From 6b7ce3134f68107438c99f8ea5424e08d418ca1b Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 27 Jan 2025 17:05:05 +0100 Subject: x86/kgdb: use IS_ERR_PCPU() macro Patch series "Enable strict percpu address space checks", v4. Enable strict percpu address space checks via x86 named address space qualifiers. Percpu variables are declared in __seg_gs/__seg_fs named AS and kept named AS qualified until they are dereferenced via percpu accessor. This approach enables various compiler checks for cross-namespace variable assignments. Please note that current version of sparse doesn't know anything about __typeof_unqual__() operator. Avoid the usage of __typeof_unqual__() when sparse checking is active to prevent sparse errors with unknowing keyword. The proposed patch by Dan Carpenter to implement __typeof_unqual__() handling in sparse is located at: https://lore.kernel.org/lkml/5b8d0dee-8fb6-45af-ba6c-7f74aff9a4b8@stanley.mountain/ This patch (of 6): Use IS_ERR_PCPU() when checking the error pointer in the percpu address space. This macro adds intermediate cast to unsigned long when switching named address spaces. The patch will avoid future build errors due to pointer address space mismatch with enabled strict percpu address space checks. Link: https://lkml.kernel.org/r/20250127160709.80604-1-ubizjak@gmail.com Link: https://lkml.kernel.org/r/20250127160709.80604-2-ubizjak@gmail.com Signed-off-by: Uros Bizjak Acked-by: Nadav Amit Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Linus Torvalds Cc: Andy Lutomirski Cc: Brian Gerst Cc: Peter Zijlstra Cc: Arnd Bergmann Cc: Boqun Feng Cc: "David S. Miller" Cc: Denys Vlasenko Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Kent Overstreet Cc: Paolo Abeni Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/kernel/kgdb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 9c9faa1634fb..102641fd2172 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -655,7 +655,7 @@ void kgdb_arch_late(void) if (breakinfo[i].pev) continue; breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL); - if (IS_ERR((void * __force)breakinfo[i].pev)) { + if (IS_ERR_PCPU(breakinfo[i].pev)) { printk(KERN_ERR "kgdb: Could not allocate hw" "breakpoints\nDisabling the kernel debugger\n"); breakinfo[i].pev = NULL; -- cgit v1.2.3 From 8a3c392388c6a6e0c8937a24712b630ec9ac7016 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 27 Jan 2025 17:05:07 +0100 Subject: percpu: use TYPEOF_UNQUAL() in variable declarations Use TYPEOF_UNQUAL() to declare variables as a corresponding type without named address space qualifier to avoid "`__seg_gs' specified for auto variable `var'" errors. Link: https://lkml.kernel.org/r/20250127160709.80604-4-ubizjak@gmail.com Signed-off-by: Uros Bizjak Acked-by: Nadav Amit Acked-by: Christoph Lameter Cc: Dennis Zhou Cc: Tejun Heo Cc: Andy Lutomirski Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Kent Overstreet Cc: Arnd Bergmann Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Peter Zijlstra Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: Linus Torvalds Cc: Brian Gerst Cc: Denys Vlasenko Signed-off-by: Andrew Morton --- arch/x86/include/asm/percpu.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index e525cd85f999..666e4137b09f 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -180,7 +180,7 @@ do { \ __pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val); \ \ if (0) { \ - typeof(_var) pto_tmp__; \ + TYPEOF_UNQUAL(_var) pto_tmp__; \ pto_tmp__ = (_val); \ (void)pto_tmp__; \ } \ @@ -219,7 +219,7 @@ do { \ __pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val); \ \ if (0) { \ - typeof(_var) pto_tmp__; \ + TYPEOF_UNQUAL(_var) pto_tmp__; \ pto_tmp__ = (_val); \ (void)pto_tmp__; \ } \ @@ -240,7 +240,7 @@ do { \ (val) == (typeof(val))-1)) ? (int)(val) : 0; \ \ if (0) { \ - typeof(var) pao_tmp__; \ + TYPEOF_UNQUAL(var) pao_tmp__; \ pao_tmp__ = (val); \ (void)pao_tmp__; \ } \ @@ -273,7 +273,7 @@ do { \ */ #define raw_percpu_xchg_op(_var, _nval) \ ({ \ - typeof(_var) pxo_old__ = raw_cpu_read(_var); \ + TYPEOF_UNQUAL(_var) pxo_old__ = raw_cpu_read(_var); \ \ raw_cpu_write(_var, _nval); \ \ @@ -287,7 +287,7 @@ do { \ */ #define this_percpu_xchg_op(_var, _nval) \ ({ \ - typeof(_var) pxo_old__ = this_cpu_read(_var); \ + TYPEOF_UNQUAL(_var) pxo_old__ = this_cpu_read(_var); \ \ do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval)); \ \ -- cgit v1.2.3 From 6a39fe05ecaa3946ed0af9efd3e56689d519e420 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 27 Jan 2025 17:05:08 +0100 Subject: percpu: use TYPEOF_UNQUAL() in *_cpu_ptr() accessors Use TYPEOF_UNQUAL() macro to declare the return type of *_cpu_ptr() accessors in the generic named address space to avoid access to data from pointer to non-enclosed address space type of errors. Link: https://lkml.kernel.org/r/20250127160709.80604-5-ubizjak@gmail.com Signed-off-by: Uros Bizjak Acked-by: Nadav Amit Acked-by: Christoph Lameter Cc: Dennis Zhou Cc: Tejun Heo Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Linus Torvalds Cc: Andy Lutomirski Cc: Brian Gerst Cc: Peter Zijlstra Cc: Arnd Bergmann Cc: Boqun Feng Cc: "David S. Miller" Cc: Denys Vlasenko Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Kent Overstreet Cc: Paolo Abeni Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/include/asm/percpu.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 666e4137b09f..27f668660abe 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -73,10 +73,14 @@ unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off); \ \ tcp_ptr__ += (__force unsigned long)(_ptr); \ - (typeof(*(_ptr)) __kernel __force *)tcp_ptr__; \ + (TYPEOF_UNQUAL(*(_ptr)) __force __kernel *)tcp_ptr__; \ }) #else -#define arch_raw_cpu_ptr(_ptr) ({ BUILD_BUG(); (typeof(_ptr))0; }) +#define arch_raw_cpu_ptr(_ptr) \ +({ \ + BUILD_BUG(); \ + (TYPEOF_UNQUAL(*(_ptr)) __force __kernel *)0; \ +}) #endif #define PER_CPU_VAR(var) %__percpu_seg:(var)__percpu_rel -- cgit v1.2.3 From 6a367577153acd9b432a5340fb10891eeb7e10f1 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 27 Jan 2025 17:05:10 +0100 Subject: percpu/x86: enable strict percpu checks via named AS qualifiers This patch declares percpu variables in __seg_gs/__seg_fs named AS and keeps them named AS qualified until they are dereferenced with percpu accessor. This approach enables various compiler check for cross-namespace variable assignments. Link: https://lkml.kernel.org/r/20250127160709.80604-7-ubizjak@gmail.com Signed-off-by: Uros Bizjak Acked-by: Nadav Amit Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Linus Torvalds Cc: Andy Lutomirski Cc: Brian Gerst Cc: Peter Zijlstra Cc: Arnd Bergmann Cc: Boqun Feng Cc: "David S. Miller" Cc: Denys Vlasenko Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Kent Overstreet Cc: Paolo Abeni Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/x86/include/asm/percpu.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 27f668660abe..474d648bca9a 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -95,9 +95,18 @@ #endif /* CONFIG_SMP */ -#define __my_cpu_type(var) typeof(var) __percpu_seg_override -#define __my_cpu_ptr(ptr) (__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr) -#define __my_cpu_var(var) (*__my_cpu_ptr(&(var))) +#if defined(CONFIG_USE_X86_SEG_SUPPORT) && defined(USE_TYPEOF_UNQUAL) +# define __my_cpu_type(var) typeof(var) +# define __my_cpu_ptr(ptr) (ptr) +# define __my_cpu_var(var) (var) + +# define __percpu_qual __percpu_seg_override +#else +# define __my_cpu_type(var) typeof(var) __percpu_seg_override +# define __my_cpu_ptr(ptr) (__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr) +# define __my_cpu_var(var) (*__my_cpu_ptr(&(var))) +#endif + #define __percpu_arg(x) __percpu_prefix "%" #x #define __force_percpu_arg(x) __force_percpu_prefix "%" #x -- cgit v1.2.3 From 6df8bae8e851eacf2acf2237860213e002aba74f Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Wed, 29 Jan 2025 18:06:32 +0000 Subject: mm: zbud: remove zbud The zbud compressed pages allocator is rarely used, most users use zsmalloc. zbud consumes much more memory (only stores 1 or 2 compressed pages per physical page). The only advantage of zbud is a marginal performance improvement that by no means justify the memory overhead. Historically, zsmalloc had significantly worse latency than zbud and z3fold but offered better memory savings. This is no longer the case as shown by a simple recent analysis [1]. In a kernel build test on tmpfs in a limited cgroup, zbud 2-3% less time than zsmalloc, but at the cost of using ~32% more memory (1.5G vs 1.13G). The tradeoff does not make sense for zbud in any practical scenario. The only alleged advantage of zbud is not having the dependency on CONFIG_MMU, but CONFIG_SWAP already depends on CONFIG_MMU anyway, and zbud is only used by zswap. Remove zbud after z3fold's removal, leaving zsmalloc as the one and only zpool allocator. Leave the removal of the zpool API (and its associated config options) to a followup cleanup after no more allocators show up. Deprecating zbud for a few cycles before removing it was initially proposed [2], like z3fold was marked as deprecated for 2 cycles [3]. However, Johannes rightfully pointed out that the 2 cycles is too short for most downstream consumers, and z3fold was deprecated first only as a courtesy anyway. [1]https://lore.kernel.org/lkml/CAJD7tkbRF6od-2x_L8-A1QL3=2Ww13sCj4S3i4bNndqF+3+_Vg@mail.gmail.com/ [2]https://lore.kernel.org/lkml/Z5gdnSX5Lv-nfjQL@google.com/ [3]https://lore.kernel.org/lkml/20240904233343.933462-1-yosryahmed@google.com/ Link: https://lkml.kernel.org/r/20250129180633.3501650-3-yosry.ahmed@linux.dev Signed-off-by: Yosry Ahmed Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Nhat Pham Cc: Alexander Gordeev Cc: Chengming Zhou Cc: Christian Borntraeger Cc: Dan Streetman Cc: Heiko Carstens Cc: Huacai Chen Cc: Miaohe Lin Cc: Seth Jennings Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Vitaly Wool Cc: Vlastimil Babka Cc: WANG Xuerui Signed-off-by: Andrew Morton --- arch/loongarch/configs/loongson3_defconfig | 3 +-- arch/s390/configs/debug_defconfig | 2 +- arch/s390/configs/defconfig | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index 73c77500ac46..7ce5beb3cbf3 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -109,8 +109,7 @@ CONFIG_BINFMT_MISC=m CONFIG_ZPOOL=y CONFIG_ZSWAP=y CONFIG_ZSWAP_COMPRESSOR_DEFAULT_ZSTD=y -CONFIG_ZBUD=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y # CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE is not set diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 80bdfbae6e5b..074df6328376 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -92,7 +92,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y -CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_SLAB_BUCKETS=y CONFIG_SLUB_STATS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 449a0e996b96..ac68e663dd4d 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -86,7 +86,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y -CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_SLAB_BUCKETS=y # CONFIG_COMPAT_BRK is not set -- cgit v1.2.3 From 2f4ab3ac10e1476abb6ed55f0b5f176cf635e776 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Fri, 14 Feb 2025 22:30:13 +1300 Subject: mm: support tlbbatch flush for a range of PTEs This patch lays the groundwork for supporting batch PTE unmapping in try_to_unmap_one(). It introduces range handling for TLB batch flushing, with the range currently set to the size of PAGE_SIZE. The function __flush_tlb_range_nosync() is architecture-specific and is only used within arch/arm64. This function requires the mm structure instead of the vma structure. To allow its reuse by arch_tlbbatch_add_pending(), which operates with mm but not vma, this patch modifies the argument of __flush_tlb_range_nosync() to take mm as its parameter. Link: https://lkml.kernel.org/r/20250214093015.51024-3-21cnbao@gmail.com Signed-off-by: Barry Song Acked-by: Will Deacon Reviewed-by: Kefeng Wang Cc: Catalin Marinas Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Ryan Roberts Cc: Shaoqin Huang Cc: Gavin Shan Cc: Mark Rutland Cc: David Hildenbrand Cc: Lance Yang Cc: "Kirill A. Shutemov" Cc: Yosry Ahmed Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Yicong Yang Cc: Baolin Wang Cc: Chis Li Cc: "Huang, Ying" Cc: Kairui Song Cc: Lorenzo Stoakes Cc: Mauricio Faria de Oliveira Cc: Tangquan Zheng Signed-off-by: Andrew Morton --- arch/arm64/include/asm/tlbflush.h | 23 +++++++++++------------ arch/arm64/mm/contpte.c | 2 +- arch/riscv/include/asm/tlbflush.h | 3 +-- arch/riscv/mm/tlbflush.c | 3 +-- arch/x86/include/asm/tlbflush.h | 3 +-- 5 files changed, 15 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index bc94e036a26b..b7e1920570bd 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -322,13 +322,6 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) return true; } -static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm, - unsigned long uaddr) -{ - __flush_tlb_page_nosync(mm, uaddr); -} - /* * If mprotect/munmap/etc occurs during TLB batched flushing, we need to * synchronise all the TLBI issued with a DSB to avoid the race mentioned in @@ -448,7 +441,7 @@ static inline bool __flush_tlb_range_limit_excess(unsigned long start, return false; } -static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma, +static inline void __flush_tlb_range_nosync(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long stride, bool last_level, int tlb_level) @@ -460,12 +453,12 @@ static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma, pages = (end - start) >> PAGE_SHIFT; if (__flush_tlb_range_limit_excess(start, end, pages, stride)) { - flush_tlb_mm(vma->vm_mm); + flush_tlb_mm(mm); return; } dsb(ishst); - asid = ASID(vma->vm_mm); + asid = ASID(mm); if (last_level) __flush_tlb_range_op(vale1is, start, pages, stride, asid, @@ -474,7 +467,7 @@ static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma, __flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true, lpa2_is_enabled()); - mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } static inline void __flush_tlb_range(struct vm_area_struct *vma, @@ -482,7 +475,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long stride, bool last_level, int tlb_level) { - __flush_tlb_range_nosync(vma, start, end, stride, + __flush_tlb_range_nosync(vma->vm_mm, start, end, stride, last_level, tlb_level); dsb(ish); } @@ -533,6 +526,12 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr) dsb(ish); isb(); } + +static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, unsigned long start, unsigned long end) +{ + __flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3); +} #endif #endif diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 55107d27d3f8..bcac4f55f9c1 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -335,7 +335,7 @@ int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, * eliding the trailing DSB applies here. */ addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); - __flush_tlb_range_nosync(vma, addr, addr + CONT_PTE_SIZE, + __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE, PAGE_SIZE, true, 3); } diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 72e559934952..ce0dd0fed764 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -60,8 +60,7 @@ void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, bool arch_tlbbatch_should_defer(struct mm_struct *mm); void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm, - unsigned long uaddr); + struct mm_struct *mm, unsigned long start, unsigned long end); void arch_flush_tlb_batched_pending(struct mm_struct *mm); void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 9b6e86ce3867..74dd9307fbf1 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -186,8 +186,7 @@ bool arch_tlbbatch_should_defer(struct mm_struct *mm) } void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm, - unsigned long uaddr) + struct mm_struct *mm, unsigned long start, unsigned long end) { cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 02fc2aa06e9e..29373da7b00a 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -279,8 +279,7 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) } static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, - struct mm_struct *mm, - unsigned long uaddr) + struct mm_struct *mm, unsigned long start, unsigned long end) { inc_mm_tlb_gen(mm); cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); -- cgit v1.2.3 From 86758b504864913233f6a16076184ba784cd4466 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Tue, 18 Feb 2025 15:49:54 +0530 Subject: mm/ioremap: pass pgprot_t to ioremap_prot() instead of unsigned long ioremap_prot() currently accepts pgprot_val parameter as an unsigned long, thus implicitly assuming that pgprot_val and pgprot_t could never be bigger than unsigned long. But this assumption soon will not be true on arm64 when using D128 pgtables. In 128 bit page table configuration, unsigned long is 64 bit, but pgprot_t is 128 bit. Passing platform abstracted pgprot_t argument is better as compared to size based data types. Let's change the parameter to directly pass pgprot_t like another similar helper generic_ioremap_prot(). Without this change in place, D128 configuration does not work on arm64 as the top 64 bits gets silently stripped when passing the protection value to this function. Link: https://lkml.kernel.org/r/20250218101954.415331-1-anshuman.khandual@arm.com Signed-off-by: Ryan Roberts Co-developed-by: Anshuman Khandual Signed-off-by: Anshuman Khandual Acked-by: Catalin Marinas [arm64] Signed-off-by: Andrew Morton --- arch/arc/mm/ioremap.c | 6 ++---- arch/arm64/include/asm/io.h | 6 +++--- arch/arm64/kernel/acpi.c | 2 +- arch/arm64/mm/ioremap.c | 3 +-- arch/csky/include/asm/io.h | 2 +- arch/loongarch/include/asm/io.h | 10 +++++----- arch/mips/include/asm/io.h | 8 ++++---- arch/mips/mm/ioremap.c | 4 ++-- arch/mips/mm/ioremap64.c | 4 ++-- arch/parisc/include/asm/io.h | 2 +- arch/parisc/mm/ioremap.c | 4 ++-- arch/powerpc/include/asm/io.h | 2 +- arch/powerpc/mm/ioremap.c | 4 ++-- arch/powerpc/platforms/ps3/spu.c | 4 ++-- arch/riscv/include/asm/io.h | 2 +- arch/riscv/kernel/acpi.c | 2 +- arch/s390/include/asm/io.h | 4 ++-- arch/s390/pci/pci.c | 4 ++-- arch/sh/boards/mach-landisk/setup.c | 2 +- arch/sh/boards/mach-lboxre2/setup.c | 2 +- arch/sh/boards/mach-sh03/setup.c | 2 +- arch/sh/include/asm/io.h | 2 +- arch/sh/mm/ioremap.c | 3 +-- arch/x86/include/asm/io.h | 2 +- arch/x86/mm/ioremap.c | 4 ++-- arch/xtensa/include/asm/io.h | 6 +++--- arch/xtensa/mm/ioremap.c | 4 ++-- 27 files changed, 48 insertions(+), 52 deletions(-) (limited