ia64/include/asm/meminit.h +++ b/arch/ia64/include/asm/meminit.h @@ -40,7 +40,6 @@ extern unsigned long efi_memmap_init(u64 *s, u64 *e); extern int find_max_min_low_pfn (u64, u64, void *); extern unsigned long vmcore_find_descriptor_size(unsigned long address); -extern int reserve_elfcorehdr(u64 *start, u64 *end); /* * For rounding an address to the next IA64_GRANULE_SIZE or order diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index fbd931f1eb27..5e6ee8939092 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -325,6 +325,31 @@ static inline void __init setup_crashkernel(unsigned long total, int *n) {} #endif +#ifdef CONFIG_CRASH_DUMP +static int __init reserve_elfcorehdr(u64 *start, u64 *end) +{ + u64 length; + + /* We get the address using the kernel command line, + * but the size is extracted from the EFI tables. + * Both address and size are required for reservation + * to work properly. + */ + + if (!is_vmcore_usable()) + return -EINVAL; + + if ((length = vmcore_find_descriptor_size(elfcorehdr_addr)) == 0) { + vmcore_unusable(); + return -EINVAL; + } + + *start = (unsigned long)__va(elfcorehdr_addr); + *end = *start + length; + return 0; +} +#endif /* CONFIG_CRASH_DUMP */ + /** * reserve_memory - setup reserved memory areas * @@ -522,32 +547,6 @@ static __init int setup_nomca(char *s) } early_param("nomca", setup_nomca); -#ifdef CONFIG_CRASH_DUMP -int __init reserve_elfcorehdr(u64 *start, u64 *end) -{ - u64 length; - - /* We get the address using the kernel command line, - * but the size is extracted from the EFI tables. - * Both address and size are required for reservation - * to work properly. - */ - - if (!is_vmcore_usable()) - return -EINVAL; - - if ((length = vmcore_find_descriptor_size(elfcorehdr_addr)) == 0) { - vmcore_unusable(); - return -EINVAL; - } - - *start = (unsigned long)__va(elfcorehdr_addr); - *end = *start + length; - return 0; -} - -#endif /* CONFIG_CRASH_DUMP */ - void __init setup_arch (char **cmdline_p) { -- cgit v1.2.3 From 7e4265c88968d4e53b164944c05e12e79d8ff9c6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 2 Sep 2021 14:50:08 -0700 Subject: ia64: make num_rsvd_regions static Commit f62800992e5917f2 ("ia64: switch to NO_BOOTMEM") removed the last user of num_rsvd_regions outside arch/ia64/kernel/setup.c. Link: https://lkml.kernel.org/r/a377b5437e3e9da93d02f996fe06a2b956cb0990.1629884459.git.geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Cc: Frank Rowand Cc: Jay Lan Cc: Magnus Damm Cc: Mike Rapoport Cc: Rob Herring Cc: Simon Horman Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/meminit.h | 1 - arch/ia64/kernel/setup.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h index 2738f62b5f98..f1d5bf2ba847 100644 --- a/arch/ia64/include/asm/meminit.h +++ b/arch/ia64/include/asm/meminit.h @@ -29,7 +29,6 @@ struct rsvd_region { }; extern struct rsvd_region rsvd_region[IA64_MAX_RSVD_REGIONS + 1]; -extern int num_rsvd_regions; extern void find_memory (void); extern void reserve_memory (void); diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 5e6ee8939092..31fb84de2d21 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -131,7 +131,7 @@ unsigned long ia64_cache_stride_shift = ~0; * We use a special marker for the end of memory and it uses the extra (+1) slot */ struct rsvd_region rsvd_region[IA64_MAX_RSVD_REGIONS + 1] __initdata; -int num_rsvd_regions __initdata; +static int num_rsvd_regions __initdata; /* -- cgit v1.2.3 From 4bdffd2708d65e68ff254d90793bb167d828219f Mon Sep 17 00:00:00 2001 From: kernel test robot Date: Thu, 2 Sep 2021 14:50:20 -0700 Subject: arch/csky/kernel/probes/kprobes.c: fix bugon.cocci warnings Use BUG_ON instead of a if condition followed by BUG. Generated by: scripts/coccinelle/misc/bugon.cocci Link: https://lkml.kernel.org/r/alpine.DEB.2.22.394.2107061049150.7197@hadrien Fixes: 7d37cb2c912d ("lib: fix kconfig dependency on ARCH_WANT_FRAME_POINTERS") Signed-off-by: kernel test robot Signed-off-by: Julia Lawall Reported-by: kernel test robot Cc: Julian Braha Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/csky/kernel/probes/kprobes.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c index 68b22b499aeb..8fffa34d4e1c 100644 --- a/arch/csky/kernel/probes/kprobes.c +++ b/arch/csky/kernel/probes/kprobes.c @@ -283,8 +283,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr) * normal page fault. */ regs->pc = (unsigned long) cur->addr; - if (!instruction_pointer(regs)) - BUG(); + BUG_ON(!instruction_pointer(regs)); if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); -- cgit v1.2.3 From 9857a17f206ff374aea78bccfb687f145368be2e Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 2 Sep 2021 14:53:54 -0700 Subject: mm/gup: remove try_get_page(), call try_get_compound_head() directly try_get_page() is very similar to try_get_compound_head(), and in fact try_get_page() has fallen a little behind in terms of maintenance: try_get_compound_head() handles speculative page references more thoroughly. There are only two try_get_page() callsites, so just call try_get_compound_head() directly from those, and remove try_get_page() entirely. Also, seeing as how this changes try_get_compound_head() into a non-static function, provide some kerneldoc documentation for it. Link: https://lkml.kernel.org/r/20210813044133.1536842-4-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index e33c43b38afe..81d760749987 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -817,7 +817,7 @@ void do_secure_storage_access(struct pt_regs *regs) break; case KERNEL_FAULT: page = phys_to_page(addr); - if (unlikely(!try_get_page(page))) + if (unlikely(!try_get_compound_head(page, 1))) break; rc = arch_make_page_accessible(page); put_page(page); -- cgit v1.2.3 From ec403e2ae0dfc85996aad6e944a98a16e6dfcc6d Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 2 Sep 2021 14:55:43 -0700 Subject: memcg: enable accounting for ldt_struct objects Each task can request own LDT and force the kernel to allocate up to 64Kb memory per-mm. There are legitimate workloads with hundreds of processes and there can be hundreds of workloads running on large machines. The unaccounted memory can cause isolation issues between the workloads particularly on highly utilized machines. It makes sense to account for this objects to restrict the host's memory consumption from inside the memcg-limited container. Link: https://lkml.kernel.org/r/38010594-50fe-c06d-7cb0-d1f77ca422f3@virtuozzo.com Signed-off-by: Vasily Averin Acked-by: Borislav Petkov Reviewed-by: Shakeel Butt Cc: Alexander Viro Cc: Alexey Dobriyan Cc: Andrei Vagin Cc: Borislav Petkov Cc: Christian Brauner Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Jens Axboe Cc: Jiri Slaby Cc: Johannes Weiner Cc: Kirill Tkhai Cc: Michal Hocko Cc: Oleg Nesterov Cc: Roman Gushchin Cc: Serge Hallyn Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vladimir Davydov Cc: Yutian Yang Cc: Zefan Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/ldt.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index aa15132228da..525876e7b9f4 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -154,7 +154,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) if (num_entries > LDT_ENTRIES) return NULL; - new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL_ACCOUNT); if (!new_ldt) return NULL; @@ -168,9 +168,9 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) * than PAGE_SIZE. */ if (alloc_size > PAGE_SIZE) - new_ldt->entries = vzalloc(alloc_size); + new_ldt->entries = __vmalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); else - new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL); + new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!new_ldt->entries) { kfree(new_ldt); -- cgit v1.2.3 From f358afc52c3066f4e8cd7b3a2d75b31e822519e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 2 Sep 2021 14:56:36 -0700 Subject: mm: remove flush_kernel_dcache_page flush_kernel_dcache_page is a rather confusing interface that implements a subset of flush_dcache_page by not being able to properly handle page cache mapped pages. The only callers left are in the exec code as all other previous callers were incorrect as they could have dealt with page cache pages. Replace the calls to flush_kernel_dcache_page with calls to flush_dcache_page, which for all architectures does either exactly the same thing, can contains one or more of the following: 1) an optimization to defer the cache flush for page cache pages not mapped into userspace 2) additional flushing for mapped page cache pages if cache aliases are possible Link: https://lkml.kernel.org/r/20210712060928.4161649-7-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds Reviewed-by: Ira Weiny Cc: Alex Shi Cc: Geoff Levand Cc: Greentime Hu Cc: Guo Ren Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Nick Hu Cc: Paul Cercueil Cc: Rich Felker Cc: Russell King Cc: Thomas Bogendoerfer Cc: Ulf Hansson Cc: Vincent Chen Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/cacheflush.h | 4 +--- arch/arm/mm/flush.c | 33 --------------------------------- arch/arm/mm/nommu.c | 6 ------ arch/csky/abiv1/cacheflush.c | 11 ----------- arch/csky/abiv1/inc/abi/cacheflush.h | 4 +--- arch/mips/include/asm/cacheflush.h | 8 +------- arch/nds32/include/asm/cacheflush.h | 3 +-- arch/nds32/mm/cacheflush.c | 9 --------- arch/parisc/include/asm/cacheflush.h | 8 ++------ arch/parisc/kernel/cache.c | 3 +-- arch/sh/include/asm/cacheflush.h | 8 ++------ 11 files changed, 9 insertions(+), 88 deletions(-) (limited to 'arch') diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 2e24e765e6d3..5e56288e343b 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -291,6 +291,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) { if ((cache_is_vivt() || cache_is_vipt_aliasing())) @@ -312,9 +313,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma, __flush_anon_page(vma, page, vmaddr); } -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -extern void flush_kernel_dcache_page(struct page *); - #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 6d89db7895d1..7ff9feea13a6 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -345,39 +345,6 @@ void flush_dcache_page(struct page *page) } EXPORT_SYMBOL(flush_dcache_page); -/* - * Ensure cache coherency for the kernel mapping of this page. We can - * assume that the page is pinned via kmap. - * - * If the page only exists in the page cache and there are no user - * space mappings, this is a no-op since the page was already marked - * dirty at creation. Otherwise, we need