riscv: mm: execute local TLB flush after populating vmemmap
PATCH v6 1/1 riscv: mm: execute local TLB flush after populating vmemmap
The spare_init() calls memmap_populate() many times to create VA to PA mapping for the VMEMMAP area, where all "struct page" are located once CONFIG_SPARSEMEM_VMEMMAP is defined. These "struct page" are later initialized in the zone_sizes_init() function. However, during this process, no sfence.vma instruction is executed for this VMEMMAP area. This omission may cause the hart to fail to perform page table walk because some data related to the address translation is invisible to the hart. To solve this issue, the local_flush_tlb_kernel_range() is called right after the sparse_init() to execute a sfence.vma instruction for this VMEMMAP area, ensuring that all data related to the address translation is visible to the hart.
--- arch/riscv/include/asm/tlbflush.h | 2 ++ arch/riscv/mm/init.c | 5 +++++ arch/riscv/mm/tlbflush.c | 6 ++++++ 3 files changed, 13 insertions(+)
arch/riscv/include/asm/tlbflush.h +2 -0
@@ -46,6 +46,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end);void flush_pmd_tlb_range (struct vm_area_struct *vma,unsigned long start,unsigned long end);#endif +void local_flush_tlb_kernel_range (unsigned long start,unsigned long end);#else /* CONFIG_SMP && CONFIG_MMU */ #define flush_tlb_all () local_flush_tlb_all()
@@ -66,6 +67,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,#define flush_tlb_mm (mm) flush_tlb_all()#define flush_tlb_mm_range (mm, start, end, page_size) flush_tlb_all() +#define local_flush_tlb_kernel_range (start, end) flush_tlb_all()#endif /* !CONFIG_SMP || !CONFIG_MMU */ #endif /* _ASM_RISCV_TLBFLUSH_H */
arch/riscv/mm/init.c +5 -0
@@ -1377,6 +1377,10 @@ void __init misc_mem_init(void)early_memtest (min_low_pfn <<PAGE_SHIFT , max_low_pfn <<PAGE_SHIFT );arch_numa_init ();sparse_init (); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* The entire VMEMMAP region has been populated. Flush TLB for this region */ +local_flush_tlb_kernel_range (VMEMMAP_START ,VMEMMAP_END ); +#endif zone_sizes_init ();arch_reserve_crashkernel ();memblock_dump_all ();
@@ -1386,6 +1390,7 @@ void __init misc_mem_init(void)int __meminit vmemmap_populate (unsigned long start,unsigned long end,int node,struct vmem_altmap *altmap) { +/* Defer the required TLB flush until the entire VMEMMAP region has been populated */ return vmemmap_populate_basepages (start, end, node,NULL ); }#endif
arch/riscv/mm/tlbflush.c +6 -0
@@ -193,6 +193,12 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)__flush_tlb_range (NULL , start, end - start,PAGE_SIZE ); } +/* Flush a range of kernel pages without broadcasting */ +void local_flush_tlb_kernel_range (unsigned long start,unsigned long end) +{ +local_flush_tlb_range_asid (start, end - start,PAGE_SIZE ,FLUSH_TLB_NO_ASID ); +} +#ifdef CONFIG_TRANSPARENT_HUGEPAGE void flush_pmd_tlb_range (struct vm_area_struct *vma,unsigned long start,unsigned long end)
Signature · 7 lines
2.34.1 _______________________________________________ linux-riscv mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-riscv
Hi Vincent,
Thank you for the patch.
Quoted 13 lines · Vincent Chen
The
spare_init()callsmemmap_populate()many times to create VA to PA mapping for the VMEMMAP area, where all "struct page" are located onceCONFIG_SPARSEMEM_VMEMMAPis defined. These "struct page" are later initialized in thezone_sizes_init()function. However, during this process, no sfence.vma instruction is executed for this VMEMMAP area. This omission may cause the hart to fail to perform page table walk because some data related to the address translation is invisible to the hart. To solve this issue, thelocal_flush_tlb_kernel_range()is called right after thesparse_init()to execute a sfence.vma instruction for this VMEMMAP area, ensuring that all data related to the address translation is visible to the hart.
Quoted 9 lines
Fixes d95f1a542c3d ("RISC-V: Implement sparsemem")Signed-off-by Vincent Chen <[email protected]>Reviewed-by Alexandre Ghiti <[email protected]>--- arch/riscv/include/asm/tlbflush.h | 2 ++ arch/riscv/mm/init.c | 5 +++++ arch/riscv/mm/tlbflush.c | 6 ++++++ 3 files changed, 13 insertions(+)
I get below build issue with this patch applied:
arch/riscv/mm/tlbflush.c:207:6: error: redefinition of 'local_flush_tlb_kernel_range'
207 | void local_flush_tlb_kernel_range(unsigned long start,
unsigned long end)
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
arch/riscv/mm/tlbflush.c:69:6: note: previous definition of 'local_flush_tlb_kernel_range' with type 'void(long unsigned int, long unsigned int)'
69 | void local_flush_tlb_kernel_range(unsigned long start,
unsigned long end)
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
make[4]: *** [scripts/Makefile.build:243: arch/riscv/mm/tlbflush.o] Error 1 make[4]: *** Waiting for unfinished jobs....