to 'arch') diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c index b07004d53267..fd8897a0e52c 100644 --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -32,7 +32,7 @@ void __iomem *ioremap(phys_addr_t paddr, unsigned long size) return (void __iomem *)(u32)paddr; return ioremap_prot(paddr, size, - pgprot_val(pgprot_noncached(PAGE_KERNEL))); + pgprot_noncached(PAGE_KERNEL)); } EXPORT_SYMBOL(ioremap); @@ -44,10 +44,8 @@ EXPORT_SYMBOL(ioremap); * might need finer access control (R/W/X) */ void __iomem *ioremap_prot(phys_addr_t paddr, size_t size, - unsigned long flags) + pgprot_t prot) { - pgprot_t prot = __pgprot(flags); - /* force uncached */ return generic_ioremap_prot(paddr, size, pgprot_noncached(prot)); } diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 76ebbdc6ffdd..9b96840fb979 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -270,9 +270,9 @@ int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook); #define _PAGE_IOREMAP PROT_DEVICE_nGnRE #define ioremap_wc(addr, size) \ - ioremap_prot((addr), (size), PROT_NORMAL_NC) + ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC)) #define ioremap_np(addr, size) \ - ioremap_prot((addr), (size), PROT_DEVICE_nGnRnE) + ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE)) /* * io{read,write}{16,32,64}be() macros @@ -293,7 +293,7 @@ static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size) if (pfn_is_map_memory(__phys_to_pfn(addr))) return (void __iomem *)__phys_to_virt(addr); - return ioremap_prot(addr, size, PROT_NORMAL); + return ioremap_prot(addr, size, __pgprot(PROT_NORMAL)); } /* diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index e6f66491fbe9..b9a66fc146c9 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -379,7 +379,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) prot = __acpi_get_writethrough_mem_attribute(); } } - return ioremap_prot(phys, size, pgprot_val(prot)); + return ioremap_prot(phys, size, prot); } /* diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index 6cc0b7e7eb03..10e246f11271 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -15,10 +15,9 @@ int arm64_ioremap_prot_hook_register(ioremap_prot_hook_t hook) } void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot) + pgprot_t pgprot) { unsigned long last_addr = phys_addr + size - 1; - pgprot_t pgprot = __pgprot(prot); /* Don't allow outside PHYS_MASK */ if (last_addr & ~PHYS_MASK) diff --git a/arch/csky/include/asm/io.h b/arch/csky/include/asm/io.h index ed53f0b47388..536d3bf32ff1 100644 --- a/arch/csky/include/asm/io.h +++ b/arch/csky/include/asm/io.h @@ -36,7 +36,7 @@ */ #define ioremap_wc(addr, size) \ ioremap_prot((addr), (size), \ - (_PAGE_IOREMAP & ~_CACHE_MASK) | _CACHE_UNCACHED) + __pgprot((_PAGE_IOREMAP & ~_CACHE_MASK) | _CACHE_UNCACHED)) #include diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index e77a56eaf906..eaff72b38dc8 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -23,9 +23,9 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size); #ifdef CONFIG_ARCH_IOREMAP static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, - unsigned long prot_val) + pgprot_t prot) { - switch (prot_val & _CACHE_MASK) { + switch (pgprot_val(prot) & _CACHE_MASK) { case _CACHE_CC: return (void __iomem *)(unsigned long)(CACHE_BASE + offset); case _CACHE_SUC: @@ -38,7 +38,7 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, } #define ioremap(offset, size) \ - ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_SUC)) + ioremap_prot((offset), (size), PAGE_KERNEL_SUC) #define iounmap(addr) ((void)(addr)) @@ -55,10 +55,10 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, */ #define ioremap_wc(offset, size) \ ioremap_prot((offset), (size), \ - pgprot_val(wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC)) + wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC) #define ioremap_cache(offset, size) \ - ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL)) + ioremap_prot((offset), (size), PAGE_KERNEL) #define mmiowb() wmb() diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index 0bddb568af7c..4dacf40ebefd 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -126,7 +126,7 @@ static inline unsigned long isa_virt_to_bus(volatile void *address) } void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, - unsigned long prot_val); + pgprot_t prot); void iounmap(const volatile void __iomem *addr); /* @@ -141,7 +141,7 @@ void iounmap(const volatile void __iomem *addr); * address. */ #define ioremap(offset, size) \ - ioremap_prot((offset), (size), _CACHE_UNCACHED) + ioremap_prot((offset), (size), __pgprot(_CACHE_UNCACHED)) /* * ioremap_cache - map bus memory into CPU space @@ -159,7 +159,7 @@ void iounmap(const volatile void __iomem *addr); * memory-like regions on I/O busses. */ #define ioremap_cache(offset, size) \ - ioremap_prot((offset), (size), _page_cachable_default) + ioremap_prot((offset), (size), __pgprot(_page_cachable_default)) /* * ioremap_wc - map bus memory into CPU space @@ -180,7 +180,7 @@ void iounmap(const volatile void __iomem *addr); * _CACHE_UNCACHED option (see cpu_probe() method). */ #define ioremap_wc(offset, size) \ - ioremap_prot((offset), (size), boot_cpu_data.writecombine) + ioremap_prot((offset), (size), __pgprot(boot_cpu_data.writecombine)) #if defined(CONFIG_CPU_CAVIUM_OCTEON) #define war_io_reorder_wmb() wmb() diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c index d8243d61ef32..c6c4576cd4a8 100644 --- a/arch/mips/mm/ioremap.c +++ b/arch/mips/mm/ioremap.c @@ -44,9 +44,9 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, * ioremap_prot gives the caller control over cache coherency attributes (CCA) */ void __iomem *ioremap_prot(phys_addr_t phys_addr, unsigned long size, - unsigned long prot_val) + pgprot_t prot) { - unsigned long flags = prot_val & _CACHE_MASK; + unsigned long flags = pgprot_val(prot) & _CACHE_MASK; unsigned long offset, pfn, last_pfn; struct vm_struct *area; phys_addr_t last_addr; diff --git a/arch/mips/mm/ioremap64.c b/arch/mips/mm/ioremap64.c index 15e7820d6a5f..acc03ba20098 100644 --- a/arch/mips/mm/ioremap64.c +++ b/arch/mips/mm/ioremap64.c @@ -3,9 +3,9 @@ #include void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, - unsigned long prot_val) + pgprot_t prot) { - unsigned long flags = prot_val & _CACHE_MASK; + unsigned long flags = pgprot_val(prot) & _CACHE_MASK; u64 base = (flags == _CACHE_UNCACHED ? IO_BASE : UNCAC_BASE); void __iomem *addr; diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h index 3143cf29ce27..04b783e2a6d1 100644 --- a/arch/parisc/include/asm/io.h +++ b/arch/parisc/include/asm/io.h @@ -131,7 +131,7 @@ static inline void gsc_writeq(unsigned long long val, unsigned long addr) _PAGE_ACCESSED | _PAGE_NO_CACHE) #define ioremap_wc(addr, size) \ - ioremap_prot((addr), (size), _PAGE_IOREMAP) + ioremap_prot((addr), (size), __pgprot(_PAGE_IOREMAP)) #define pci_iounmap pci_iounmap diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index fd996472dfe7..0b65c4b3baee 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -14,7 +14,7 @@ #include void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot) + pgprot_t prot) { #ifdef CONFIG_EISA unsigned long end = phys_addr + size - 1; @@ -41,6 +41,6 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, } } - return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); + return generic_ioremap_prot(phys_addr, size, prot); } EXPORT_SYMBOL(ioremap_prot); diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index fd92ac450169..0436cdc7cfcc 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -895,7 +895,7 @@ void __iomem *ioremap_wt(phys_addr_t address, unsigned long size); void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size); #define ioremap_cache(addr, size) \ - ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) + ioremap_prot((addr), (size), PAGE_KERNEL) #define iounmap iounmap diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c index 7b0afcabd89f..0d6615620ada 100644 --- a/arch/powerpc/mm/ioremap.c +++ b/arch/powerpc/mm/ioremap.c @@ -41,9 +41,9 @@ void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size) return __ioremap_caller(addr, size, prot, caller); } -void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long flags) +void __iomem *ioremap_prot(phys_addr_t addr, size_t size, pgprot_t prot) { - pte_t pte = __pte(flags); + pte_t pte = __pte(pgprot_val(prot)); void *caller = __builtin_return_address(0); /* writeable implies dirty for kernel addresses */ diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index 4a2520ec6d7f..61b37c9400b2 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -190,10 +190,10 @@ static void spu_unmap(struct spu *spu) static int __init setup_areas(struct spu *spu) { struct table {char* name; unsigned long addr; unsigned long size;}; - unsigned long shadow_flags = pgprot_val(pgprot_noncached_wc(PAGE_KERNEL_RO)); spu_pdata(spu)->shadow = ioremap_prot(spu_pdata(spu)->shadow_addr, - sizeof(struct spe_shadow), shadow_flags); + sizeof(struct spe_shadow), + pgprot_noncached_wc(PAGE_KERNEL_RO)); if (!spu_pdata(spu)->shadow) { pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__); goto fail_ioremap; diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 1c5c641075d2..0536846db9b6 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -137,7 +137,7 @@ __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) #ifdef CONFIG_MMU #define arch_memremap_wb(addr, size) \ - ((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL)) + ((__force void *)ioremap_prot((addr), (size), __pgprot(_PAGE_KERNEL))) #endif #endif /* _ASM_RISCV_IO_H */ diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 2fd29695a788..3f6d5a6789e8 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -305,7 +305,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) } } - return ioremap_prot(phys, size, pgprot_val(prot)); + return ioremap_prot(phys, size, prot); } #ifdef CONFIG_PCI diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index fc9933a743d6..82f1043a4fc3 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -33,9 +33,9 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL) #define ioremap_wc(addr, size) \ - ioremap_prot((addr), (size), pgprot_val(pgprot_writecombine(PAGE_KERNEL))) + ioremap_prot((addr), (size), pgprot_writecombine(PAGE_KERNEL)) #define ioremap_wt(addr, size) \ - ioremap_prot((addr), (size), pgprot_val(pgprot_writethrough(PAGE_KERNEL))) + ioremap_prot((addr), (size), pgprot_writethrough(PAGE_KERNEL)) static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) { diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 88f72745fa59..9fdcd733d40e 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -255,7 +255,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, } void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot) + pgprot_t prot) { /* * When PCI MIO instructions are unavailable the "physical" address @@ -265,7 +265,7 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, if (!static_branch_unlikely(&have_mio)) return (void __iomem *)phys_addr; - return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); + return generic_ioremap_prot(phys_addr, size, prot); } EXPORT_SYMBOL(ioremap_prot); diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c index 2c44b94f82fb..1b3f43c3ac46 100644 --- a/arch/sh/boards/mach-landisk/setup.c +++ b/arch/sh/boards/mach-landisk/setup.c @@ -58,7 +58,7 @@ static int __init landisk_devices_setup(void) /* open I/O area window */ paddrbase = virt_to_phys((void *)PA_AREA5_IO); prot = PAGE_KERNEL_PCC(1, _PAGE_PCC_IO16); - cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, pgprot_val(prot)); + cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, prot); if (!cf_ide_base) { printk("allocate_cf_area : can't open CF I/O window!\n"); return -ENOMEM; diff --git a/arch/sh/boards/mach-lboxre2/setup.c b/arch/sh/boards/mach-lboxre2/setup.c index 20d01b430f2a..e95bde207adb 100644 --- a/arch/sh/boards/mach-lboxre2/setup.c +++ b/arch/sh/boards/mach-lboxre2/setup.c @@ -53,7 +53,7 @@ static int __init lboxre2_devices_setup(void) paddrbase = virt_to_phys((void*)PA_AREA5_IO); psize = PAGE_SIZE; prot = PAGE_KERNEL_PCC(1, _PAGE_PCC_IO16); - cf0_io_base = (u32)ioremap_prot(paddrbase, psize, pgprot_val(prot)); + cf0_io_base = (u32)ioremap_prot(paddrbase, psize, prot); if (!cf0_io_base) { printk(KERN_ERR "%s : can't open CF I/O window!\n" , __func__ ); return -ENOMEM; diff --git a/arch/sh/boards/mach-sh03/setup.c b/arch/sh/boards/mach-sh03/setup.c index 3901b6031ad5..5c9312f334d3 100644 --- a/arch/sh/boards/mach-sh03/setup.c +++ b/arch/sh/boards/mach-sh03/setup.c @@ -75,7 +75,7 @@ static int __init sh03_devices_setup(void) /* open I/O area window */ paddrbase = virt_to_phys((void *)PA_AREA5_IO); prot = PAGE_KERNEL_PCC(1, _PAGE_PCC_IO16); - cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, pgprot_val(prot)); + cf_ide_base = ioremap_prot(paddrbase, PAGE_SIZE, prot); if (!cf_ide_base) { printk("allocate_cf_area : can't open CF I/O window!\n"); return -ENOMEM; diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index cf5eab840d57..531ec49b878d 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -299,7 +299,7 @@ unsigned long long poke_real_address_q(unsigned long long addr, #define _PAGE_IOREMAP pgprot_val(PAGE_KERNEL_NOCACHE) #define ioremap_cache(addr, size) \ - ioremap_prot((addr), (size), pgprot_val(PAGE_KERNEL)) + ioremap_prot((addr), (size), PAGE_KERNEL) #endif /* CONFIG_MMU */ #include diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c index 33d20f34560f..5bbde53fb32d 100644 --- a/arch/sh/mm/ioremap.c +++ b/arch/sh/mm/ioremap.c @@ -73,10 +73,9 @@ __ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot) #endif /* CONFIG_29BIT */ void __iomem __ref *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot) + pgprot_t pgprot) { void __iomem *mapped; - pgprot_t pgprot = __pgprot(prot); mapped = __ioremap_trapped(phys_addr, size); if (mapped) diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index ed580c7f9d0a..0794936ec187 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -170,7 +170,7 @@ extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); #define ioremap_uc ioremap_uc extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); #define ioremap_cache ioremap_cache -extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, pgprot_t prot); #define ioremap_prot ioremap_prot extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size); #define ioremap_encrypted ioremap_encrypted diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 38ff7791a9c7..d501f0871aa5 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -440,10 +440,10 @@ void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) EXPORT_SYMBOL(ioremap_cache); void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, - unsigned long prot_val) + pgprot_t prot) { return __ioremap_caller(phys_addr, size, - pgprot2cachemode(__pgprot(prot_val)), + pgprot2cachemode(prot), __builtin_return_address(0), false); } EXPORT_SYMBOL(ioremap_prot); diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h index 934e58399c8c..7cdcc2deab3e 100644 --- a/arch/xtensa/include/asm/io.h +++ b/arch/xtensa/include/asm/io.h @@ -29,7 +29,7 @@ * I/O memory mapping functions. */ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot); + pgprot_t prot); #define ioremap_prot ioremap_prot #define iounmap iounmap @@ -40,7 +40,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size) return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_BYPASS_VADDR); else return ioremap_prot(offset, size, - pgprot_val(pgprot_noncached(PAGE_KERNEL))); + pgprot_noncached(PAGE_KERNEL)); } #define ioremap ioremap @@ -51,7 +51,7 @@ static inline void __iomem *ioremap_cache(unsigned long offset, && offset - XCHAL_KIO_PADDR < XCHAL_KIO_SIZE) return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_CACHED_VADDR); else - return ioremap_prot(offset, size, pgprot_val(PAGE_KERNEL)); + return ioremap_prot(offset, size, PAGE_KERNEL); } #define ioremap_cache ioremap_cache diff --git a/arch/xtensa/mm/ioremap.c b/arch/xtensa/mm/ioremap.c index 8ca660b7ab49..26f238fa9d0d 100644 --- a/arch/xtensa/mm/ioremap.c +++ b/arch/xtensa/mm/ioremap.c @@ -11,12 +11,12 @@ #include void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot) + pgprot_t prot) { unsigned long pfn = __phys_to_pfn((phys_addr)); WARN_ON(pfn_valid(pfn)); - return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); + return generic_ioremap_prot(phys_addr, size, prot); } EXPORT_SYMBOL(ioremap_prot); -- cgit v1.2.3 From 624ab90b7b8758090654520b03c97cecc438a414 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Fri, 28 Feb 2025 18:29:04 +0000 Subject: mm/cma: introduce cma_intersects function Now that CMA areas can have multiple physical ranges, code can't assume a CMA struct represents a base_pfn plus a size, as returned from cma_get_base. Most cases are ok though, since they all explicitly refer to CMA areas that were created using existing interfaces (cma_declare_contiguous_nid or cma_init_reserved_mem), which guarantees they have just one physical range. An exception is the s390 code, which walks all CMA ranges to see if they intersect with a range of memory that is about to be hotremoved. So, in the future, it might run in to multi-range areas. To keep this check working, define a cma_intersects function. This just checks if a physaddr range intersects any of the ranges. Use it in the s390 check. Link: https://lkml.kernel.org/r/20250228182928.2645936-4-fvdl@google.com Signed-off-by: Frank van der Linden Acked-by: Alexander Gordeev Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dan Carpenter Cc: Dave Hansen Cc: David Hildenbrand Cc: Joao Martins Cc: Johannes Weiner Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Muchun Song Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Roman Gushchin (Cruise) Cc: Usama Arif Cc: Yu Zhao Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/s390/mm/init.