to flush the dirty kernel - * cache lines directly. - */ -void flush_kernel_dcache_page(struct page *page) -{ - if (cache_is_vivt() || cache_is_vipt_aliasing()) { - struct address_space *mapping; - - mapping = page_mapping_file(page); - - if (!mapping || mapping_mapped(mapping)) { - void *addr; - - addr = page_address(page); - /* - * kmap_atomic() doesn't set the page virtual - * address for highmem pages, and - * kunmap_atomic() takes care of cache - * flushing already. - */ - if (!IS_ENABLED(CONFIG_HIGHMEM) || addr) - __cpuc_flush_dcache_area(addr, PAGE_SIZE); - } - } -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - /* * Flush an anonymous page so that users of get_user_pages() * can safely access the data. The expected sequence is: diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 8b3d7191e2b8..2658f52903da 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -166,12 +166,6 @@ void flush_dcache_page(struct page *page) } EXPORT_SYMBOL(flush_dcache_page); -void flush_kernel_dcache_page(struct page *page) -{ - __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) diff --git a/arch/csky/abiv1/cacheflush.c b/arch/csky/abiv1/cacheflush.c index 07ff17ea33de..fb91b069dc69 100644 --- a/arch/csky/abiv1/cacheflush.c +++ b/arch/csky/abiv1/cacheflush.c @@ -56,17 +56,6 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, } } -void flush_kernel_dcache_page(struct page *page) -{ - struct address_space *mapping; - - mapping = page_mapping_file(page); - - if (!mapping || mapping_mapped(mapping)) - dcache_wbinv_all(); -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h index 6cab7afae962..ed62e2066ba7 100644 --- a/arch/csky/abiv1/inc/abi/cacheflush.h +++ b/arch/csky/abiv1/inc/abi/cacheflush.h @@ -14,12 +14,10 @@ extern void flush_dcache_page(struct page *); #define flush_cache_page(vma, page, pfn) cache_wbinv_all() #define flush_cache_dup_mm(mm) cache_wbinv_all() -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -extern void flush_kernel_dcache_page(struct page *); - #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) { dcache_wbinv_all(); diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index d687b40b9fbb..b3dc9c589442 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -125,13 +125,7 @@ static inline void kunmap_noncoherent(void) kunmap_coherent(); } -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -static inline void flush_kernel_dcache_page(struct page *page) -{ - BUG_ON(cpu_has_dc_aliases && PageHighMem(page)); - flush_dcache_page(page); -} - +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 /* * For now flush_kernel_vmap_range and invalidate_kernel_vmap_range both do a * cache writeback and invalidate operation. diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 7d6824f7c0e8..c2a222ebfa2a 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -36,8 +36,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr); -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -void flush_kernel_dcache_page(struct page *page); +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *addr, int size); void invalidate_kernel_vmap_range(void *addr, int size); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&(mapping)->i_pages) diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c index ad5344ef5d33..07aac65d1cab 100644 --- a/arch/nds32/mm/cacheflush.c +++ b/arch/nds32/mm/cacheflush.c @@ -318,15 +318,6 @@ void flush_anon_page(struct vm_area_struct *vma, local_irq_restore(flags); } -void flush_kernel_dcache_page(struct page *page) -{ - unsigned long flags; - local_irq_save(flags); - cpu_dcache_wbinval_page((unsigned long)page_address(page)); - local_irq_restore(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page); - void flush_kernel_vmap_range(void *addr, int size) { unsigned long flags; diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 99663fc1f997..eef0096db5f8 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -36,16 +36,12 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE void flush_kernel_dcache_page_addr(void *addr); -static inline void flush_kernel_dcache_page(struct page *page) -{ - flush_kernel_dcache_page_addr(page_address(page)); -} #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); @@ -59,7 +55,7 @@ extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) #define flush_icache_page(vma,page) do { \ - flush_kernel_dcache_page(page); \ + flush_kernel_dcache_page_addr(page_address(page)); \ flush_kernel_icache_page(page_address(page)); \ } while (0) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 86a1a63563fd..39e02227e231 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -334,7 +334,7 @@ void flush_dcache_page(struct page *page) return; } - flush_kernel_dcache_page(page); + flush_kernel_dcache_page_addr(page_address(page)); if (!mapping) return; @@ -375,7 +375,6 @@ EXPORT_SYMBOL(flush_dcache_page); /* Defined in arch/parisc/kernel/pacache.S */ EXPORT_SYMBOL(flush_kernel_dcache_range_asm); -EXPORT_SYMBOL(flush_kernel_dcache_page_asm); EXPORT_SYMBOL(flush_data_cache_local); EXPORT_SYMBOL(flush_kernel_icache_range_asm); diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index 4486a865ff62..372afa82fee6 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -63,6 +63,8 @@ static inline void