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index f2298f7a3f21..d88cb1c13f7d 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -239,16 +239,13 @@ struct s390_cma_mem_data { static int s390_cma_check_range(struct cma *cma, void *data) { struct s390_cma_mem_data *mem_data; - unsigned long start, end; mem_data = data; - start = cma_get_base(cma); - end = start + cma_get_size(cma); - if (end < mem_data->start) - return 0; - if (start >= mem_data->end) - return 0; - return -EBUSY; + + if (cma_intersects(cma, mem_data->start, mem_data->end)) + return -EBUSY; + + return 0; } static int s390_cma_mem_notifier(struct notifier_block *nb, -- cgit v1.2.3 From d3cd80c5879443c6986091717b6de889c60b3eb1 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Fri, 28 Feb 2025 18:29:09 +0000 Subject: x86/mm: make register_page_bootmem_memmap handle PTE mappings register_page_bootmem_memmap expects that vmemmap pages handed to it are PMD-mapped, and that the number of pages to call get_page_bootmem on is PMD-aligned. This is currently a correct assumption, but will no longer be true once pre-HVO of hugetlb pages is implemented. Make it handle PTE-mapped vmemmap pages and a nr_pages argument that is not necessarily PAGES_PER_SECTION. Link: https://lkml.kernel.org/r/20250228182928.2645936-9-fvdl@google.com Signed-off-by: Frank van der Linden Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Dan Carpenter Cc: Alexander Gordeev Cc: Arnd Bergmann Cc: David Hildenbrand Cc: Heiko Carstens Cc: Joao Martins Cc: Johannes Weiner Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Muchun Song Cc: Oscar Salvador Cc: Roman Gushchin (Cruise) Cc: Usama Arif Cc: Vasily Gorbik Cc: Yu Zhao Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/x86/mm/init_64.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 01ea7c6df303..6e8e4ef5312a 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1599,11 +1599,14 @@ void register_page_bootmem_memmap(unsigned long section_nr, } get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO); - if (!boot_cpu_has(X86_FEATURE_PSE)) { + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + continue; + } + + if (!boot_cpu_has(X86_FEATURE_PSE) || !pmd_leaf(*pmd)) { next = (addr + PAGE_SIZE) & PAGE_MASK; - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) - continue; get_page_bootmem(section_nr, pmd_page(*pmd), MIX_SECTION_INFO); @@ -1614,12 +1617,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, SECTION_INFO); } else { next = pmd_addr_end(addr, end); - - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) - continue; - - nr_pmd_pages = 1 << get_order(PMD_SIZE); + nr_pmd_pages = (next - addr) >> PAGE_SHIFT; page = pmd_page(*pmd); while (nr_pmd_pages--) get_page_bootmem(section_nr, page++, -- cgit v1.2.3 From 243a75e236802614075511266c8d1834d4bcffe9 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Fri, 28 Feb 2025 18:29:10 +0000 Subject: mm/bootmem_info: export register_page_bootmem_memmap If other mm code wants to use this function for early memmap inialization (on the platforms that have it), it should be made available properly, not just unconditionally in mm.h Make this function available for such cases. Link: https://lkml.kernel.org/r/20250228182928.2645936-10-fvdl@google.com Signed-off-by: Frank van der Linden Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dan Carpenter Cc: Dave Hansen Cc: David Hildenbrand Cc: Heiko Carstens Cc: Joao Martins Cc: Johannes Weiner Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Muchun Song Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Roman Gushchin (Cruise) Cc: Usama Arif Cc: Vasily Gorbik Cc: Yu Zhao Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/powerpc/mm/init_64.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index d96bbc001e73..b6f3ae03ca9e 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -386,10 +387,13 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, } #endif + +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) { } +#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */ #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -- cgit v1.2.3 From 752fe17af693323dba5622b19c858a46fed219a1 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Fri, 28 Feb 2025 18:29:18 +0000 Subject: mm/hugetlb: add pre-HVO framework Define flags for pre-HVOed bootmem hugetlb pages, and act on them. The most important flag is the HVO flag, signalling that a bootmem allocated gigantic page has already been HVO-ed. If this flag is seen by the hugetlb bootmem gather code, the page is marked as HVO optimized. The HVO code will then not try to optimize it again. Instead, it will just map the tail page mirror pages read-only, completing the HVO steps. No functional change, as nothing sets the flags yet. Link: https://lkml.kernel.org/r/20250228182928.2645936-18-fvdl@google.com Signed-off-by: Frank van der Linden Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dan Carpenter Cc: Dave Hansen Cc: David Hildenbrand Cc: Heiko Carstens Cc: Joao Martins Cc: Johannes Weiner Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Muchun Song Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Roman Gushchin (Cruise) Cc: Usama Arif Cc: Vasily Gorbik Cc: Yu Zhao Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/powerpc/mm/hugetlbpage.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 6b043180220a..d3c1b749dcfc 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -113,6 +113,7 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) gpage_freearray[nr_gpages] = 0; list_add(&m->list, &huge_boot_pages[0]); m->hstate = hstate; + m->flags = 0; return 1; } -- cgit v1.2.3 From 665eaf313314432b5bbb5f71ec71e275ff2358e0 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Fri, 28 Feb 2025 18:29:21 +0000 Subject: x86/setup: call hugetlb_bootmem_alloc early Call hugetlb_bootmem_allloc in an earlier spot in setup, after hugelb_cma_reserve. This will make vmemmap preinit of the sections covered by the allocated hugetlb pages possible. Link: https://lkml.kernel.org/r/20250228182928.2645936-21-fvdl@google.com Signed-off-by: Frank van der Linden Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Alexander Gordeev Cc: Arnd Bergmann Cc: Dan Carpenter Cc: David Hildenbrand Cc: Heiko Carstens Cc: Joao Martins Cc: Johannes Weiner Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Muchun Song Cc: Oscar Salvador Cc: Roman Gushchin (Cruise) Cc: Usama Arif Cc: Vasily Gorbik Cc: Yu Zhao Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/x86/kernel/setup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cebee310e200..ff8604007b08 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1108,8 +1108,10 @@ void __init setup_arch(char **cmdline_p) initmem_init(); dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); - if (boot_cpu_has(X86_FEATURE_GBPAGES)) + if (boot_cpu_has(X86_FEATURE_GBPAGES)) { hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); + hugetlb_bootmem_alloc(); + } /* * Reserve memory for crash kernel after SRAT is parsed so that it -- cgit v1.2.3 From 08efe293503098b539cb18f55528176b6b559348 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Fri, 28 Feb 2025 18:29:22 +0000 Subject: x86/mm: set ARCH_WANT_HUGETLB_VMEMMAP_PREINIT Now that hugetlb bootmem pages are allocated earlier, and available for section preinit (HVO-style), set ARCH_WANT_HUGETLB_VMEMMAP_PREINIT for x86_64, so that is can be done. This enables pre-HVO on x86_64. Link: https://lkml.kernel.org/r/20250228182928.2645936-22-fvdl@google.com Signed-off-by: Frank van der Linden Cc: Johannes Weiner Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dan Carpenter Cc: Dave Hansen Cc: David Hildenbrand Cc: Heiko Carstens Cc: Joao Martins Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Muchun Song Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Roman Gushchin (Cruise) Cc: Usama Arif Cc: Vasily Gorbik Cc: Yu Zhao Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0e27ebd7e36a..cf49c130d1d0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -146,6 +146,7 @@ config X86 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64 select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64 + select ARCH_WANT_HUGETLB_VMEMMAP_PREINIT if X86_64 select ARCH_WANTS_THP_SWAP if X86_64 select ARCH_HAS_PARANOID_L1D_FLUSH select BUILDTIME_TABLE_SORT -- cgit v1.2.3 From d2d78671408061b5332d9ad357686812bbec5070 Mon Sep 17 00:00:00 2001 From: Frank van der Linden Date: Fri, 28 Feb 2025 18:29:27 +0000 Subject: mm/hugetlb: enable bootmem allocation from CMA areas If hugetlb_cma_only is enabled, we know that hugetlb pages can only be allocated from CMA. Now that there is an interface to do early reservations from a CMA area (returning memblock memory), it can be used to allocate hugetlb pages from CMA. This also allows for doing pre-HVO on these pages (if enabled). Make sure to initialize the page structures and associated data correctly. Create a flag to signal that a hugetlb page has been allocated from CMA to make things a little easier. Some configurations of powerpc have a special hugetlb bootmem allocator, so introduce a boolean arch_specific_huge_bootmem_alloc that returns true if such an allocator is present. In that case, CMA bootmem allocations can't be used, so check that function before trying. Link: https://lkml.kernel.org/r/20250228182928.2645936-27-fvdl@google.com Signed-off-by: Frank van der Linden Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Alexander Gordeev Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dan Carpenter Cc: Dave Hansen Cc: David Hildenbrand Cc: Heiko Carstens Cc: Joao Martins Cc: Johannes Weiner Cc: Muchun Song Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Roman Gushchin (Cruise) Cc: Usama Arif Cc: Vasily Gorbik Cc: Yu Zhao Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/powerpc/include/asm/book3s/64/hugetlb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch') diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index f0bba9c5f9c3..bb786694dd26 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -94,4 +94,10 @@ static inline int check_and_get_huge_psize(int shift) return mmu_psize; } +#define arch_has_huge_bootmem_alloc arch_has_huge_bootmem_alloc + +static inline bool arch_has_huge_bootmem_alloc(void) +{ + return (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()); +} #endif -- cgit v1.2.3 From 2560c8c3f41d7a53e1554d1e4f207bf966e7527f Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Wed, 19 Feb 2025 12:24:02 +0100 Subject: arm/pgtable: remove duplicate included header file The header file asm-generic/pgtable-nopud.h is included whether CONFIG_MMU is defined or not. Include it only once before the #ifndef/#else/#endif preprocessor directives and remove the following make includecheck warning: asm-generic/pgtable-nopud.h is included more than once Link: https://lkml.kernel.org/r/20250219112403.3959-2-thorsten.blum@linux.dev Signed-off-by: Thorsten Blum Reviewed-by: Mike Rapoport (Microsoft) Signed-off-by: Andrew Morton --- arch/arm/include/asm/pgtable.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index be91e376df79..6b986ef6042f 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -19,14 +19,13 @@ extern struct page *empty_zero_page; #define ZERO_PAGE(vaddr) (empty_zero_page) #endif -#ifndef CONFIG_MMU - #include + +#ifndef CONFIG_MMU #include #else -#include #include #include -- cgit v1.2.3 From 2c5e6ac2db64ace51f66a9f3b3b3ab9553d748e8 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 26 Feb 2025 17:54:01 +0530 Subject: arch/powerpc: drop GENERIC_PTDUMP from mpc885_ads_defconfig GENERIC_PTDUMP gets selected on powerpc explicitly and hence can be dropped off from mpc885_ads_defconfig. Replace with CONFIG_PTDUMP_DEBUGFS instead. Link: https://lkml.kernel.org/r/20250226122404.1927473-3-anshuman.khandual@arm.com Fixes: e084728393a5 ("powerpc/ptdump: Convert powerpc to GENERIC_PTDUMP") Signed-off-by: Anshuman Khandual Suggested-by: Christophe Leroy Reviewed-by: Christophe Leroy Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Catalin Marinas Cc: Heiko Carstens Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Marc Zyngier Cc: Mark Rutland Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Steven Price Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/powerpc/configs/mpc885_ads_defconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig index 77306be62e9e..129355f87f80 100644 --- a/arch/powerpc/configs/mpc885_ads_defconfig +++ b/arch/powerpc/configs/mpc885_ads_defconfig @@ -78,4 +78,4 @@ CONFIG_DEBUG_VM_PGTABLE=y CONFIG_DETECT_HUNG_TASK=y CONFIG_BDI_SWITCH=y CONFIG_PPC_EARLY_DEBUG=y -CONFIG_GENERIC_PTDUMP=y +CONFIG_PTDUMP_DEBUGFS=y -- cgit v1.2.3 From f9aad622006bd64c28fdf73c03a1c5139fcbf049 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 26 Feb 2025 17:54:04 +0530 Subject: mm: rename GENERIC_PTDUMP and PTDUMP_CORE Platforms subscribe into generic ptdump implementation via GENERIC_PTDUMP. But generic ptdump gets enabled via PTDUMP_CORE. These configs combination is confusing as they sound very similar and does not differentiate between platform's feature subscription and feature enablement for ptdump. Rename the configs as ARCH_HAS_PTDUMP and PTDUMP making it more clear and improve readability. Link: https://lkml.kernel.org/r/20250226122404.1927473-6-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Christophe Leroy (powerpc) Acked-by: Catalin Marinas [arm64] Cc: Will Deacon Cc: Jonathan Corbet Cc: Marc Zyngier Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Christophe Leroy Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Steven Price Signed-off-by: Andrew Morton --- arch/arm64/Kconfig | 2 +- arch/arm64/include/asm/ptdump.h | 4 ++-- arch/arm64/kvm/Kconfig | 4 ++-- arch/arm64/mm/Makefile | 2 +- arch/powerpc/Kconfig | 2 +- arch/powerpc/mm/Makefile | 2 +- arch/riscv/Kconfig | 2 +- arch/riscv/mm/Makefile | 2 +- arch/s390/Kconfig | 2 +- arch/s390/mm/Makefile | 2 +- arch/x86/Kconfig | 2 +- arch/x86/Kconfig.debug | 2 +- arch/x86/mm/Makefile | 2 +- 13 files changed, 15 insertions(+), 15 deletions(-) (limited to 'arch') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 940343beb3d4..5cf688ee01b7 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -41,6 +41,7 @@ config ARM64 select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT + select ARCH_HAS_PTDUMP select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_HW_PTE_YOUNG @@ -157,7 +158,6 @@ config ARM64 select GENERIC_IRQ_SHOW_LEVEL select GENERIC_LIB_DEVMEM_IS_ALLOWED select GENERIC_PCI_IOMAP - select GENERIC_PTDUMP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h index 6cf4aae05219..b2931d1ae0fb 100644 --- a/arch/arm64/include/asm/ptdump.h +++ b/arch/arm64/include/asm/ptdump.h @@ -7,7 +7,7 @@ #include -#ifdef CONFIG_PTDUMP_CORE +#ifdef CONFIG_PTDUMP #include #include @@ -70,6 +70,6 @@ static inline void ptdump_debugfs_register(struct ptdump_info *info, #else static inline void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val) { } -#endif /* CONFIG_PTDUMP_CORE */ +#endif /* CONFIG_PTDUMP */ #endif /* __ASM_PTDUMP_H */ diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index ead632ad01b4..096e45acadb2 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -71,8 +71,8 @@ config PTDUMP_STAGE2_DEBUGFS depends on KVM depends on DEBUG_KERNEL depends on DEBUG_FS - depends on GENERIC_PTDUMP - select PTDUMP_CORE + depends on ARCH_HAS_PTDUMP + select PTDUMP default n help Say Y here if you want to show the stage-2 kernel pagetables diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile index fc92170a8f37..c26489cf96cd 100644 --- a/arch/arm64/mm/Makefile +++ b/arch/arm64/mm/Makefile @@ -5,7 +5,7 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ context.o proc.o pageattr.o fixmap.o obj-$(CONFIG_ARM64_CONTPTE) += contpte.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_PTDUMP_CORE) += ptdump.o +obj-$(CONFIG_PTDUMP) += ptdump.o obj-$(CONFIG_PTDUMP_DEBUGFS) += ptdump_debugfs.o obj-$(CONFIG_TRANS_TABLE) += trans_pgd.o obj-$(CONFIG_TRANS_TABLE) += trans_pgd-asm.o diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 424f188e62d9..6f1ae41dcf85 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -148,6 +148,7 @@ config PPC select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API select ARCH_HAS_PREEMPT_LAZY + select ARCH_HAS_PTDUMP select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 @@ -206,7 +207,6 @@ config PPC select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_PCI_IOMAP if PCI - select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select GENERIC_VDSO_TIME_NS diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 0fe2f085c05a..8c1582b2987d 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -15,5 +15,5 @@ obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o obj-$(CONFIG_PPC_COPRO_BASE) += copro_fault.o -obj-$(CONFIG_PTDUMP_CORE) += ptdump/ +obj-$(CONFIG_PTDUMP) += ptdump/ obj-$(CONFIG_KASAN) += kasan/ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7612c52e9b1e..353cf41d01f4 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -43,6 +43,7 @@ config RISCV select ARCH_HAS_PMEM_API select ARCH_HAS_PREEMPT_LAZY select ARCH_HAS_PREPARE_SYNC_CORE_CMD + select ARCH_HAS_PTDUMP if MMU select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_DIRECT_MAP if MMU @@ -112,7 +113,6 @@ config RISCV select GENERIC_IRQ_SHOW_LEVEL select GENERIC_LIB_DEVMEM_IS_ALLOWED select GENERIC_PCI_IOMAP - select GENERIC_PTDUMP if MMU select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index cbe4d775ef56..b916a68d324a 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -19,7 +19,7 @@ obj-y += context.o obj-y += pmem.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_PTDUMP_CORE) += ptdump.o +obj-$(CONFIG_PTDUMP) += ptdump.o obj-$(CONFIG_KASAN) += kasan_init.o ifdef CONFIG_KASAN diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9c9ec08d78c7..dd9dd2f8e673 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -96,6 +96,7 @@ config S390 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_PREEMPT_LAZY + select ARCH_HAS_PTDUMP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SCALED_CPUTIME select ARCH_HAS_SET_DIRECT_MAP @@ -163,7 +164,6 @@ config S390 select GENERIC_CPU_VULNERABILITIES select GENERIC_ENTRY select GENERIC_GETTIMEOFDAY - select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select GENERIC_VDSO_TIME_NS diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index f6c2db7a8669..9726b91fe7e4 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -9,6 +9,6 @@ obj-y += page-states.o pageattr.o pgtable.o pgalloc.o extable.