flush_anon_page(struct vm_area_struct *vma, if (boot_cpu_data.dcache.n_aliases && PageAnon(page)) __flush_anon_page(page, vmaddr); } + +#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) { __flush_wback_region(addr, size); @@ -72,12 +74,6 @@ static inline void invalidate_kernel_vmap_range(void *addr, int size) __flush_invalidate_region(addr, size); } -#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE -static inline void flush_kernel_dcache_page(struct page *page) -{ - flush_dcache_page(page); -} - extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, const void *src, unsigned long len); -- cgit v1.2.3 From fc1f5e980a463325cf41d39ac6a69aa3cca73995 Mon Sep 17 00:00:00 2001 From: Ohhoon Kwon Date: Thu, 2 Sep 2021 14:57:01 -0700 Subject: mm: sparse: pass section_nr to find_memory_block With CONFIG_SPARSEMEM_EXTREME enabled, __section_nr() which converts mem_section to section_nr could be costly since it iterates all section roots to check if the given mem_section is in its range. On the other hand, __nr_to_section() which converts section_nr to mem_section can be done in O(1). Let's pass section_nr instead of mem_section ptr to find_memory_block() in order to reduce needless iterations. Link: https://lkml.kernel.org/r/20210707150212.855-3-ohoono.kwon@samsung.com Signed-off-by: Ohhoon Kwon Acked-by: Michal Hocko Acked-by: Mike Rapoport Reviewed-by: David Hildenbrand Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 377d852f5a9a..d4f28ee4d5dc 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -211,13 +211,11 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb) static struct memory_block *lmb_to_memblock(struct drmem_lmb *lmb) { unsigned long section_nr; - struct mem_section *mem_sect; struct memory_block *mem_block; section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); - mem_sect = __nr_to_section(section_nr); - mem_block = find_memory_block(mem_sect); + mem_block = find_memory_block(section_nr); return mem_block; } -- cgit v1.2.3 From c3ab6baf6a004eab7344a1d8880a971f2414e1b6 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 2 Sep 2021 14:57:56 -0700 Subject: mm/page_alloc: always initialize memory map for the holes Patch series "mm: ensure consistency of memory map poisoning". Currently memory map allocation for FLATMEM case does not poison the struct pages regardless of CONFIG_PAGE_POISON setting. This happens because allocation of the memory map for FLATMEM and SPARSMEM use different memblock functions and those that are used for SPARSMEM case (namely memblock_alloc_try_nid_raw() and memblock_alloc_exact_nid_raw()) implicitly poison the allocated memory. Another side effect of this implicit poisoning is that early setup code that uses the same functions to allocate memory burns cycles for the memory poisoning even if it was not intended. These patches introduce memmap_alloc() wrapper that ensure that the memory map allocation is consistent for different memory models. This patch (of 4): Currently memory map for the holes is initialized only when SPARSEMEM memory model is used. Yet, even with FLATMEM there could be holes in the physical memory layout that have memory map entries. For instance, the memory reserved using e820 API on i386 or "reserved-memory" nodes in device tree would not appear in memblock.memory and hence the struct pages for such holes will be skipped during memory map initialization. These struct pages will be zeroed because the memory map for FLATMEM systems is allocated with memblock_alloc_node() that clears the allocated memory. While zeroed struct pages do not cause immediate problems, the correct behaviour is to initialize every page using __init_single_page(). Besides, enabling page poison for FLATMEM case will trigger PF_POISONED_CHECK() unless the memory map is properly initialized. Make sure init_unavailable_range() is called for both SPARSEMEM and FLATMEM so that struct pages representing memory holes would appear as PG_Reserved with any memory layout. [rppt@kernel.org: fix microblaze] Link: https://lkml.kernel.org/r/YQWW3RCE4eWBuMu/@kernel.org Link: https://lkml.kernel.org/r/20210714123739.16493-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210714123739.16493-2-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: David Hildenbrand Tested-by: Guenter Roeck Cc: Michal Simek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/microblaze/include/asm/page.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h index ce550978f4fc..4b8b2fa78fc5 100644 --- a/arch/microblaze/include/asm/page.h +++ b/arch/microblaze/include/asm/page.h @@ -112,8 +112,7 @@ extern int page_is_ram(unsigned long pfn); # define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) # define ARCH_PFN_OFFSET (memory_start >> PAGE_SHIFT) -# define pfn_valid(pfn) ((pfn) < (max_mapnr + ARCH_PFN_OFFSET)) - +# define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < (max_mapnr + ARCH_PFN_OFFSET)) # endif /* __ASSEMBLY__ */ #define virt_addr_valid(vaddr) (pfn_valid(virt_to_pfn(vaddr))) -- cgit v1.2.3 From 22e7878102f94a50e9a4c2c19f909a9a0898c4ce Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 2 Sep 2021 14:57:59 -0700 Subject: microblaze: simplify pte_alloc_one_kernel() The microblaze's implementation of pte_alloc_one_kernel() used