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_PTDUMP) += dump_pagetables.o obj-$(CONFIG_PGSTE) += gmap.o obj-$(CONFIG_PFAULT) += pfault.o diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cf49c130d1d0..bfd23a09b911 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,6 +26,7 @@ config X86_64 depends on 64BIT # Options that are inherently 64-bit kernel only: select ARCH_HAS_GIGANTIC_PAGE + select ARCH_HAS_PTDUMP select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_SUPPORTS_PER_VMA_LOCK select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE @@ -175,7 +176,6 @@ config X86 select GENERIC_IRQ_RESERVATION_MODE select GENERIC_IRQ_SHOW select GENERIC_PENDING_IRQ if SMP - select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 1eb4d23cdaae..c95c3aaadf97 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -59,7 +59,7 @@ config EARLY_PRINTK_USB_XDBC config EFI_PGT_DUMP bool "Dump the EFI pagetable" depends on EFI - select PTDUMP_CORE + select PTDUMP help Enable this if you want to dump the EFI page table before enabling virtual mode. This can be used to debug miscellaneous diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 690fbf48e853..e0c99a8760ca 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -39,7 +39,7 @@ CFLAGS_fault.o := -I $(src)/../include/asm/trace obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_PTDUMP) += dump_pagetables.o obj-$(CONFIG_PTDUMP_DEBUGFS) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o -- cgit v1.2.3 From a1d416bf9faf4f4871cb5a943614a07f80a7d70f Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Mon, 3 Mar 2025 14:15:37 +0000 Subject: sparc/mm: disable preemption in lazy mmu mode Since commit 38e0edb15bd0 ("mm/apply_to_range: call pte function with lazy updates") it's been possible for arch_[enter|leave]_lazy_mmu_mode() to be called without holding a page table lock (for the kernel mappings case), and therefore it is possible that preemption may occur while in the lazy mmu mode. The Sparc lazy mmu implementation is not robust to preemption since it stores the lazy mode state in a per-cpu structure and does not attempt to manage that state on task switch. Powerpc had the same issue and fixed it by explicitly disabling preemption in arch_enter_lazy_mmu_mode() and re-enabling in arch_leave_lazy_mmu_mode(). See commit b9ef323ea168 ("powerpc/64s: Disable preemption in hash lazy mmu mode"). Given Sparc's lazy mmu mode is based on powerpc's, let's fix it in the same way here. Link: https://lkml.kernel.org/r/20250303141542.3371656-4-ryan.roberts@arm.com Fixes: 38e0edb15bd0 ("mm/apply_to_range: call pte function with lazy updates") Signed-off-by: Ryan Roberts Acked-by: David Hildenbrand Acked-by: Andreas Larsson Acked-by: Juergen Gross Cc: Borislav Betkov Cc: Boris Ostrovsky Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Juegren Gross Cc: Matthew Wilcow (Oracle) Cc: Thomas Gleinxer Cc: Signed-off-by: Andrew Morton --- arch/sparc/mm/tlb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 8648a50afe88..a35ddcca5e76 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -52,8 +52,10 @@ out: void arch_enter_lazy_mmu_mode(void) { - struct tlb_batch *tb = this_cpu_ptr(&tlb_batch); + struct tlb_batch *tb; + preempt_disable(); + tb = this_cpu_ptr(&tlb_batch); tb->active = 1; } @@ -64,6 +66,7 @@ void arch_leave_lazy_mmu_mode(void) if (tb->tlb_nr) flush_tlb_pending(); tb->active = 0; + preempt_enable(); } static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, -- cgit v1.2.3 From eb61ad14c459b54f71f76331ca35d12fa3eb8f98 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Mon, 3 Mar 2025 14:15:38 +0000 Subject: sparc/mm: avoid calling arch_enter/leave_lazy_mmu() in set_ptes With commit 1a10a44dfc1d ("sparc64: implement the new page table range API") set_ptes was added to the sparc architecture. The implementation included calling arch_enter/leave_lazy_mmu() calls. The patch removes the usage of arch_enter/leave_lazy_mmu() since this implies nesting of lazy mmu regions which is not supported. Without this fix, lazy mmu mode is effectively disabled because we exit the mode after the first set_ptes: remap_pte_range() -> arch_enter_lazy_mmu() -> set_ptes() -> arch_enter_lazy_mmu() -> arch_leave_lazy_mmu() -> arch_leave_lazy_mmu() Powerpc suffered the same problem and fixed it in a corresponding way with commit 47b8def9358c ("powerpc/mm: Avoid calling arch_enter/leave_lazy_mmu() in set_ptes"). Link: https://lkml.kernel.org/r/20250303141542.3371656-5-ryan.roberts@arm.com Fixes: 1a10a44dfc1d ("sparc64: implement the new page table range API") Signed-off-by: Ryan Roberts Acked-by: David Hildenbrand Acked-by: Andreas Larsson Acked-by: Juergen Gross Cc: Borislav Betkov Cc: Boris Ostrovsky Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Juegren Gross Cc: Matthew Wilcow (Oracle) Cc: Thomas Gleinxer Cc: Signed-off-by: Andrew Morton --- arch/sparc/include/asm/pgtable_64.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch') diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 2b7f358762c1..dc28f2c4eee3 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -936,7 +936,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, static inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { - arch_enter_lazy_mmu_mode(); for (;;) { __set_pte_at(mm, addr, ptep, pte, 0); if (--nr == 0) @@ -945,7 +944,6 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_val(pte) += PAGE_SIZE; addr += PAGE_SIZE; } - arch_leave_lazy_mmu_mode(); } #define set_ptes set_ptes -- cgit v1.2.3 From c36549ff8d8423fbf1a0c5bbd72be4f902d74700 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Mon, 3 Mar 2025 14:15:39 +0000 Subject: Revert "x86/xen: allow nesting of same lazy mode" Commit 49147beb0ccb ("x86/xen: allow nesting of same lazy mode") was added as a solution for a core-mm code change where arch_[enter|leave]_lazy_mmu_mode() started to be called in a nested manner; see commit bcc6cc832573 ("mm: add default definition of set_ptes()"). However, now that we have fixed the API to avoid nesting, we no longer need this capability in the x86 implementation. Additionally, from code review, I don't believe the fix was ever robust in the case of preemption occurring while in the nested lazy mode. The implementation usually deals with preemption by calling arch_leave_lazy_mmu_mode() from xen_start_context_switch() for the outgoing task if we are in the lazy mmu mode. Then in xen_end_context_switch(), it restarts the lazy mode by calling arch_enter_lazy_mmu_mode() for an incoming task that was in the lazy mode when it was switched out. But arch_leave_lazy_mmu_mode() will only unwind a single level of nesting. If we are in the double nest, then it's not fully unwound and per-cpu variables are left in a bad state. So the correct solution is to remove the possibility of nesting from the higher level (which has now been done) and remove this x86-specific solution. Link: https://lkml.kernel.org/r/20250303141542.3371656-6-ryan.roberts@arm.com Signed-off-by: Ryan Roberts Acked-by: David Hildenbrand Acked-by: Juergen Gross Cc: Andreas Larsson Cc: Borislav Betkov Cc: Boris Ostrovsky Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Juegren Gross Cc: Matthew Wilcow (Oracle) Cc: Thomas Gleinxer Signed-off-by: Andrew Morton --- arch/x86/include/asm/xen/hypervisor.h | 15 ++------------- arch/x86/xen/enlighten_pv.c | 1 - 2 files changed, 2 insertions(+), 14 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index a9088250770f..bd0fc69a10a7 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -72,18 +72,10 @@ enum xen_lazy_mode { }; DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode); -DECLARE_PER_CPU(unsigned int, xen_lazy_nesting); static inline void enter_lazy(enum xen_lazy_mode mode) { - enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode); - - if (mode == old_mode) { - this_cpu_inc(xen_lazy_nesting); - return; - } - - BUG_ON(old_mode != XEN_LAZY_NONE); + BUG_ON(this_cpu_read(xen_lazy_mode) != XEN_LAZY_NONE); this_cpu_write(xen_lazy_mode, mode); } @@ -92,10 +84,7 @@ static inline void leave_lazy(enum xen_lazy_mode mode) { BUG_ON(this_cpu_read(xen_lazy_mode) != mode); - if (this_cpu_read(xen_lazy_nesting) == 0) - this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE); - else - this_cpu_dec(xen_lazy_nesting); + this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE); } enum xen_lazy_mode xen_get_lazy_mode(void); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5e57835e999d..919e4df9380b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -99,7 +99,6 @@ struct tls_descs { }; DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE; -DEFINE_PER_CPU(unsigned int, xen_lazy_nesting); enum xen_lazy_mode xen_get_lazy_mode(void) { -- cgit v1.2.3 From e11079dd25c525aaf238d81287851ef16a521ef3 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:51 +0200 Subject: arm: mem_init: use memblock_phys_free() to free DMA memory on SA1111 Patch series "arch, mm: reduce code duplication in mem_init()", v2. Every architecture has implementation of mem_init() function and some even more than one. All these release free memory to the buddy allocator, most of them set high_memory to the end of directly addressable memory and many of them set max_mapnr for FLATMEM case. These patches pull the commonalities into the generic code and refactor some of the mem_init() implementations so that many of them can be just dropped. This patch (of 13): This will help to pull out memblock_free_all() to generic code. Link: https://lkml.kernel.org/r/20250313135003.836600-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20250313135003.836600-2-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Tested-by: Mark Brown Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: "Mike Rapoport (IBM)" Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm/mm/init.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 5345d218899a..9aec1cb2386f 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -277,14 +277,14 @@ void __init mem_init(void) set_max_mapnr(pfn_to_page(max_pfn) - mem_map); - /* this will put all unused low memory onto the freelists */ - memblock_free_all(); - #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ - free_reserved_area(__va(PHYS_OFFSET), swapper_pg_dir, -1, NULL); + memblock_phys_free(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET); #endif + /* this will put all unused low memory onto the freelists */ + memblock_free_all(); + free_highpages(); /* -- cgit v1.2.3 From 2b1d532e106ee63acb61a8e11608fafd75e52c4d Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:52 +0200 Subject: csky: move setup_initrd() to setup.c Memory used by initrd should be reserved as soon as possible before there any memblock allocations that might overwrite that memory. This will also help with pulling out memblock_free_all() to the generic code and reducing code duplication in arch::mem_init(). Link: https://lkml.kernel.org/r/20250313135003.836600-3-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Guo Ren (csky) Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Mark Brown Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/csky/kernel/setup.c | 43 +++++++++++++++++++++++++++++++++++++++++++ arch/csky/mm/init.c | 43 ------------------------------------------- 2 files changed, 43 insertions(+), 43 deletions(-) (limited to 'arch') diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c index fe715b707fd0..e0d6ca86ea8c 100644 --- a/arch/csky/kernel/setup.c +++ b/arch/csky/kernel/setup.c @@ -12,6 +12,45 @@ #include #include +#ifdef CONFIG_BLK_DEV_INITRD +static void __init setup_initrd(void) +{ + unsigned long size; + + if (initrd_start >= initrd_end) { + pr_err("initrd not found or empty"); + goto disable; + } + + if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) { + pr_err("initrd extends beyond end of memory"); + goto disable; + } + + size = initrd_end - initrd_start; + + if (memblock_is_region_reserved(__pa(initrd_start), size)) { + pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region", + __pa(initrd_start), size); + goto disable; + } + + memblock_reserve(__pa(initrd_start), size); + + pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", + (void *)(initrd_start), size); + + initrd_below_start_ok = 1; + + return; + +disable: + initrd_start = initrd_end = 0; + + pr_err(" - disabling initrd\n"); +} +#endif + static void __init csky_memblock_init(void) { unsigned long lowmem_size = PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET); @@ -40,6 +79,10 @@ static void __init csky_memblock_init(void) max_low_pfn = min_low_pfn + sseg_size; } +#ifdef CONFIG_BLK_DEV_INITRD + setup_initrd(); +#endif + max_zone_pfn[ZONE_NORMAL] = max_low_pfn; mmu_init(min_low_pfn, max_low_pfn); diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index bde7cabd23df..ab51acbc19b2 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -42,45 +42,6 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); -#ifdef CONFIG_BLK_DEV_INITRD -static void __init setup_initrd(void) -{ - unsigned long size; - - if (initrd_start >= initrd_end) { - pr_err("initrd not found or empty"); - goto disable; - } - - if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) { - pr_err("initrd extends beyond end of memory"); - goto disable; - } - - size = initrd_end - initrd_start; - - if (memblock_is_region_reserved(__pa(initrd_start), size)) { - pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region", - __pa(initrd_start), size); - goto disable; - } - - memblock_reserve(__pa(initrd_start), size); - - pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", - (void *)(initrd_start), size); - - initrd_below_start_ok = 1; - - return; - -disable: - initrd_start = initrd_end = 0; - - pr_err(" - disabling initrd\n"); -} -#endif - void __init mem_init(void) { #ifdef CONFIG_HIGHMEM @@ -92,10 +53,6 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); -#ifdef CONFIG_BLK_DEV_INITRD - setup_initrd(); -#endif - memblock_free_all(); #ifdef CONFIG_HIGHMEM -- cgit v1.2.3 From 30686816214b6062246e4918f3eadd1f55382425 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:53 +0200 Subject: hexagon: move initialization of init_mm.context init to paging_init() This will help with pulling out memblock_free_all() to the generic code and reducing code duplication in arch::mem_init(). Link: https://lkml.kernel.org/r/20250313135003.836600-4-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Mark Brown Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/hexagon/mm/init.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index 3458f39ca2ac..508bb6a8dcc9 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -59,14 +59,6 @@ void __init mem_init(void) * To-Do: someone somewhere should wipe out the bootmem map * after we're done? */ - - /* - * This can be moved to some more virtual-memory-specific - * initialization hook at some point. Set the init_mm - * descriptors "context" value to point to the initial - * kernel segment table's physical address. - */ - init_mm.context.ptbase = __pa(init_mm.pgd); } void sync_icache_dcache(pte_t pte) @@ -103,6 +95,12 @@ static void __init paging_init(void) free_area_init(max_zone_pfn); /* sets up the zonelists and mem_map */ + /* + * Set the init_mm descriptors "context" value to point to the + * initial kernel segment table's physical address. + */ + init_mm.context.ptbase = __pa(init_mm.pgd); + /* * Start of high memory area. Will probably need something more * fancy if we... get more fancy. -- cgit v1.2.3 From 67e7a600869ca557e259f1ce20f8b89bb95ca97d Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:54 +0200 Subject: MIPS: consolidate mem_init() for NUMA machines Both MIPS systems that support numa (loongsoon3 and sgi-ip27) have identical mem_init() for NUMA case. Move that into arch/mips/mm/init.c and drop duplicate per-machine definitions. Link: https://lkml.kernel.org/r/20250313135003.836600-5-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Mark Brown Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/mips/loongson64/numa.c | 7 ------- arch/mips/mm/init.c | 7 +++++++ arch/mips/sgi-ip27/ip27-memory.c | 9 --------- 3 files changed, 7 insertions(+), 16 deletions(-) (limited to 'arch') diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c index 8388400d052f..95d5f553ce19 100644 --- a/arch/mips/loongson64/numa.c +++ b/arch/mips/loongson64/numa.c @@ -164,13 +164,6 @@ void __init paging_init(void) free_area_init(zones_size); } -void __init mem_init(void) -{ - high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); - memblock_free_all(); - setup_zero_pages(); /* This comes from node 0 */ -} - /* All PCI device belongs to logical Node-0 */ int pcibus_to_node(struct pci_bus *bus) { diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 4583d1a2a73e..3db6082c611e 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -482,6 +482,13 @@ void __init mem_init(void) 0x80000000 - 4, KCORE_TEXT); #endif } +#else /* CONFIG_NUMA */ +void __init mem_init(void) +{ + high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); + memblock_free_all(); + setup_zero_pages(); /* This comes from node 0 */ +} #endif /* !CONFIG_NUMA */ void free_init_pages(const char *what, unsigned long begin, unsigned long end) diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 1963313f55d8..2b3e46e2e607 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -406,8 +406,6 @@ void __init prom_meminit(void) } } -extern void setup_zero_pages(void); - void __init paging_init(void) { unsigned long zones_size[MAX_NR_ZONES] = {0, }; @@ -416,10 +414,3 @@ void __init paging_init(void) zones_size[ZONE_NORMAL] = max_low_pfn; free_area_init(zones_size); } - -void __init mem_init(void) -{ - high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); - memblock_free_all(); - setup_zero_pages(); /* This comes from node 0 */ -} -- cgit v1.2.3 From e74e2b8eb424c26dff35727d242437edb87684aa Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:55 +0200 Subject: MIPS: make setup_zero_pages() use memblock Allocating the zero pages from memblock is simpler because the memory is already reserved. This will also help with pulling out memblock_free_all() to the generic code and reducing code duplication in arch::mem_init(). Link: https://lkml.kernel.org/r/20250313135003.836600-6-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Mark Brown Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/mips/include/asm/mmzone.h | 2 -- arch/mips/mm/init.c | 18 +++++------------- 2 files changed, 5 insertions(+), 15 deletions(-) (limited to 'arch') diff --git a/arch/mips/include/asm/mmzone.h b/arch/mips/include/asm/mmzone.h index 14226ea42036..602a21aee9d4 100644 --- a/arch/mips/include/asm/mmzone.h +++ b/arch/mips/include/asm/mmzone.h @@ -20,6 +20,4 @@ #define nid_to_addrbase(nid) 0 #endif -extern void setup_zero_pages(void); - #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 3db6082c611e..820e35a59d4d 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -59,24 +59,16 @@ EXPORT_SYMBOL(zero_page_mask); /* * Not static inline because used by IP27 special magic initialization code */ -void setup_zero_pages(void) +static void __init setup_zero_pages(void) { - unsigned int order, i; - struct page *page; + unsigned int order; if (cpu_has_vce) order = 3; else order = 0; - empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); - if (!empty_zero_page) - panic("Oh boy, that early out of memory?"); - - page = virt_to_page((void *)empty_zero_page); - split_page(page, order); - for (i = 0; i < (1 << order); i++, page++) - mark_page_reserved(page); + empty_zero_page = (unsigned long)memblock_alloc_or_panic(PAGE_SIZE << order, PAGE_SIZE); zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK; } @@ -470,9 +462,9 @@ void __init mem_init(void) BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (PFN_PTE_SHIFT > PAGE_SHIFT)); maar_init(); - memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ mem_init_free_highmem(); + memblock_free_all(); #ifdef CONFIG_64BIT if ((unsigned long) &_text > (unsigned long) CKSEG0) @@ -486,8 +478,8 @@ void __init mem_init(void) void __init mem_init(void) { high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); - memblock_free_all(); setup_zero_pages(); /* This comes from node 0 */ + memblock_free_all(); } #endif /* !CONFIG_NUMA */ -- cgit v1.2.3 From be971f957a80e2bbd7747a295886df1472803ff1 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:56 +0200 Subject: nios2: move pr_debug() about memory start and end to setup_arch() This will help with pulling out memblock_free_all() to the generic code and reducing code duplication in arch::mem_init(). Link: https://lkml.kernel.org/r/20250313135003.836600-7-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Mark Brown Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/nios2/kernel/setup.c | 2 ++ arch/nios2/mm/init.