memblock_alloc_try_nid_raw() along with clear_page() to allocated a zeroed page during early setup. Replace calls of these functions with a call to memblock_alloc_try_nid() that already returns zeroed page and respects the same allocation limits as memblock_alloc_try_nid_raw(). While on it drop early_get_page() wrapper that was only used in pte_alloc_one_kernel(). Link: https://lkml.kernel.org/r/20210714123739.16493-3-rppt@kernel.org Signed-off-by: Mike Rapoport Reviewed-by: David Hildenbrand Cc: Michal Simek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/microblaze/include/asm/pgtable.h | 2 -- arch/microblaze/mm/init.c | 12 ------------ arch/microblaze/mm/pgtable.c | 17 ++++++++--------- 3 files changed, 8 insertions(+), 23 deletions(-) (limited to 'arch') diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index 71cd547655d9..c136a01e467e 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -443,8 +443,6 @@ extern int mem_init_done; asmlinkage void __init mmu_init(void); -void __init *early_get_page(void); - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index ab55c70380a5..952f35b335b2 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -265,18 +265,6 @@ asmlinkage void __init mmu_init(void) dma_contiguous_reserve(memory_start + lowmem_size - 1); } -/* This is only called until mem_init is done. */ -void __init *early_get_page(void) -{ - /* - * Mem start + kernel_tlb -> here is limit - * because of mem mapping from head.S - */ - return memblock_alloc_try_nid_raw(PAGE_SIZE, PAGE_SIZE, - MEMBLOCK_LOW_LIMIT, memory_start + kernel_tlb, - NUMA_NO_NODE); -} - void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) { void *p; diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c index 38ccb909bc9d..c1833b159d3b 100644 --- a/arch/microblaze/mm/pgtable.c +++ b/arch/microblaze/mm/pgtable.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -242,15 +243,13 @@ unsigned long iopa(unsigned long addr) __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { - pte_t *pte; - if (mem_init_done) { - pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - } else { - pte = (pte_t *)early_get_page(); - if (pte) - clear_page(pte); - } - return pte; + if (mem_init_done) + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + else + return memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, + MEMBLOCK_LOW_LIMIT, + memory_start + kernel_tlb, + NUMA_NO_NODE); } void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) -- cgit v1.2.3 From a7259df7670240ee03b0cfce8a3e5d3773911e24 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 2 Sep 2021 15:00:26 -0700 Subject: memblock: make memblock_find_in_range method private There are a lot of uses of memblock_find_in_range() along with memblock_reserve() from the times memblock allocation APIs did not exist. memblock_find_in_range() is the very core of memblock allocations, so any future changes to its internal behaviour would mandate updates of all the users outside memblock. Replace the calls to memblock_find_in_range() with an equivalent calls to memblock_phys_alloc() and memblock_phys_alloc_range() and make memblock_find_in_range() private method of memblock. This simplifies the callers, ensures that (unlikely) errors in memblock_reserve() are handled and improves maintainability of memblock_find_in_range(). Link: https://lkml.kernel.org/r/20210816122622.30279-1-rppt@kernel.org Signed-off-by: Mike Rapoport Reviewed-by: Catalin Marinas [arm64] Acked-by: Kirill A. Shutemov Acked-by: Rafael J. Wysocki [ACPI] Acked-by: Russell King (Oracle) Acked-by: Nick Kossifidis [riscv] Tested-by: Guenter Roeck Acked-by: Rob Herring Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/setup.c | 20 +++++++----------- arch/arm64/kvm/hyp/reserved_mem.c | 9 +++----- arch/arm64/mm/init.c | 36 ++++++++++---------------------- arch/mips/kernel/setup.c | 14 ++++++------- arch/riscv/mm/init.c | 44 +++++++++++++-------------------------- arch/s390/kernel/setup.c | 9 +++++--- arch/x86/kernel/aperture_64.c | 5 ++--- arch/x86/mm/init.c | 23 +++++++++++++------- arch/x86/mm/numa.c | 5 ++--- arch/x86/mm/numa_emulation.c | 5 ++--- arch/x86/realmode/init.c | 2 +- 11 files changed, 69 insertions(+), 103 deletions(-) (limited to 'arch') diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index f97eb2371672..284a80c0b6e1 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1012,31 +1012,25 @@ static void __init reserve_crashkernel(void) unsigned long long lowmem_max = __pa(high_memory - 1) + 1; if (crash_max > lowmem_max) crash_max = lowmem_max; - crash_base = memblock_find_in_range(CRASH_ALIGN, crash_max, - crash_size, CRASH_ALIGN); + + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, + CRASH_ALIGN, crash_max); if (!crash_base) { pr_err("crashkernel reservation failed - No suitable area found.\n"); return; } } else { + unsigned long long crash_max = crash_base + crash_size; unsigned long long start; - start = memblock_find_in_range(crash_base, - crash_base + crash_size, - crash_size, SECTION_SIZE); - if (start != crash_base) { + start = memblock_phys_alloc_range(crash_size, SECTION_SIZE, + crash_base, crash_max); + if (!start) { pr_err("crashkernel reservation failed - memory is in use.