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index da122a5fa43b..a4cffbfc1399 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -149,6 +149,8 @@ void __init setup_arch(char **cmdline_p) memory_start = memblock_start_of_DRAM(); memory_end = memblock_end_of_DRAM(); + pr_debug("%s: start=%lx, end=%lx\n", __func__, memory_start, memory_end); + setup_initial_init_mm(_stext, _etext, _edata, _end); init_task.thread.kregs = &fake_regs; diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index a2278485de19..aa692ad30044 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -65,8 +65,6 @@ void __init mem_init(void) unsigned long end_mem = memory_end; /* this must not include kernel stack at top */ - pr_debug("mem_init: start=%lx, end=%lx\n", memory_start, memory_end); - end_mem &= PAGE_MASK; high_memory = __va(end_mem); -- cgit v1.2.3 From 54ccf66f99d6d2630895eb13156be19a033d4566 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:57 +0200 Subject: s390: make setup_zero_pages() use memblock Allocating the zero pages from memblock is simpler because the memory is already reserved. This will also help with pulling out memblock_free_all() to the generic code and reducing code duplication in arch::mem_init(). Link: https://lkml.kernel.org/r/20250313135003.836600-8-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Heiko Carstens Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Mark Brown Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/s390/mm/init.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index d88cb1c13f7d..2b41dc9b1fa3 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -73,8 +73,6 @@ static void __init setup_zero_pages(void) { unsigned long total_pages = memblock_estimated_nr_free_pages(); unsigned int order; - struct page *page; - int i; /* Latest machines require a mapping granularity of 512KB */ order = 7; @@ -83,16 +81,7 @@ static void __init setup_zero_pages(void) while (order > 2 && (total_pages >> 10) < (1UL << order)) order--; - empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); - if (!empty_zero_page) - panic("Out of memory in setup_zero_pages"); - - page = virt_to_page((void *) empty_zero_page); - split_page(page, order); - for (i = 1 << order; i > 0; i--) { - mark_page_reserved(page); - page++; - } + empty_zero_page = (unsigned long)memblock_alloc_or_panic(PAGE_SIZE << order, PAGE_SIZE); zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK; } @@ -176,9 +165,10 @@ void __init mem_init(void) pv_init(); kfence_split_mapping(); + setup_zero_pages(); /* Setup zeroed pages. */ + /* this will put all low memory onto the freelists */ memblock_free_all(); - setup_zero_pages(); /* Setup zeroed pages. */ } unsigned long memory_block_size_bytes(void) -- cgit v1.2.3 From d319c8b4918d24aea6fd90bd39cd5bc9fcf40859 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:58 +0200 Subject: xtensa: split out printing of virtual memory layout to a function This will help with pulling out memblock_free_all() to the generic code and reducing code duplication in arch::mem_init(). Link: https://lkml.kernel.org/r/20250313135003.836600-9-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Reviewed-by: Max Filippov Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Mark Brown Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/xtensa/mm/init.c | 97 ++++++++++++++++++++++++++------------------------- 1 file changed, 50 insertions(+), 47 deletions(-) (limited to 'arch') diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index b2587a1a7c46..01577d33e602 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -66,6 +66,55 @@ void __init bootmem_init(void) memblock_dump_all(); } +static void __init print_vm_layout(void) +{ + pr_info("virtual kernel memory layout:\n" +#ifdef CONFIG_KASAN + " kasan : 0x%08lx - 0x%08lx (%5lu MB)\n" +#endif +#ifdef CONFIG_MMU + " vmalloc : 0x%08lx - 0x%08lx (%5lu MB)\n" +#endif +#ifdef CONFIG_HIGHMEM + " pkmap : 0x%08lx - 0x%08lx (%5lu kB)\n" + " fixmap : 0x%08lx - 0x%08lx (%5lu kB)\n" +#endif + " lowmem : 0x%08lx - 0x%08lx (%5lu MB)\n" + " .text : 0x%08lx - 0x%08lx (%5lu kB)\n" + " .rodata : 0x%08lx - 0x%08lx (%5lu kB)\n" + " .data : 0x%08lx - 0x%08lx (%5lu kB)\n" + " .init : 0x%08lx - 0x%08lx (%5lu kB)\n" + " .bss : 0x%08lx - 0x%08lx (%5lu kB)\n", +#ifdef CONFIG_KASAN + KASAN_SHADOW_START, KASAN_SHADOW_START + KASAN_SHADOW_SIZE, + KASAN_SHADOW_SIZE >> 20, +#endif +#ifdef CONFIG_MMU + VMALLOC_START, VMALLOC_END, + (VMALLOC_END - VMALLOC_START) >> 20, +#ifdef CONFIG_HIGHMEM + PKMAP_BASE, PKMAP_BASE + LAST_PKMAP * PAGE_SIZE, + (LAST_PKMAP*PAGE_SIZE) >> 10, + FIXADDR_START, FIXADDR_END, + (FIXADDR_END - FIXADDR_START) >> 10, +#endif + PAGE_OFFSET, PAGE_OFFSET + + (max_low_pfn - min_low_pfn) * PAGE_SIZE, +#else + min_low_pfn * PAGE_SIZE, max_low_pfn * PAGE_SIZE, +#endif + ((max_low_pfn - min_low_pfn) * PAGE_SIZE) >> 20, + (unsigned long)_text, (unsigned long)_etext, + (unsigned long)(_etext - _text) >> 10, + (unsigned long)__start_rodata, (unsigned long)__end_rodata, + (unsigned long)(__end_rodata - __start_rodata) >> 10, + (unsigned long)_sdata, (unsigned long)_edata, + (unsigned long)(_edata - _sdata) >> 10, + (unsigned long)__init_begin, (unsigned long)__init_end, + (unsigned long)(__init_end - __init_begin) >> 10, + (unsigned long)__bss_start, (unsigned long)__bss_stop, + (unsigned long)(__bss_stop - __bss_start) >> 10); +} void __init zones_init(void) { @@ -77,6 +126,7 @@ void __init zones_init(void) #endif }; free_area_init(max_zone_pfn); + print_vm_layout(); } static void __init free_highpages(void) @@ -118,53 +168,6 @@ void __init mem_init(void) high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); - - pr_info("virtual kernel memory layout:\n" -#ifdef CONFIG_KASAN - " kasan : 0x%08lx - 0x%08lx (%5lu MB)\n" -#endif -#ifdef CONFIG_MMU - " vmalloc : 0x%08lx - 0x%08lx (%5lu MB)\n" -#endif -#ifdef CONFIG_HIGHMEM - " pkmap : 0x%08lx - 0x%08lx (%5lu kB)\n" - " fixmap : 0x%08lx - 0x%08lx (%5lu kB)\n" -#endif - " lowmem : 0x%08lx - 0x%08lx (%5lu MB)\n" - " .text : 0x%08lx - 0x%08lx (%5lu kB)\n" - " .rodata : 0x%08lx - 0x%08lx (%5lu kB)\n" - " .data : 0x%08lx - 0x%08lx (%5lu kB)\n" - " .init : 0x%08lx - 0x%08lx (%5lu kB)\n" - " .bss : 0x%08lx - 0x%08lx (%5lu kB)\n", -#ifdef CONFIG_KASAN - KASAN_SHADOW_START, KASAN_SHADOW_START + KASAN_SHADOW_SIZE, - KASAN_SHADOW_SIZE >> 20, -#endif -#ifdef CONFIG_MMU - VMALLOC_START, VMALLOC_END, - (VMALLOC_END - VMALLOC_START) >> 20, -#ifdef CONFIG_HIGHMEM - PKMAP_BASE, PKMAP_BASE + LAST_PKMAP * PAGE_SIZE, - (LAST_PKMAP*PAGE_SIZE) >> 10, - FIXADDR_START, FIXADDR_END, - (FIXADDR_END - FIXADDR_START) >> 10, -#endif - PAGE_OFFSET, PAGE_OFFSET + - (max_low_pfn - min_low_pfn) * PAGE_SIZE, -#else - min_low_pfn * PAGE_SIZE, max_low_pfn * PAGE_SIZE, -#endif - ((max_low_pfn - min_low_pfn) * PAGE_SIZE) >> 20, - (unsigned long)_text, (unsigned long)_etext, - (unsigned long)(_etext - _text) >> 10, - (unsigned long)__start_rodata, (unsigned long)__end_rodata, - (unsigned long)(__end_rodata - __start_rodata) >> 10, - (unsigned long)_sdata, (unsigned long)_edata, - (unsigned long)(_edata - _sdata) >> 10, - (unsigned long)__init_begin, (unsigned long)__init_end, - (unsigned long)(__init_end - __init_begin) >> 10, - (unsigned long)__bss_start, (unsigned long)__bss_stop, - (unsigned long)(__bss_stop - __bss_start) >> 10); } static void __init parse_memmap_one(char *p) -- cgit v1.2.3 From 8268af309d07d1c6279080b4e6fd16ec75cc977c Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:49:59 +0200 Subject: arch, mm: set max_mapnr when allocating memory map for FLATMEM max_mapnr is essentially the size of the memory map for systems that use FLATMEM. There is no reason to calculate it in each and every architecture when it's anyway calculated in alloc_node_mem_map(). Drop setting of max_mapnr from architecture code and set it once in alloc_node_mem_map(). While on it, move definition of mem_map and max_mapnr to mm/mm_init.c so there won't be two copies for MMU and !MMU variants. Link: https://lkml.kernel.org/r/20250313135003.836600-10-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Dave Hansen [x86] Tested-by: Mark Brown Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/alpha/mm/init.c | 1 - arch/arc/mm/init.c | 5 ----- arch/arm/mm/init.c | 2 -- arch/csky/mm/init.c | 4 ---- arch/loongarch/mm/init.c | 1 - arch/microblaze/mm/init.c | 4 ---- arch/mips/mm/init.c | 8 -------- arch/nios2/kernel/setup.c | 1 - arch/nios2/mm/init.c | 2 +- arch/openrisc/mm/init.c | 1 - arch/parisc/mm/init.c | 1 - arch/powerpc/kernel/setup-common.c | 2 -- arch/riscv/mm/init.c | 1 - arch/s390/mm/init.c | 1 - arch/sh/mm/init.c | 1 - arch/sparc/mm/init_32.c | 1 - arch/um/include/shared/mem_user.h | 1 - arch/um/kernel/physmem.c | 12 ------------ arch/um/kernel/um_arch.c | 1 - arch/x86/mm/init_32.c | 3 --- arch/xtensa/mm/init.c | 1 - 21 files changed, 1 insertion(+), 53 deletions(-) (limited to 'arch') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 61c2198b1359..ec0eeae9c653 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -276,7 +276,6 @@ srm_paging_stop (void) void __init mem_init(void) { - set_max_mapnr(max_low_pfn); high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); memblock_free_all(); } diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 6a71b23f1383..7ef883d58dc1 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -154,11 +154,6 @@ void __init setup_arch_memory(void) arch_pfn_offset = min(min_low_pfn, min_high_pfn); kmap_init(); - -#else /* CONFIG_HIGHMEM */ - /* pfn_valid() uses this when FLATMEM=y and HIGHMEM=n */ - max_mapnr = max_low_pfn - min_low_pfn; - #endif /* CONFIG_HIGHMEM */ free_area_init(max_zone_pfn); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 9aec1cb2386f..d4bcc745a044 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -275,8 +275,6 @@ void __init mem_init(void) swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE); #endif - set_max_mapnr(pfn_to_page(max_pfn) - mem_map); - #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ memblock_phys_free(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET); diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index ab51acbc19b2..ba6694d6170a 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -46,10 +46,6 @@ void __init mem_init(void) { #ifdef CONFIG_HIGHMEM unsigned long tmp; - - set_max_mapnr(highend_pfn - ARCH_PFN_OFFSET); -#else - set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index ca5aa5f46a9f..00449df50db1 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -78,7 +78,6 @@ void __init paging_init(void) void __init mem_init(void) { - max_mapnr = max_low_pfn; high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 4520c5741579..857cd2b44bcf 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -104,17 +104,13 @@ void __init setup_memory(void) * * min_low_pfn - the first page (mm/bootmem.c - node_boot_start) * max_low_pfn - * max_mapnr - the first unused page (mm/bootmem.c - node_low_pfn) */ /* memory start is from the kernel end (aligned) to higher addr */ min_low_pfn = memory_start >> PAGE_SHIFT; /* minimum for allocation */ - /* RAM is assumed contiguous */ - max_mapnr = memory_size >> PAGE_SHIFT; max_low_pfn = ((u64)memory_start + (u64)lowmem_size) >> PAGE_SHIFT; max_pfn = ((u64)memory_start + (u64)memory_size) >> PAGE_SHIFT; - pr_info("%s: max_mapnr: %#lx\n", __func__, max_mapnr); pr_info("%s: min_low_pfn: %#lx\n", __func__, min_low_pfn); pr_info("%s: max_low_pfn: %#lx\n", __func__, max_low_pfn); pr_info("%s: max_pfn: %#lx\n", __func__, max_pfn); diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 820e35a59d4d..eb61a73520a0 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -415,15 +415,7 @@ void __init paging_init(void) " %ldk highmem ignored\n", (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10)); max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn; - - max_mapnr = max_low_pfn; - } else if (highend_pfn) { - max_mapnr = highend_pfn; - } else { - max_mapnr = max_low_pfn; } -#else - max_mapnr = max_low_pfn; #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index a4cffbfc1399..2a40150142c3 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -158,7 +158,6 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; find_limits(&min_low_pfn, &max_low_pfn, &max_pfn); - max_mapnr = max_low_pfn; memblock_reserve(__pa_symbol(_stext), _end - _stext); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index aa692ad30044..3cafa87ead9e 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -51,7 +51,7 @@ void __init paging_init(void) pagetable_init(); pgd_current = swapper_pg_dir; - max_zone_pfn[ZONE_NORMAL] = max_mapnr; + max_zone_pfn[ZONE_NORMAL] = max_low_pfn; /* pass the memory from the bootmem allocator to the main allocator */ free_area_init(max_zone_pfn); diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index d0cb1a0126f9..9093c336e158 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -193,7 +193,6 @@ void __init mem_init(void) { BUG_ON(!mem_map); - max_mapnr = max_low_pfn; high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); /* clear the zero-page */ diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 61c0a2477072..2cdfc0b1195c 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -563,7 +563,6 @@ void __init mem_init(void) #endif high_memory = __va((max_pfn << PAGE_SHIFT)); - set_max_mapnr(max_low_pfn); memblock_free_all(); #ifdef CONFIG_PA11 diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index a08b0ede4e64..68d47c53876c 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -957,8 +957,6 @@ void __init setup_arch(char **cmdline_p) /* Parse memory topology */ mem_topology_setup(); - /* Set max_mapnr before paging_init() */ - set_max_mapnr(max_pfn); high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); /* diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 15b2eda4c364..157c9ca51541 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -298,7 +298,6 @@ static void __init setup_bootmem(void) high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); - set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); reserve_initrd_mem(); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 2b41dc9b1fa3..ad567e2100b7 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -159,7 +159,6 @@ void __init mem_init(void) cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask); cpumask_set_cpu(0, mm_cpumask(&init_mm)); - set_max_mapnr(max_low_pfn); high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); pv_init(); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 289a2fecebef..72aea5cd1b85 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -290,7 +290,6 @@ void __init paging_init(void) */ max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; min_low_pfn = __MEMORY_START >> PAGE_SHIFT; - set_max_mapnr(max_low_pfn - min_low_pfn); nodes_clear(node_online_map); diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index d96a14ffceeb..6b58da14edc6 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -275,7 +275,6 @@ void __init mem_init(void) taint_real_pages(); - max_mapnr = last_valid_pfn - pfn_base; high_memory = __va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); diff --git a/arch/um/include/shared/mem_user.h b/arch/um/include/shared/mem_user.h index adfa08062f88..d4727efcf23d 100644 --- a/arch/um/include/shared/mem_user.h +++ b/arch/um/include/shared/mem_user.h @@ -47,7 +47,6 @@ extern int iomem_size; #define ROUND_4M(n) ((((unsigned long) (n)) + (1 << 22)) & ~((1 << 22) - 1)) extern unsigned long find_iomem(char *driver, unsigned long *len_out); -extern void mem_total_pages(unsigned long physmem, unsigned long iomem); extern void setup_physmem(unsigned long start, unsigned long usable, unsigned long len); extern void map_memory(unsigned long virt, unsigned long phys, diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index a74f17b033c4..af02b5f9911d 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -22,18 +22,6 @@ static int physmem_fd = -1; unsigned long high_physmem; EXPORT_SYMBOL(high_physmem); -void __init mem_total_pages(unsigned long physmem, unsigned long iomem) -{ - unsigned long phys_pages, iomem_pages, total_pages; - - phys_pages = physmem >> PAGE_SHIFT; - iomem_pages = iomem >> PAGE_SHIFT; - - total_pages = phys_pages + iomem_pages; - - max_mapnr = total_pages; -} - void map_memory(unsigned long virt, unsigned long phys, unsigned long len, int r, int w, int x) { diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 79ea97d4797e..6414cbf00572 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -419,7 +419,6 @@ void __init setup_arch(char **cmdline_p) stack_protections((unsigned long) init_task.stack); setup_physmem(uml_physmem, uml_reserved, physmem_size); - mem_total_pages(physmem_size, iomem_size); uml_dtb_init(); read_initrd(); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ac41b1e0940d..6d2f8cb9451e 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -650,9 +650,6 @@ void __init initmem_init(void) memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); -#ifdef CONFIG_FLATMEM - max_mapnr = IS_ENABLED(CONFIG_HIGHMEM) ? highend_pfn : max_low_pfn; -#endif __vmalloc_start_set = true; printk(KERN_NOTICE "%ldMB LOWMEM available.\n", diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 01577d33e602..9f1b0d5fccc7 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -164,7 +164,6 @@ void __init mem_init(void) { free_highpages(); - max_mapnr = max_pfn - ARCH_PFN_OFFSET; high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); -- cgit v1.2.3 From e120d1bc12da5c1bb871c346f741296610fd6fcb Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:50:00 +0200 Subject: arch, mm: set high_memory in free_area_init() high_memory defines upper bound on the directly mapped memory. This bound is defined by the beginning of ZONE_HIGHMEM when a system has high memory and by the end of memory otherwise. All this is known to generic memory management initialization code that can set high_memory while initializing core mm structures. Add a generic calculation of high_memory to free_area_init() and remove per-architecture calculation except for the architectures that set and use high_memory earlier than that. Link: https://lkml.kernel.org/r/20250313135003.836600-11-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Dave Hansen [x86] Tested-by: Mark Brown Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/alpha/mm/init.c | 1 - arch/arc/mm/init.c | 2 -- arch/arm64/mm/init.c | 2 -- arch/csky/mm/init.c | 1 - arch/hexagon/mm/init.c | 6 ------ arch/loongarch/kernel/numa.c | 1 - arch/loongarch/mm/init.c | 2 -- arch/microblaze/mm/init.c | 2 -- arch/mips/mm/init.c | 2 -- arch/nios2/mm/init.c | 6 ------ arch/openrisc/mm/init.c | 2 -- arch/parisc/mm/init.c | 1 - arch/riscv/mm/init.c | 1 - arch/s390/mm/init.c | 2 -- arch/sh/mm/init.c | 7 ------- arch/sparc/mm/init_32.c | 1 - arch/sparc/mm/init_64.c | 2 -- arch/um/kernel/um_arch.c | 1 - arch/x86/kernel/setup.c | 2 -- arch/x86/mm/init_32.c | 3 --- arch/x86/mm/numa_32.c | 3 --- arch/xtensa/mm/init.c | 2 -- 22 files changed, 52 deletions(-) (limited to 'arch') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index ec0eeae9c653..3ab2d2f3c917 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -276,7 +276,6 @@ srm_paging_stop (void) void __init mem_init(void) { - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); memblock_free_all(); } diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 7ef883d58dc1..05025122e965 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -150,8 +150,6 @@ void __init setup_arch_memory(void) */ max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn; - high_memory = (void *)(min_high_pfn << PAGE_SHIFT); - arch_pfn_offset = min(min_low_pfn, min_high_pfn); kmap_init(); #endif /* CONFIG_HIGHMEM */ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index ccdef53872a0..53a0b105890b 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -309,8 +309,6 @@ void __init arm64_memblock_init(void) } early_init_fdt_scan_reserved_mem(); - - high_memory = __va(memblock_end_of_DRAM() - 1) + 1; } void __init bootmem_init(void) diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index ba6694d6170a..a22801aa503a 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -47,7 +47,6 @@ void __init mem_init(void) #ifdef CONFIG_HIGHMEM unsigned long tmp; #endif - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index 508bb6a8dcc9..d412c2314509 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -100,12 +100,6 @@ static void __init paging_init(void) * initial kernel segment table's physical address. */ init_mm.context.ptbase = __pa(init_mm.pgd); - - /* - * Start of high memory area. Will probably need something more - * fancy if we... get more fancy. - */ - high_memory = (void *)((bootmem_lastpg + 1) << PAGE_SHIFT); } #ifndef DMA_RESERVE diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index 84fe7f854820..8eb489725b1a 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -389,7 +389,6 @@ void __init paging_init(void) void __init mem_init(void) { - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); } diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index 00449df50db1..6affa3609188 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -78,8 +78,6 @@ void __init paging_init(void) void __init mem_init(void) { - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - memblock_free_all(); } #endif /* !CONFIG_NUMA */ diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 857cd2b44bcf..7e2e342e84c5 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -120,8 +120,6 @@ void __init setup_memory(void) void __init mem_init(void) { - high_memory = (void *)__va(memory_start + lowmem_size - 1); - /* this will put all memory onto the freelists */ memblock_free_all(); #ifdef CONFIG_HIGHMEM diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index eb61a73520a0..ed9dde6a00f7 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -417,7 +417,6 @@ void __init paging_init(void) max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn; } #endif - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); free_area_init(max_zone_pfns); } @@ -469,7 +468,6 @@ void __init mem_init(void) #else /* CONFIG_NUMA */ void __init mem_init(void) { - high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); setup_zero_pages(); /* This comes from node 0 */ memblock_free_all(); } diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index 3cafa87ead9e..4ba8dfa0d238 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -62,12 +62,6 @@ void __init paging_init(void) void __init mem_init(void) { - unsigned long end_mem = memory_end; /* this must not include - kernel stack at top */ - - end_mem &= PAGE_MASK; - high_memory = __va(end_mem); - /* this will put all memory onto the freelists */ memblock_free_all(); } diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 9093c336e158..72c5952607ac 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -193,8 +193,6 @@ void __init mem_init(void) { BUG_ON(!mem_map); - high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); - /* clear the zero-page */ memset((void *)empty_zero_page, 0, PAGE_SIZE); diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 2cdfc0b1195c..4fbe354dc9b4 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -562,7 +562,6 @@ void __init mem_init(void) BUILD_BUG_ON(TMPALIAS_MAP_START >= 0x80000000); #endif - high_memory = __va((max_pfn << PAGE_SHIFT)); memblock_free_all(); #ifdef CONFIG_PA11 diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 157c9ca51541..ac6d41e86243 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -295,7 +295,6 @@ static void __init setup_bootmem(void) phys_ram_end = memblock_end_of_DRAM(); min_low_pfn = PFN_UP(phys_ram_base); max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); - high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index ad567e2100b7..4bd6f316d71f 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -159,8 +159,6 @@ void __init mem_init(void) cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask); cpumask_set_cpu(0, mm_cpumask(&init_mm)); - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - pv_init(); kfence_split_mapping(); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 72aea5cd1b85..6d459ffba4bc 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -330,13 +330,6 @@ unsigned int mem_init_done = 0; void __init mem_init(void) { - pg_data_t *pgdat; - - high_memory = NULL; - for_each_online_pgdat(pgdat) - high_memory = max_t(void *, high_memory, - __va(pgdat_end_pfn(pgdat) << PAGE_SHIFT)); - memblock_free_all(); /* Set this up early, so we can take care of the zero page */ diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 6b58da14edc6..81a468a9c223 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -275,7 +275,6 @@ void __init mem_init(void) taint_real_pages(); - high_memory = __va(max_low_pfn << PAGE_SHIFT); memblock_free_all(); for (i = 0; sp_banks[i].num_bytes != 0; i++) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 05882bca5b73..34d46adb9571 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2505,8 +2505,6 @@ static void __init register_page_bootmem_info(void) } void __init mem_init(void) { - high_memory = __va(last_valid_pfn << PAGE_SHIFT); - memblock_free_all(); /* diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 6414cbf00572..f24a3ce37ab7 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -385,7 +385,6 @@ int __init linux_main(int argc, char **argv, char **envp) high_physmem = uml_physmem + physmem_size; end_iomem = high_physmem + iomem_size; - high_memory = (void *) end_iomem; start_vm = VMALLOC_START; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ff8604007b08..74ac686d441a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -972,8 +972,6 @@ void __init setup_arch(char **cmdline_p) max_low_pfn = e820__end_of_low_ram_pfn(); else max_low_pfn = max_pfn; - - high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; #endif /* Find and reserve MPTABLE area */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 6d2f8cb9451e..801b659ead0c 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -643,9 +643,6 @@ void __init initmem_init(void) highstart_pfn = max_low_pfn; printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); - high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; -#else - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 65fda406e6f2..442ef3facff0 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -41,9 +41,6 @@ void __init initmem_init(void) highstart_pfn = max_low_pfn; printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); - high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; -#else - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif printk(KERN_NOTICE "%ldMB LOWMEM available.\n", pages_to_mb(max_low_pfn)); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 9f1b0d5fccc7..9b662477b3d4 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -164,8 +164,6 @@ void __init mem_init(void) { free_highpages(); - high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); - memblock_free_all(); } -- cgit v1.2.3 From 6faea3422e3b4e8de44a55aa3e6e843320da66d2 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:50:01 +0200 Subject: arch, mm: streamline HIGHMEM freeing All architectures that support HIGHMEM have their code that frees high memory pages to the buddy allocator while __free_memory_core() is limited to freeing only low memory. There is no actual reason for that. The memory map is completely ready by the time memblock_free_all() is called and high pages can be released to the buddy allocator along with low memory. Remove low memory limit from __free_memory_core() and drop per-architecture code that frees high memory pages. Link: https://lkml.kernel.org/r/20250313135003.836600-12-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Dave Hansen [x86] Tested-by: Mark Brown Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arc/mm/init.c | 6 +----- arch/arm/mm/init.c | 29 ----------------------------- arch/csky/mm/init.c | 14 -------------- arch/microblaze/mm/init.c | 16 ---------------- arch/mips/mm/init.c | 20 -------------------- arch/powerpc/mm/mem.c | 14 -------------- arch/sparc/mm/init_32.c | 25 ------------------------- arch/x86/include/asm/highmem.h | 3 --- arch/x86/include/asm/numa.h | 4 ---- arch/x86/include/asm/numa_32.h | 13 ------------- arch/x86/mm/Makefile | 2 -- arch/x86/mm/highmem_32.c | 34 ---------------------------------- arch/x86/mm/init_32.c | 28 ---------------------------- arch/xtensa/mm/init.c | 29 ----------------------------- 14 files changed, 1 insertion(+), 236 deletions(-) delete mode 100644 arch/x86/include/asm/numa_32.h delete mode 100644 arch/x86/mm/highmem_32.c (limited to 'arch') diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 05025122e965..11ce638731c9 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -160,11 +160,7 @@ void __init setup_arch_memory(void) static void __init highmem_init(void) { #ifdef CONFIG_HIGHMEM - unsigned long tmp; - memblock_phys_free(high_mem_start, high_mem_sz); - for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++) - free_highmem_page(pfn_to_page(tmp)); #endif } @@ -176,8 +172,8 @@ static void __init highmem_init(void) */ void __init mem_init(void) { - memblock_free_all(); highmem_init(); + memblock_free_all(); BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE); BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index d4bcc745a044..7bb5ce02b9b5 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -237,33 +237,6 @@ static inline void poison_init_mem(void *s, size_t count) *p++ = 0xe7fddef0; } -static void __init free_highpages(void) -{ -#ifdef CONFIG_HIGHMEM - unsigned long max_low = max_low_pfn; - phys_addr_t range_start, range_end; - u64 i; - - /* set highmem page free */ - for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, - &range_start, &range_end, NULL) { - unsigned long start = PFN_UP(range_start); - unsigned long end = PFN_DOWN(range_end); - - /* Ignore complete lowmem entries */ - if (end <= max_low) - continue; - - /* Truncate partial highmem entries */ - if (start < max_low) - start = max_low; - - for (; start < end; start++) - free_highmem_page(pfn_to_page(start)); - } -#endif -} - /* * mem_init() marks the free areas in the mem_map and tells us how much * memory is free. This is done after various parts of the system have @@ -283,8 +256,6 @@ void __init mem_init(void) /* this will put all unused low memory onto the freelists */ memblock_free_all(); - free_highpages(); - /* * Check boundaries twice: Some fundamental inconsistencies can * be detected at build time already. diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index a22801aa503a..3914c2b873da 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -44,21 +44,7 @@ EXPORT_SYMBOL(empty_zero_page); void __init mem_init(void) { -#ifdef CONFIG_HIGHMEM - unsigned long tmp; -#endif - memblock_free_all(); - -#ifdef CONFIG_HIGHMEM - for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { - struct page *page = pfn_to_page(tmp); - - /* FIXME not sure about */ - if (!memblock_is_reserved(tmp << PAGE_SHIFT)) - free_highmem_page(page); - } -#endif } void free_initmem(void) diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 7e2e342e84c5..3e664e0efc33 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -52,19 +52,6 @@ static void __init highmem_init(void) map_page(PKMAP_BASE, 0, 0); /* XXX gross */ pkmap_page_table = virt_to_kpte(PKMAP_BASE); } - -static void __meminit highmem_setup(void) -{ - unsigned long pfn; - - for (pfn = max_low_pfn; pfn < max_pfn; ++pfn) { - struct page *page = pfn_to_page(pfn); - - /* FIXME not sure about */ - if (!memblock_is_reserved(pfn << PAGE_SHIFT)) - free_highmem_page(page); - } -} #endif /* CONFIG_HIGHMEM */ /* @@ -122,9 +109,6 @@ void __init mem_init(void) { /* this will put all memory onto the freelists */ memblock_free_all(); -#ifdef CONFIG_HIGHMEM - highmem_setup(); -#endif mem_init_done = 1; } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index ed9dde6a00f7..075177e817ac 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -425,25 +425,6 @@ void __init paging_init(void) static struct kcore_list kcore_kseg0; #endif -static inline void __init mem_init_free_highmem(void) -{ -#ifdef CONFIG_HIGHMEM - unsigned long tmp; - - if (cpu_has_dc_aliases) - return; - - for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { - struct page *page = pfn_to_page(tmp); - - if (!memblock_is_memory(PFN_PHYS(tmp))) - SetPageReserved(page); - else - free_highmem_page(page); - } -#endif -} - void __init mem_init(void) { /* @@ -454,7 +435,6 @@ void __init mem_init(void) maar_init(); setup_zero_pages(); /* Setup zeroed pages. */ - mem_init_free_highmem(); memblock_free_all(); #ifdef CONFIG_64BIT diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index c7708c8fad29..1bc94bca9944 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -297,20 +297,6 @@ void __init mem_init(void) memblock_free_all(); -#ifdef CONFIG_HIGHMEM - { - unsigned long pfn, highmem_mapnr; - - highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT; - for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) { - phys_addr_t paddr = (phys_addr_t)pfn << PAGE_SHIFT; - struct page *page = pfn_to_page(pfn); - if (memblock_is_memory(paddr) && !memblock_is_reserved(paddr)) - free_highmem_page(page); - } - } -#endif /* CONFIG_HIGHMEM */ - #if defined(CONFIG_PPC_E500) && !defined(CONFIG_SMP) /* * If smp is enabled, next_tlbcam_idx is initialized in the cpu up diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 81a468a9c223..043e9b6fadd0 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -232,18 +232,6 @@ static void __init taint_real_pages(void) } } -static void map_high_region(unsigned long start_pfn, unsigned long end_pfn) -{ - unsigned long tmp; - -#ifdef CONFIG_DEBUG_HIGHMEM - printk("mapping high region %08lx - %08lx\n", start_pfn, end_pfn); -#endif - - for (tmp = start_pfn; tmp < end_pfn; tmp++) - free_highmem_page(pfn_to_page(tmp)); -} - void __init mem_init(void) { int i; @@ -276,19 +264,6 @@ void __init mem_init(void) taint_real_pages(); memblock_free_all(); - - for (i = 0; sp_banks[i].num_bytes != 0; i++) { - unsigned long start_pfn = sp_banks[i].base_addr >> PAGE_SHIFT; - unsigned long end_pfn = (sp_banks[i].base_addr + sp_banks[i].num_bytes) >> PAGE_SHIFT; - - if (end_pfn <= highstart_pfn) - continue; - - if (start_pfn < highstart_pfn) - start_pfn = highstart_pfn; - - map_high_region(start_pfn, end_pfn); - } } void sparc_flush_page_to_ram(struct page *page) diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 731ee7cc40a5..585bdadba47d 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -69,9 +69,6 @@ extern unsigned long highstart_pfn, highend_pfn; arch_flush_lazy_mmu_mode(); \ } while (0) -extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn, - unsigned long end_pfn); - #endif /* __KERNEL__ */ #endif /* _ASM_X86_HIGHMEM_H */ diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 5469d7a7c40f..53ba39ce010c 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -41,10 +41,6 @@ static inline int numa_cpu_node(int cpu) } #endif /* CONFIG_NUMA */ -#ifdef CONFIG_X86_32 -# include -#endif - #ifdef CONFIG_NUMA extern void numa_set_node(int cpu, int node); extern void numa_clear_node(int cpu); diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h deleted file mode 100644 index 9c8e9e85be77..000000000000 --- a/arch/x86/include/asm/numa_32.