\n"); return; } } - ret = memblock_reserve(crash_base, crash_size); - if (ret < 0) { - pr_warn("crashkernel reservation failed - memory is in use (0x%lx)\n", - (unsigned long)crash_base); - return; - } - pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crash_base >> 20), diff --git a/arch/arm64/kvm/hyp/reserved_mem.c b/arch/arm64/kvm/hyp/reserved_mem.c index d654921dd09b..578670e3f608 100644 --- a/arch/arm64/kvm/hyp/reserved_mem.c +++ b/arch/arm64/kvm/hyp/reserved_mem.c @@ -92,12 +92,10 @@ void __init kvm_hyp_reserve(void) * this is unmapped from the host stage-2, and fallback to PAGE_SIZE. */ hyp_mem_size = hyp_mem_pages << PAGE_SHIFT; - hyp_mem_base = memblock_find_in_range(0, memblock_end_of_DRAM(), - ALIGN(hyp_mem_size, PMD_SIZE), - PMD_SIZE); + hyp_mem_base = memblock_phys_alloc(ALIGN(hyp_mem_size, PMD_SIZE), + PMD_SIZE); if (!hyp_mem_base) - hyp_mem_base = memblock_find_in_range(0, memblock_end_of_DRAM(), - hyp_mem_size, PAGE_SIZE); + hyp_mem_base = memblock_phys_alloc(hyp_mem_size, PAGE_SIZE); else hyp_mem_size = ALIGN(hyp_mem_size, PMD_SIZE); @@ -105,7 +103,6 @@ void __init kvm_hyp_reserve(void) kvm_err("Failed to reserve hyp memory\n"); return; } - memblock_reserve(hyp_mem_base, hyp_mem_size); kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20, hyp_mem_base); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 1fdb7bb7c198..bf5b8a5cd451 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -74,6 +74,7 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init; static void __init reserve_crashkernel(void) { unsigned long long crash_base, crash_size; + unsigned long long crash_max = arm64_dma_phys_limit; int ret; ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), @@ -84,33 +85,18 @@ static void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crash_size); - if (crash_base == 0) { - /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, arm64_dma_phys_limit, - crash_size, SZ_2M); - if (crash_base == 0) { - pr_warn("cannot allocate crashkernel (size:0x%llx)\n", - crash_size); - return; - } - } else { - /* User specifies base address explicitly. */ - if (!memblock_is_region_memory(crash_base, crash_size)) { - pr_warn("cannot reserve crashkernel: region is not memory\n"); - return; - } + /* User specifies base address explicitly. */ + if (crash_base) + crash_max = crash_base + crash_size; - if (memblock_is_region_reserved(crash_base, crash_size)) { - pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n"); - return; - } - - if (!IS_ALIGNED(crash_base, SZ_2M)) { - pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n"); - return; - } + /* Current arm64 boot protocol requires 2MB alignment */ + crash_base = memblock_phys_alloc_range(crash_size, SZ_2M, + crash_base, crash_max); + if (!crash_base) { + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", + crash_size); + return; } - memblock_reserve(crash_base, crash_size); pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 23a140327a0b..f979adfd4fc2 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -452,8 +452,9 @@ static void __init mips_parse_crashkernel(void) return; if (crash_base <= 0) { - crash_base = memblock_find_in_range(CRASH_ALIGN, CRASH_ADDR_MAX, - crash_size, CRASH_ALIGN); + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, + CRASH_ALIGN, + CRASH_ADDR_MAX); if (!crash_base) { pr_warn("crashkernel reservation failed - No suitable area found.\n"); return; @@ -461,8 +462,9 @@ static void __init mips_parse_crashkernel(void) } else { unsigned long long start; - start = memblock_find_in_range(crash_base, crash_base + crash_size, - crash_size, 1); + start = memblock_phys_alloc_range(crash_size, 1, + crash_base, + crash_base + crash_size); if (start != crash_base) { pr_warn("Invalid memory region reserved for crash kernel\n"); return; @@ -656,10 +658,6 @@ static void __init arch_mem_init(char **cmdline_p) mips_reserve_vmcore(); mips_parse_crashkernel(); -#ifdef CONFIG_KEXEC - if (crashk_res.start != crashk_res.end) - memblock_reserve(crashk_res.start, resource_size(&crashk_res)); -#endif device_tree_init(); /* diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 7cb4f391d106..e6cac495a9e8 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -819,38 +819,22 @@ static void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crash_size); - if (crash_base == 0) { - /* - * Current riscv boot protocol requires 2MB alignment for - * RV64 and 4MB alignment for RV32 (hugepage size) - */ - crash_base = memblock_find_in_range(search_start, search_end, - crash_size, PMD_SIZE); - - if (crash_base == 0) { - pr_warn("crashkernel: couldn't allocate %lldKB\n", - crash_size >> 10); - return; - } - } else { - /* User specifies base address explicitly. */ - if (!memblock_is_region_memory(crash_base, crash_size)) { - pr_warn("crashkernel: requested region is not memory\n"); - return; - } - - if (memblock_is_region_reserved(crash_base, crash_size)) { - pr_warn("crashkernel: requested region is reserved\n"); - return; - } - + if (crash_base) { + search_start = crash_base; + search_end = crash_base + crash_size; + } - if (!IS_ALIGNED(crash_base, PMD_SIZE)) { - pr_warn("crashkernel: requested region is misaligned\n"); - return; - } + /* + * Current riscv boot protocol requires 2MB alignment for + * RV64 and 4MB alignment for RV32 (hugepage size) + */ + crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, + search_start, search_end); + if (crash_base == 0) { + pr_warn("crashkernel: couldn't allocate %lldKB\n", + crash_size >> 10); + return; } - memblock_reserve(crash_base, crash_size); pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ff0f9e838916..0bab57d6413b 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -626,8 +626,9 @@ static void __init reserve_crashkernel(void) return; } low = crash_base ?: low; - crash_base = memblock_find_in_range(low, high, crash_size, - KEXEC_CRASH_MEM_ALIGN); + crash_base = memblock_phys_alloc_range(crash_size, + KEXEC_CRASH_MEM_ALIGN, + low, high); } if (!crash_base) { @@ -636,8 +637,10 @@ static void __init reserve_crashkernel(void) return; } - if (register_memory_notifier(&kdump_mem_nb)) + if (register_memory_notifier(&kdump_mem_nb)) { + memblock_free(crash_base, crash_size); return; + } if (!OLDMEM_BASE && MACHINE_IS_VM) diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size)); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 294ed4392a0e..10562885f5fc 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -109,14 +109,13 @@ static u32 __init allocate_aperture(void) * memory. Unfortunately we cannot move it up because that would * make the IOMMU useless. */ - addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, - aper_size, aper_size); + addr = memblock_phys_alloc_range(aper_size, aper_size, + GART_MIN_ADDR, GART_MAX_ADDR); if (!addr) { pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n", addr, addr + aper_size - 1, aper_size >> 10); return 0; } - memblock_reserve(addr, aper_size); pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n", addr, addr + aper_size - 1, aper_size >> 10); register_nosave_region(addr >> PAGE_SHIFT, diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 75ef19aa8903..23a14d82e783 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -127,14 +127,12 @@ __ref void *alloc_low_pages(unsigned int num) unsigned long ret = 0; if (min_pfn_mapped < max_pfn_mapped) { - ret = memblock_find_in_range( + ret = memblock_phys_alloc_range( + PAGE_SIZE * num, PAGE_SIZE, min_pfn_mapped << PAGE_SHIFT, - max_pfn_mapped << PAGE_SHIFT, - PAGE_SIZE * num , PAGE_SIZE); + max_pfn_mapped << PAGE_SHIFT); } - if (ret) - memblock_reserve(ret, PAGE_SIZE * num); - else if (can_use_brk_pgt) + if (!ret && can_use_brk_pgt) ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE)); if (!ret) @@ -610,8 +608,17 @@ static void __init memory_map_top_down(unsigned long map_start, unsigned long addr; unsigned long mapped_ram_size = 0; - /* xen has big range in reserved near end of ram, skip it at first.*/ - addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE); + /* + * Systems that have many reserved areas near top of the memory, + * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will + * require lots of 4K mappings which may exhaust pgt_buf. + * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure + * there is enough mapped memory that can be allocated from + * memblock. + */ + addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, + map_end); + memblock_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index e94da744386f..a1b5c71099e6 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -376,15 +376,14 @@ static int __init numa_alloc_distance(void) cnt++; size = cnt * cnt * sizeof(numa_distance[0]); - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), - size, PAGE_SIZE); + phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, + PFN_PHYS(max_pfn_mapped)); if (!phys) { pr_warn("Warning: can't allocate distance table!\n"); /* don't retry until explicitly reset */ numa_distance = (void *)1LU; return -ENOMEM; } - memblock_reserve(phys, size); numa_distance = __va(phys); numa_distance_cnt = cnt; diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 87d77cc52f86..737491b13728 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -447,13 +447,12 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) if (numa_dist_cnt) { u64 phys; - phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), - phys_size, PAGE_SIZE); + phys = memblock_phys_alloc_range(phys_size, PAGE_SIZE, 0, + PFN_PHYS(max_pfn_mapped)); if (!phys) { pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); goto no_emu; } - memblock_reserve(phys, phys_size); phys_dist = __va(phys); for (i = 0; i < numa_dist_cnt; i++) diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 6534c92d0f83..31b5856010cb 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -28,7 +28,7 @@ void __init reserve_real_mode(void) WARN_ON(slab_is_available()); /* Has to be under 1M so we can execute real-mode AP code. */ - mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); + mem = memblock_phys_alloc_range(size, PAGE_SIZE, 0, 1<<20); if (!mem) pr_info("No sub-1M memory is available for the trampoline\n"); else -- cgit v1.2.3 From dce49103962840dd61423d7627748d6c558d58c5 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 2 Sep 2021 15:00:33 -0700 Subject: mm: wire up syscall process_mrelease Split off from prev patch in the series that implements the syscall. Link: https://lkml.kernel.org/r/20210809185259.405936-2-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Geert Uytterhoeven Cc: Andy Lutomirski