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_NUMA_32_H -#define _ASM_X86_NUMA_32_H - -#ifdef CONFIG_HIGHMEM -extern void set_highmem_pages_init(void); -#else -static inline void set_highmem_pages_init(void) -{ -} -#endif - -#endif /* _ASM_X86_NUMA_32_H */ diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index e0c99a8760ca..32035d5be5a0 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -42,8 +42,6 @@ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PTDUMP) += dump_pagetables.o obj-$(CONFIG_PTDUMP_DEBUGFS) += debug_pagetables.o -obj-$(CONFIG_HIGHMEM) += highmem_32.o - KASAN_SANITIZE_kasan_init_$(BITS).o := n obj-$(CONFIG_KASAN) += kasan_init_$(BITS).o diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c deleted file mode 100644 index d9efa35711ee..000000000000 --- a/arch/x86/mm/highmem_32.c +++ /dev/null @@ -1,34 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include -#include -#include /* for totalram_pages */ -#include -#include - -void __init set_highmem_pages_init(void) -{ - struct zone *zone; - int nid; - - /* - * Explicitly reset zone->managed_pages because set_highmem_pages_init() - * is invoked before memblock_free_all() - */ - reset_all_zones_managed_pages(); - for_each_zone(zone) { - unsigned long zone_start_pfn, zone_end_pfn; - - if (!is_highmem(zone)) - continue; - - zone_start_pfn = zone->zone_start_pfn; - zone_end_pfn = zone_start_pfn + zone->spanned_pages; - - nid = zone_to_nid(zone); - printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n", - zone->name, nid, zone_start_pfn, zone_end_pfn); - - add_highpages_with_active_regions(nid, zone_start_pfn, - zone_end_pfn); - } -} diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 801b659ead0c..9ee8ec2bc5d1 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -394,23 +394,6 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = virt_to_kpte(vaddr); } - -void __init add_highpages_with_active_regions(int nid, - unsigned long start_pfn, unsigned long end_pfn) -{ - phys_addr_t start, end; - u64 i; - - for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) { - unsigned long pfn = clamp_t(unsigned long, PFN_UP(start), - start_pfn, end_pfn); - unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end), - start_pfn, end_pfn); - for ( ; pfn < e_pfn; pfn++) - if (pfn_valid(pfn)) - free_highmem_page(pfn_to_page(pfn)); - } -} #else static inline void permanent_kmaps_init(pgd_t *pgd_base) { @@ -715,17 +698,6 @@ void __init mem_init(void) #ifdef CONFIG_FLATMEM BUG_ON(!mem_map); #endif - /* - * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to - * be done before memblock_free_all(). Memblock use free low memory for - * temporary data (see find_range_array()) and for this purpose can use - * pages that was already passed to the buddy allocator, hence marked as - * not accessible in the page tables when compiled with - * CONFIG_DEBUG_PAGEALLOC. Otherwise order of initialization is not - * important here. - */ - set_highmem_pages_init(); - /* this will put all low memory onto the freelists */ memblock_free_all(); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 9b662477b3d4..47ecbe28263e 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -129,41 +129,12 @@ void __init zones_init(void) print_vm_layout(); } -static void __init free_highpages(void) -{ -#ifdef CONFIG_HIGHMEM - unsigned long max_low = max_low_pfn; - phys_addr_t range_start, range_end; - u64 i; - - /* set highmem page free */ - for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, - &range_start, &range_end, NULL) { - unsigned long start = PFN_UP(range_start); - unsigned long end = PFN_DOWN(range_end); - - /* Ignore complete lowmem entries */ - if (end <= max_low) - continue; - - /* Truncate partial highmem entries */ - if (start < max_low) - start = max_low; - - for (; start < end; start++) - free_highmem_page(pfn_to_page(start)); - } -#endif -} - /* * Initialize memory pages. */ void __init mem_init(void) { - free_highpages(); - memblock_free_all(); } -- cgit v1.2.3 From 0d98484ee3330c35d1dc0da0be0871b3596cbe0d Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:50:02 +0200 Subject: arch, mm: introduce arch_mm_preinit Currently, implementation of mem_init() in every architecture consists of one or more of the following: * initializations that must run before page allocator is active, for instance swiotlb_init() * a call to memblock_free_all() to release all the memory to the buddy allocator * initializations that must run after page allocator is ready and there is no arch-specific hook other than mem_init() for that, like for example register_page_bootmem_info() in x86 and sparc64 or simple setting of mem_init_done = 1 in several architectures * a bunch of semi-related stuff that apparently had no better place to live, for example a ton of BUILD_BUG_ON()s in parisc. Introduce arch_mm_preinit() that will be the first thing called from mm_core_init(). On architectures that have initializations that must happen before the page allocator is ready, move those into arch_mm_preinit() along with the code that does not depend on ordering with page allocator setup. On several architectures this results in reduction of mem_init() to a single call to memblock_free_all() that allows its consolidation next. Link: https://lkml.kernel.org/r/20250313135003.836600-13-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Dave Hansen [x86] Tested-by: Mark Brown Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: David S. Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arc/mm/init.c | 13 ++++++------- arch/arm/mm/init.c | 21 ++++++++++++--------- arch/arm64/mm/init.c | 21 ++++++++++++--------- arch/mips/mm/init.c | 11 +++++++---- arch/powerpc/mm/mem.c | 9 ++++++--- arch/riscv/mm/init.c | 8 ++++++-- arch/s390/mm/init.c | 5 ++++- arch/sparc/mm/init_32.c | 5 ++++- arch/um/kernel/mem.c | 7 +++++-- arch/x86/mm/init_32.c | 6 +++++- arch/x86/mm/init_64.c | 5 ++++- 11 files changed, 71 insertions(+), 40 deletions(-) (limited to 'arch') diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 11ce638731c9..90715b4a0bfa 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -157,11 +157,16 @@ void __init setup_arch_memory(void) free_area_init(max_zone_pfn); } -static void __init highmem_init(void) +void __init arch_mm_preinit(void) { #ifdef CONFIG_HIGHMEM memblock_phys_free(high_mem_start, high_mem_sz); #endif + + BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE); + BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE); + BUILD_BUG_ON((PTRS_PER_PMD * sizeof(pmd_t)) > PAGE_SIZE); + BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE); } /* @@ -172,13 +177,7 @@ static void __init highmem_init(void) */ void __init mem_init(void) { - highmem_init(); memblock_free_all(); - - BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE); - BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE); - BUILD_BUG_ON((PTRS_PER_PMD * sizeof(pmd_t)) > PAGE_SIZE); - BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE); } #ifdef CONFIG_HIGHMEM diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 7bb5ce02b9b5..7222100b0631 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -237,12 +237,7 @@ static inline void poison_init_mem(void *s, size_t count) *p++ = 0xe7fddef0; } -/* - * mem_init() marks the free areas in the mem_map and tells us how much - * memory is free. This is done after various parts of the system have - * claimed their memory after the kernel image. - */ -void __init mem_init(void) +void __init arch_mm_preinit(void) { #ifdef CONFIG_ARM_LPAE swiotlb_init(max_pfn > arm_dma_pfn_limit, SWIOTLB_VERBOSE); @@ -253,9 +248,6 @@ void __init mem_init(void) memblock_phys_free(PHYS_OFFSET, __pa(swapper_pg_dir) - PHYS_OFFSET); #endif - /* this will put all unused low memory onto the freelists */ - memblock_free_all(); - /* * Check boundaries twice: Some fundamental inconsistencies can * be detected at build time already. @@ -271,6 +263,17 @@ void __init mem_init(void) #endif } +/* + * mem_init() marks the free areas in the mem_map and tells us how much + * memory is free. This is done after various parts of the system have + * claimed their memory after the kernel image. + */ +void __init mem_init(void) +{ + /* this will put all unused low memory onto the freelists */ + memblock_free_all(); +} + #ifdef CONFIG_STRICT_KERNEL_RWX struct section_perm { const char *name; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 53a0b105890b..2312e3812043 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -357,12 +357,7 @@ void __init bootmem_init(void) memblock_dump_all(); } -/* - * mem_init() marks the free areas in the mem_map and tells us how much memory - * is free. This is done after various parts of the system have claimed their - * memory after the kernel image. - */ -void __init mem_init(void) +void __init arch_mm_preinit(void) { unsigned int flags = SWIOTLB_VERBOSE; bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit); @@ -386,9 +381,6 @@ void __init mem_init(void) swiotlb_init(swiotlb, flags); swiotlb_update_mem_attributes(); - /* this will put all unused low memory onto the freelists */ - memblock_free_all(); - /* * Check boundaries twice: Some fundamental inconsistencies can be * detected at build time already. @@ -414,6 +406,17 @@ void __init mem_init(void) } } +/* + * mem_init() marks the free areas in the mem_map and tells us how much memory + * is free. This is done after various parts of the system have claimed their + * memory after the kernel image. + */ +void __init mem_init(void) +{ + /* this will put all unused low memory onto the freelists */ + memblock_free_all(); +} + void free_initmem(void) { void *lm_init_begin = lm_alias(__init_begin); diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 075177e817ac..eec38e7735dd 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -425,7 +425,7 @@ void __init paging_init(void) static struct kcore_list kcore_kseg0; #endif -void __init mem_init(void) +void __init arch_mm_preinit(void) { /* * When PFN_PTE_SHIFT is greater than PAGE_SHIFT we won't have enough PTE @@ -435,7 +435,6 @@ void __init mem_init(void) maar_init(); setup_zero_pages(); /* Setup zeroed pages. */ - memblock_free_all(); #ifdef CONFIG_64BIT if ((unsigned long) &_text > (unsigned long) CKSEG0) @@ -446,13 +445,17 @@ void __init mem_init(void) #endif } #else /* CONFIG_NUMA */ -void __init mem_init(void) +void __init arch_mm_preinit(void) { setup_zero_pages(); /* This comes from node 0 */ - memblock_free_all(); } #endif /* !CONFIG_NUMA */ +void __init mem_init(void) +{ + memblock_free_all(); +} + void free_init_pages(const char *what, unsigned long begin, unsigned long end) { unsigned long pfn; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 1bc94bca9944..68efdaf14e58 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -273,7 +273,7 @@ void __init paging_init(void) mark_nonram_nosave(); } -void __init mem_init(void) +void __init arch_mm_preinit(void) { /* * book3s is limited to 16 page sizes due to encoding this in @@ -295,8 +295,6 @@ void __init mem_init(void) kasan_late_init(); - memblock_free_all(); - #if defined(CONFIG_PPC_E500) && !defined(CONFIG_SMP) /* * If smp is enabled, next_tlbcam_idx is initialized in the cpu up @@ -329,6 +327,11 @@ void __init mem_init(void) #endif /* CONFIG_PPC32 */ } +void __init mem_init(void) +{ + memblock_free_all(); +} + void free_initmem(void) { ppc_md.progress = ppc_printk_progress; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ac6d41e86243..9efadabf6be1 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -171,7 +171,7 @@ static void __init print_vm_layout(void) static void print_vm_layout(void) { } #endif /* CONFIG_DEBUG_VM */ -void __init mem_init(void) +void __init arch_mm_preinit(void) { bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit); #ifdef CONFIG_FLATMEM @@ -192,11 +192,15 @@ void __init mem_init(void) } swiotlb_init(swiotlb, SWIOTLB_VERBOSE); - memblock_free_all(); print_vm_layout(); } +void __init mem_init(void) +{ + memblock_free_all(); +} + /* Limit the memory size via mem. */ static phys_addr_t memory_limit; #ifdef CONFIG_XIP_KERNEL diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 4bd6f316d71f..e771b7458d8b 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -154,7 +154,7 @@ static void pv_init(void) swiotlb_update_mem_attributes(); } -void __init mem_init(void) +void __init arch_mm_preinit(void) { cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask); cpumask_set_cpu(0, mm_cpumask(&init_mm)); @@ -163,7 +163,10 @@ void __init mem_init(void) kfence_split_mapping(); setup_zero_pages(); /* Setup zeroed pages. */ +} +void __init mem_init(void) +{ /* this will put all low memory onto the freelists */ memblock_free_all(); } diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 043e9b6fadd0..e16c32c5728f 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -232,7 +232,7 @@ static void __init taint_real_pages(void) } } -void __init mem_init(void) +void __init arch_mm_preinit(void) { int i; @@ -262,7 +262,10 @@ void __init mem_init(void) memset(sparc_valid_addr_bitmap, 0, i << 2); taint_real_pages(); +} +void __init mem_init(void) +{ memblock_free_all(); } diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index befed230aac2..cce387438e60 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -54,7 +54,7 @@ int kmalloc_ok = 0; /* Used during early boot */ static unsigned long brk_end; -void __init mem_init(void) +void __init arch_mm_preinit(void) { /* clear the zero-page */ memset(empty_zero_page, 0, PAGE_SIZE); @@ -66,10 +66,13 @@ void __init mem_init(void) map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); memblock_free((void *)brk_end, uml_reserved - brk_end); uml_reserved = brk_end; + max_pfn = max_low_pfn; +} +void __init mem_init(void) +{ /* this will put all low memory onto the freelists */ memblock_free_all(); - max_pfn = max_low_pfn; kmalloc_ok = 1; } diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 9ee8ec2bc5d1..16664c5464b5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -691,13 +691,17 @@ static void __init test_wp_bit(void) panic("Linux doesn't support CPUs with broken WP."); } -void __init mem_init(void) +void __init arch_mm_preinit(void) { pci_iommu_alloc(); #ifdef CONFIG_FLATMEM BUG_ON(!mem_map); #endif +} + +void __init mem_init(void) +{ /* this will put all low memory onto the freelists */ memblock_free_all(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 6e8e4ef5312a..a88f7db8089e 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1348,10 +1348,13 @@ failed: panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl); } -void __init mem_init(void) +void __init arch_mm_preinit(void) { pci_iommu_alloc(); +} +void __init mem_init(void) +{ /* clear_bss() already clear the empty_zero_page */ /* this will put all memory onto the freelists */ -- cgit v1.2.3 From 8afa901c147a41f92e83943cddf154bbb7995ee6 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Thu, 13 Mar 2025 15:50:03 +0200 Subject: arch, mm: make releasing of memory to page allocator more explicit The point where the memory is released from memblock to the buddy allocator is hidden inside arch-specific mem_init()s and the call to memblock_free_all() is needlessly duplicated in every artiste cure and after introduction of arch_mm_preinit() hook, mem_init() implementation on many architecture only contains the call to memblock_free_all(). Pull memblock_free_all() call into mm_core_init() and drop mem_init() on relevant architectures to make it more explicit where the free memory is released from memblock to the buddy allocator and to reduce code duplication in architecture specific code. Link: https://lkml.kernel.org/r/20250313135003.836600-14-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Dave Hansen [x86] Acked-by: Geert Uytterhoeven [m68k] Tested-by: Mark Brown Cc: Alexander Gordeev Cc: Andreas Larsson Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Borislav Betkov Cc: Catalin Marinas Cc: David S. Miller Cc: Dinh Nguyen Cc: Gerald Schaefer Cc: Guo Ren (csky) Cc: Heiko Carstens Cc: Helge Deller Cc: Huacai Chen Cc: Ingo Molnar Cc: Jiaxun Yang Cc: Johannes Berg Cc: John Paul Adrian Glaubitz Cc: Madhavan Srinivasan Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Russel King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleinxer Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/alpha/mm/init.c | 6 ------ arch/arc/mm/init.c | 11 ----------- arch/arm/mm/init.c | 11 ----------- arch/arm64/mm/init.c | 11 ----------- arch/csky/mm/init.c | 5 ----- arch/hexagon/mm/init.c | 18 ------------------ arch/loongarch/kernel/numa.c | 5 ----- arch/loongarch/mm/init.c | 5 ----- arch/m68k/mm/init.c | 2 -- arch/microblaze/mm/init.c | 3 --- arch/mips/mm/init.c | 5 ----- arch/nios2/mm/init.c | 6 ------ arch/openrisc/mm/init.c | 3 --- arch/parisc/mm/init.c | 2 -- arch/powerpc/mm/mem.c | 5 ----- arch/riscv/mm/init.c | 5 ----- arch/s390/mm/init.c | 6 ------ arch/sh/mm/init.c | 2 -- arch/sparc/mm/init_32.c | 5 ----- arch/sparc/mm/init_64.c | 2 -- arch/um/kernel/mem.c | 2 -- arch/x86/mm/init_32.c | 3 --- arch/x86/mm/init_64.c | 2 -- arch/xtensa/mm/init.c | 9 --------- 24 files changed, 134 deletions(-) (limited to 'arch') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 3ab2d2f3c917..2d491b8cdab9 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -273,12 +273,6 @@ srm_paging_stop (void) } #endif -void __init -mem_init(void) -{ - memblock_free_all(); -} - static const pgprot_t protection_map[16] = { [VM_NONE] = _PAGE_P(_PAGE_FOE | _PAGE_FOW | _PAGE_FOR), diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 90715b4a0bfa..a73cc94f806e 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -169,17 +169,6 @@ void __init arch_mm_preinit(void) BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE); } -/* - * mem_init - initializes memory - * - * Frees up bootmem - * Calculates and displays memory available/used - */ -void __init mem_init(void) -{ - memblock_free_all(); -} - #ifdef CONFIG_HIGHMEM int pfn_valid(unsigned long pfn) { diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 7222100b0631..54bdca025c9f 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -263,17 +263,6 @@ void __init arch_mm_preinit(void) #endif } -/* - * mem_init() marks the free areas in the mem_map and tells us how much - * memory is free. This is done after various parts of the system have - * claimed their memory after the kernel image. - */ -void __init mem_init(void) -{ - /* this will put all unused low memory onto the freelists */ - memblock_free_all(); -} - #ifdef CONFIG_STRICT_KERNEL_RWX struct section_perm { const char *name; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 2312e3812043..4b966d5709d2 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -406,17 +406,6 @@ void __init arch_mm_preinit(void) } } -/* - * mem_init() marks the free areas in the mem_map and tells us how much memory - * is free. This is done after various parts of the system have claimed their - * memory after the kernel image. - */ -void __init mem_init(void) -{ - /* this will put all unused low memory onto the freelists */ - memblock_free_all(); -} - void free_initmem(void) { void *lm_init_begin = lm_alias(__init_begin); diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index 3914c2b873da..573da66b2543 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -42,11 +42,6 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); -void __init mem_init(void) -{ - memblock_free_all(); -} - void free_initmem(void) { free_initmem_default(-1); diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index d412c2314509..34eb9d424b96 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -43,24 +43,6 @@ DEFINE_SPINLOCK(kmap_gen_lock); /* checkpatch says don't init this to 0. */ unsigned long long kmap_generation; -/* - * mem_init - initializes memory - * - * Frees up bootmem - * Fixes up more stuff for HIGHMEM - * Calculates and displays memory available/used - */ -void __init mem_init(void) -{ - /* No idea where this is actually declared. Seems to evade LXR. */ - memblock_free_all(); - - /* - * To-Do: someone somewhere should wipe out the bootmem map - * after we're done? - */ -} - void sync_icache_dcache(pte_t pte) { unsigned long addr; diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index 8eb489725b1a..30a72fd528c0 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -387,11 +387,6 @@ void __init paging_init(void) free_area_init(zones_size); } -void __init mem_init(void) -{ - memblock_free_all(); -} - int pcibus_to_node(struct pci_bus *bus) { return dev_to_node(&bus->dev); diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index 6affa3609188..fdb7f73ad160 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -75,11 +75,6 @@ void __init paging_init(void) free_area_init(max_zone_pfns); } - -void __init mem_init(void) -{ - memblock_free_all(); -} #endif /* !CONFIG_NUMA */ void __ref free_initmem(void) diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 8b11d0d545aa..488411af1b3f 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -121,7 +121,5 @@ static inline void init_pointer_tables(void) void __init mem_init(void) { - /* this will put all memory onto the freelists */ - memblock_free_all(); init_pointer_tables(); } diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 3e664e0efc33..65f0d1fb8a2a 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -107,9 +107,6 @@ void __init setup_memory(void) void __init mem_init(void) { - /* this will put all memory onto the freelists */ - memblock_free_all(); - mem_init_done = 1; } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index eec38e7735dd..a673d3d68254 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -451,11 +451,6 @@ void __init arch_mm_preinit(void) } #endif /* !CONFIG_NUMA */ -void __init mem_init(void) -{ - memblock_free_all(); -} - void free_init_pages(const char *what, unsigned long begin, unsigned long end) { unsigned long pfn; diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index 4ba8dfa0d238..94efa3de3933 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -60,12 +60,6 @@ void __init paging_init(void) (unsigned long)empty_zero_page + PAGE_SIZE); } -void __init mem_init(void) -{ - /* this will put all memory onto the freelists */ - memblock_free_all(); -} - void __init mmu_init(void) { flush_tlb_all(); diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 72c5952607ac..be1c2eb8bb94 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -196,9 +196,6 @@ void __init mem_init(void) /* clear the zero-page */ memset((void *)empty_zero_page, 0, PAGE_SIZE); - /* this will put all low memory onto the freelists */ - memblock_free_all(); - printk("mem_init_done ...........................................\n"); mem_init_done = 1; return; diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 4fbe354dc9b4..14270715d754 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -562,8 +562,6 @@ void __init mem_init(void) BUILD_BUG_ON(TMPALIAS_MAP_START >= 0x80000000); #endif - memblock_free_all(); - #ifdef CONFIG_PA11 if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) { pcxl_dma_start = (unsigned long)SET_MAP_OFFSET(MAP_START); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 68efdaf14e58..d8fe11b64259 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -327,11 +327,6 @@ void __init arch_mm_preinit(void) #endif /* CONFIG_PPC32 */ } -void __init mem_init(void) -{ - memblock_free_all(); -} - void free_initmem(void) { ppc_md.progress = ppc_printk_progress; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9efadabf6be1..79b649f6de72 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -196,11 +196,6 @@ void __init arch_mm_preinit(void) print_vm_layout(); } -void __init mem_init(void) -{ - memblock_free_all(); -} - /* Limit the memory size via mem. */ static phys_addr_t memory_limit; #ifdef CONFIG_XIP_KERNEL diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index e771b7458d8b..5b7b7b281334 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -165,12 +165,6 @@ void __init arch_mm_preinit(void) setup_zero_pages(); /* Setup zeroed pages. */ } -void __init mem_init(void) -{ - /* this will put all low memory onto the freelists */ - memblock_free_all(); -} - unsigned long memory_block_size_bytes(void) { /* diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 6d459ffba4bc..99e302eeeec1 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -330,8 +330,6 @@ unsigned int mem_init_done = 0; void __init mem_init(void) { - memblock_free_all(); - /* Set this up early, so we can take care of the zero page */ cpu_cache_init(); diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index e16c32c5728f..fdc93dd12c3e 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -264,11 +264,6 @@ void __init arch_mm_preinit(void) taint_real_pages(); } -void __init mem_init(void) -{ - memblock_free_all(); -} - void sparc_flush_page_to_ram(struct page *page) { unsigned long vaddr = (unsigned long)page_address(page); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 34d46adb9571..760818950464 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2505,8 +2505,6 @@ static void __init register_page_bootmem_info(void) } void __init mem_init(void) { - memblock_free_all(); - /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index cce387438e60..379f33a1babf 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -71,8 +71,6 @@ void __init arch_mm_preinit(void) void __init mem_init(void) { - /* this will put all low memory onto the freelists */ - memblock_free_all(); kmalloc_ok = 1; } diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 16664c5464b5..95b2758b4e4d 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -702,9 +702,6 @@ void __init arch_mm_preinit(void) void __init mem_init(void) { - /* this will put all low memory onto the freelists */ - memblock_free_all(); - after_bootmem = 1; x86_init.hyper.init_after_bootmem(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a88f7db8089e..d67f15386ea2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1357,8 +1357,6 @@ void __init mem_init(void) { /* clear_bss() already clear the empty_zero_page */ - /* this will put all memory onto the freelists */ - memblock_free_all(); after_bootmem = 1; x86_init.hyper.init_after_bootmem(); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 47ecbe28263e..cc52733a0649 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -129,15 +129,6 @@ void __init zones_init(void) print_vm_layout(); } -/* - * Initialize memory pages. - */ - -void __init mem_init(void) -{ - memblock_free_all(); -} - static void __init parse_memmap_one(char *p) { char *oldp; -- cgit v1.2.3 From 1a15bb8303b6b104e78028b6c68f76a0d4562134 Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Wed, 12 Mar 2025 19:28:50 +0800 Subject: x86/mce: use is_copy_from_user() to determine copy-from-user context Patch series "mm/hwpoison: Fix regressions in memory failure handling", v4. ## 1. What am I trying to do: This patchset resolves two critical regressions related to memory failure handling that have appeared in the upstream kernel since version 5.17, as compared to 5.10 LTS. - copyin case: poison found in user page while kernel copying from user space - instr case: poison found while instruction fetching in user space ## 2. What is the expected outcome and why - For copyin case: Kernel can recover from poison found where kernel is doing get_user() or copy_from_user() if those places get an error return and the kernel return -EFAULT to the process instead of crashing. More specifily, MCE handler checks the fixup handler type to decide whether an in kernel #MC can be recovered. When EX_TYPE_UACCESS is found, the PC jumps to recovery code specified in _ASM_EXTABLE_FAULT() and return a -EFAULT to user space. - For instr case: If a poison found while instruction fetching in user space, full recovery is possible. User process takes #PF, Linux allocates a new page and fills by reading from storage. ## 3. What actually happens and why - For copyin case: kernel panic since v5.17 Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and later patches updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. It breaks previous EX_TYPE_UACCESS handling when posion found in get_user() or copy_from_user(). - For instr case: user process is killed by a SIGBUS signal due to #CMCI and #MCE race When an uncorrected memory error is consumed there is a race between the CMCI from the memory controller reporting an uncorrected error with a UCNA signature, and the core reporting and SRAR signature machine check when the data is about to be consumed. ### Background: why *UN*corrected errors tied to *C*MCI in Intel platform [1] Prior to Icelake memory controllers reported patrol scrub events that detected a previously unseen uncorrected error in memory by signaling a broadcast machine check with an SRAO (Software Recoverable Action Optional) signature in the machine check bank. This was overkill because it's not an urgent problem that no core is on the verge of consuming that bad data. It's also found that multi SRAO UCE may cause nested MCE interrupts and finally become an IERR. Hence, Intel downgrades the machine check bank signature of patrol scrub from SRAO to UCNA (Uncorrected, No Action required), and signal changed to #CMCI. Just to add to the confusion, Linux does take an action (in uc_decode_notifier()) to try to offline the page despite the UC*NA* signature name. ### Background: why #CMCI and #MCE race when poison is consuming in Intel platform [1] Having decided that CMCI/UCNA is the best action for patrol scrub errors, the memory controller uses it for reads too. But the memory controller is executing asynchronously from the core, and can't tell the difference between a "real" read and a speculative read. So it will do CMCI/UCNA if an error is found in any read. Thus: 1) Core is clever and thinks address A is needed soon, issues a speculative read. 2) Core finds it is going to use address A soon after sending the read request 3) The CMCI from the memory controller is in a race with MCE from the core that will soon try to retire the load from address A. Quite often (because speculation has got better) the CMCI from the memory controller is delivered before the core is committed to the instruction reading address A, so the interrupt is taken, and Linux offlines the page (marking it as poison). ## Why user process is killed for instr case Commit 046545a661af ("mm/hwpoison: fix error page recovered but reported "not recovered"") tries to fix noise message "Memory error not recovered" and skips duplicate SIGBUSs due to the race. But it also introduced a bug that kill_accessing_process() return -EHWPOISON for instr case, as result, kill_me_maybe() send a SIGBUS to user process. # 4. The fix, in my opinion, should be: - For copyin case: The key point is whether the error context is in a read from user memory. We do not care about the ex-type if we know its a MOV reading from userspace. is_copy_from_user() return true when both of the following two checks are true: - the current instruction is copy - source address is user memory If copy_user is true, we set m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; Then do_machine_check() will try fixup_exception() first. - For instr case: let kill_accessing_process() return 0 to prevent a SIGBUS. - For patch 3: The return value of memory_failure() is quite important while discussed instr case regression with Tony and Miaohe for patch 2, so add comment about the return value. This patch (of 3): Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and commit 4c132d1d844a ("x86/futex: Remove .fixup usage") updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. The error context for copy-from-user operations no longer functions as an in-kernel recovery context. Consequently, the error context for copy-from-user operations no longer functions as an in-kernel recovery context, resulting in kernel panics with the message: "Machine check: Data load in unrecoverable area of kernel." To address this, it is crucial to identify if an error context involves a read operation from user memory. The function is_copy_from_user() can be utilized to determine: - the current operation is copy - when reading user memory When these conditions are met, is_copy_from_user() will return true, confirming that it is indeed a direct copy from user memory. This check is essential for correctly handling the context of errors in these operations without relying on the extable fixup types that previously allowed for in-kernel recovery. So, use is_copy_from_user() to determine if a context is copy user directly. Link: https://lkml.kernel.org/r/20250312112852.82415-1-xueshuai@linux.alibaba.com Link: https://lkml.kernel.org/r/20250312112852.82415-2-xueshuai@linux.alibaba.com Fixes: 4c132d1d844a ("x86/futex: Remove .fixup usage") Signed-off-by: Shuai Xue Suggested-by: Peter Zijlstra Acked-by: Borislav Petkov (AMD) Tested-by: Tony Luck Cc: Baolin Wang Cc: Borislav Betkov Cc: Catalin Marinas Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Josh Poimboeuf Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Ruidong Tian Cc: Thomas Gleinxer Cc: Yazen Ghannam Cc: Jane Chu Cc: Jarkko Sakkinen Cc: Jonathan Cameron Cc: Signed-off-by: Andrew Morton --- arch/x86/kernel/cpu/mce/severity.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dac4d64dfb2a..2235a7477436 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -300,13 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) copy_user = is_copy_from_user(regs); instrumentation_end(); - switch (fixup_type) { - case EX_TYPE_UACCESS: - if (!copy_user) - return IN_KERNEL; - m->kflags |= MCE_IN_KERNEL_COPYIN; - fallthrough; + if (copy_user) { + m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; + return IN_KERNEL_RECOV; + } + switch (fixup_type) { case EX_TYPE_FAULT_MCE_SAFE: case EX_TYPE_DEFAULT_MCE_SAFE: m->kflags |= MCE_IN_KERNEL_RECOV; -- cgit v1.2.3 From d893aca973c315ee985e1f8220fcd239c0ab7d19 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Wed, 19 Mar 2025 14:23:37 +0200 Subject: x86/mm: restore early initialization of high_memory for 32-bits Kernel test robot reports the following crash on 32-bit system with HIGHMEM and DEBUG_VIRTUAL: [ 0.056128][ T0] kernel BUG at arch/x86/mm/physaddr.c:77! PANIC: early exception 0x06 IP 60:c116539d error 0 cr2 0x0 [ 0.056916][ T0] CPU: 0 UID: 0 PID: 0 Comm: swapper Not tainted 6.14.0-rc4-00010-ga4dbe5c71817 #1 [ 0.057570][ T0] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 [ 0.058299][ T0] EIP: __phys_addr (arch/x86/mm/physaddr.c:77) [ 0.058633][ T0] Code: 00 74 33 89 f0 e8 d3 8b 2e 00 89 c3 0f b6 d0 b8 58 bb 4b c5 31 c9 6a 00 e8 70 f5 15 00 83 c4 04 84 db 74 25 ff 05 78 de 5d c5 <0f> 0b b8 c8 91 ea c4 e8 e7 6e ea ff b8 58 bb 4b c5 31 d2 31 c9 6a All code [ 0.060017][ T0] EAX: 00000000 EBX: c61f7001 ECX: 00000000 EDX: 00000000 [ 0.060519][ T0] ESI: c61f7000 EDI: 061f7000 EBP: c4e31f04 ESP: c61f7000 [ 0.061016][ T0] DS: 007b ES: 007b FS: 0000 GS: 0000 SS: cff4 EFLAGS: 00210002 [ 0.061560][ T0] CR0: 80050033 CR2: 00000000 CR3: 059fc000 CR4: 00000090 [ 0.062060][ T0] Call Trace: [ 0.062288][ T0] ? show_regs (arch/x86/kernel/dumpstack.c:478) [ 0.062588][ T0] ? early_fixup_exception (arch/x86/include/asm/nospec-branch.h:595) [ 0.062968][ T0] ? early_idt_handler_common (arch/x86/kernel/head_32.S:352) [ 0.063360][ T0] ? __phys_addr (arch/x86/mm/physaddr.c:77) [ 0.063677][ T0] ? one_page_table_init (arch/x86/mm/init_32.c:100) [ 0.064037][ T0] ? page_table_range_init (arch/x86/mm/init_32.c:227) [ 0.064411][ T0] ? permanent_kmaps_init (include/linux/pgtable.h:191 include/linux/pgtable.h:196 arch/x86/mm/init_32.c:395) [ 0.064814][ T0] ? paging_init (arch/x86/mm/init_32.c:677) [ 0.065118][ T0] ? native_pagetable_init (arch/x86/mm/init_32.c:481) [ 0.065503][ T0] ? setup_arch (arch/x86/kernel/setup.c:1131) [ 0.065819][ T0] ? start_kernel (include/linux/jump_label.h:267 init/main.c:920) [ 0.066143][ T0] ? i386_start_kernel (arch/x86/kernel/head32.c:79) [ 0.066501][ T0] ? startup_32_smp (arch/x86/kernel/head_32.S:292) The crash happens because commit e120d1bc12da ("arch, mm: set high_memory in free_area_init()") moved initialization of high_memory after __vmalloc_start_set and with high_memory still set to 0 any address passes is_vmalloc_addr() check. Restore early initialization of high_memory on 32-bit systems in initmem_init(). Link: https://lkml.kernel.org/r/20250319122337.1538924-1-rppt@kernel.org Fixes: e120d1bc12da ("arch, mm: set high_memory in free_area_init()") Signed-off-by: Mike Rapoport (Microsoft) Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202503191442.112e954f-lkp@intel.com Cc: Andy Lutomirski Cc: Borislav Betkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleinxer Signed-off-by: Andrew Morton --- arch/x86/mm/init_32.c | 3 +++ arch/x86/mm/numa_32.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'arch') diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 95b2758b4e4d..f69d2436d780 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -626,6 +626,9 @@ void __init initmem_init(void) highstart_pfn = max_low_pfn; printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); + high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; +#else + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 442ef3facff0..65fda406e6f2 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -41,6 +41,9 @@ void __init initmem_init(void) highstart_pfn = max_low_pfn; printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); + high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; +#else + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif printk(KERN_NOTICE "%ldMB LOWMEM available.\n", pages_to_mb(max_low_pfn)); -- cgit v1.2.3