Cc: Christian Brauner Cc: Christoph Hellwig Cc: David Hildenbrand Cc: David Rientjes Cc: Florian Weimer Cc: Jan Engelhardt Cc: Jann Horn Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Murray Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/syscalls/syscall.tbl | 2 ++ arch/arm/tools/syscall.tbl | 2 ++ arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 2 ++ arch/m68k/kernel/syscalls/syscall.tbl | 2 ++ arch/microblaze/kernel/syscalls/syscall.tbl | 2 ++ arch/mips/kernel/syscalls/syscall_n32.tbl | 2 ++ arch/mips/kernel/syscalls/syscall_n64.tbl | 2 ++ arch/mips/kernel/syscalls/syscall_o32.tbl | 2 ++ arch/parisc/kernel/syscalls/syscall.tbl | 2 ++ arch/powerpc/kernel/syscalls/syscall.tbl | 2 ++ arch/s390/kernel/syscalls/syscall.tbl | 2 ++ arch/sh/kernel/syscalls/syscall.tbl | 2 ++ arch/sparc/kernel/syscalls/syscall.tbl | 2 ++ arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 2 ++ 18 files changed, 33 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index a17687ed4b51..605645eae04c 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -486,3 +486,5 @@ 554 common landlock_create_ruleset sys_landlock_create_ruleset 555 common landlock_add_rule sys_landlock_add_rule 556 common landlock_restrict_self sys_landlock_restrict_self +# 557 reserved for memfd_secret +558 common process_mrelease sys_process_mrelease diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index c5df1179fc5d..2f32eb8beca8 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -460,3 +460,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 727bfc3be99b..3cb206aea3db 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 447 +#define __NR_compat_syscalls 449 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 99ffcafc736c..0f49cdb180dd 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -901,6 +901,8 @@ __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) #define __NR_landlock_restrict_self 446 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) +#define __NR_process_mrelease 448 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 6d07742c57b8..9bf45f2be966 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -367,3 +367,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 541bc1b3a8f9..f1f98ee6c82d 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -446,3 +446,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a176faca2927..da49ddd4bb54 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -452,3 +452,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index c2d2e19abea8..56c8d3cf42ed 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -385,3 +385,5 @@ 444 n32 landlock_create_ruleset sys_landlock_create_ruleset 445 n32 landlock_add_rule sys_landlock_add_rule 446 n32 landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 n32 process_mrelease sys_process_mrelease diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index ac653d08b1ea..1ca7bc337932 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -361,3 +361,5 @@ 444 n64 landlock_create_ruleset sys_landlock_create_ruleset 445 n64 landlock_add_rule sys_landlock_add_rule 446 n64 landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 n64 process_mrelease sys_process_mrelease diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 253f2cd70b6b..fd3a9df60ec2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -434,3 +434,5 @@ 444 o32 landlock_create_ruleset sys_landlock_create_ruleset 445 o32 landlock_add_rule sys_landlock_add_rule 446 o32 landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 o32 process_mrelease sys_process_mrelease diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index e26187b9ab87..040df1b7a589 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -444,3 +444,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index aef2a290e71a..d8ebd7d37c0f 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -526,3 +526,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 64d51ab5a8b4..57233ace30cb 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -449,3 +449,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease sys_process_mrelease diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index e0a70be77d84..2f6e95eb4690 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -449,3 +449,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 603f5a821502..42fc2906215d 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -492,3 +492,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ce763a12311c..661a03bcfbd1 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -452,3 +452,4 @@ 445 i386 landlock_add_rule sys_landlock_add_rule 446 i386 landlock_restrict_self sys_landlock_restrict_self 447 i386 memfd_secret sys_memfd_secret +448 i386 process_mrelease sys_process_mrelease diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index f6b57799c1ea..807b6a1de8e8 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -369,6 +369,7 @@ 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self 447 common memfd_secret sys_memfd_secret +448 common process_mrelease sys_process_mrelease # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 235d67d6ceb4..f4384951f393 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -417,3 +417,5 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease -- cgit v1.2.3