CC kernel/resource.o
make[3]: *** [scripts/Makefile.build:481: arch/riscv/mm] Error 2 make[3]: *** Waiting for unfinished jobs....
I have attached the defconfig file.
Cheers,
Prabhakar
Quoted 64 lines
arch/riscv/include/asm/tlbflush.h +2
-0@@ -46,6 +46,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end);void flush_pmd_tlb_range (struct vm_area_struct *vma,unsigned long start,unsigned long end);#endif +void local_flush_tlb_kernel_range (unsigned long start,unsigned long end);#else /* CONFIG_SMP && CONFIG_MMU */ #define flush_tlb_all () local_flush_tlb_all()@@ -66,6 +67,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,#define flush_tlb_mm (mm) flush_tlb_all()#define flush_tlb_mm_range (mm, start, end, page_size) flush_tlb_all() +#define local_flush_tlb_kernel_range (start, end) flush_tlb_all()#endif /* !CONFIG_SMP || !CONFIG_MMU */ #endif /* _ASM_RISCV_TLBFLUSH_H */ arch/riscv/mm/init.c +5
-0@@ -1377,6 +1377,10 @@ void __init misc_mem_init(void)early_memtest (min_low_pfn <<PAGE_SHIFT , max_low_pfn <<PAGE_SHIFT );arch_numa_init ();sparse_init (); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* The entire VMEMMAP region has been populated. Flush TLB for this region */ +local_flush_tlb_kernel_range (VMEMMAP_START ,VMEMMAP_END ); +#endif zone_sizes_init ();arch_reserve_crashkernel ();memblock_dump_all ();@@ -1386,6 +1390,7 @@ void __init misc_mem_init(void)int __meminit vmemmap_populate (unsigned long start,unsigned long end,int node,struct vmem_altmap *altmap) { +/* Defer the required TLB flush until the entire VMEMMAP region has been populated */ return vmemmap_populate_basepages (start, end, node,NULL ); }#endif arch/riscv/mm/tlbflush.c +6
-1@@ -193,6 +193,12 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)__flush_tlb_range (NULL , start, end - start,PAGE_SIZE ); } +/* Flush a range of kernel pages without broadcasting */ +void local_flush_tlb_kernel_range (unsigned long start,unsigned long end) +{ +local_flush_tlb_range_asid (start, end - start,PAGE_SIZE ,FLUSH_TLB_NO_ASID ); +} +#ifdef CONFIG_TRANSPARENT_HUGEPAGE void flush_pmd_tlb_range (struct vm_area_struct *vma,unsigned long start,unsigned long end) --2.34.1
Quoted 4 lines
_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
Hi Prabhakar,
Quoted 40 lines · Prabhakar
Hi Vincent,
Thank you for the patch.
Quoted 13 lines · Vincent Chen
The
spare_init()callsmemmap_populate()many times to create VA to PA mapping for the VMEMMAP area, where all "struct page" are located onceCONFIG_SPARSEMEM_VMEMMAPis defined. These "struct page" are later initialized in thezone_sizes_init()function. However, during this process, no sfence.vma instruction is executed for this VMEMMAP area. This omission may cause the hart to fail to perform page table walk because some data related to the address translation is invisible to the hart. To solve this issue, thelocal_flush_tlb_kernel_range()is called right after thesparse_init()to execute a sfence.vma instruction for this VMEMMAP area, ensuring that all data related to the address translation is visible to the hart.Quoted 9 lines
Fixes d95f1a542c3d ("RISC-V: Implement sparsemem")Signed-off-by Vincent Chen <[email protected]>Reviewed-by Alexandre Ghiti <[email protected]>--- arch/riscv/include/asm/tlbflush.h | 2 ++ arch/riscv/mm/init.c | 5 +++++ arch/riscv/mm/tlbflush.c | 6 ++++++ 3 files changed, 13 insertions(+)I get below build issue with this patch applied:
arch/riscv/mm/tlbflush.c:207:6: error: redefinition of 'local_flush_tlb_kernel_range'
207 | void local_flush_tlb_kernel_range(unsigned long start,
unsigned long end)| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
arch/riscv/mm/tlbflush.c:69:6: note: previous definition of 'local_flush_tlb_kernel_range' with type 'void(long unsigned int, long unsigned int)'
69 | void local_flush_tlb_kernel_range(unsigned long start,
unsigned long end)
Quoted 9 lines
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~make[4]: *** [
scripts/Makefile.build:243:arch/riscv/mm/tlbflush.o] Error 1 make[4]: *** Waiting for unfinished jobs....
CCkernel/resource.o
make[3]: *** [scripts/Makefile.build:481:arch/riscv/mm] Error 2 make[3]: *** Waiting for unfinished jobs....I have attached the defconfig file.
Indeed, we recently added the same function, you can find a rebased version of this patch on top of 6.8 here:
https://github.com/AlexGhiti/linux-riscv/commit/756d1871f58edac455773db0bb996f8d064a6b06
Quoted 67 lines
Cheers,
PrabhakarQuoted 64 lines
arch/riscv/include/asm/tlbflush.h +2
-0@@ -46,6 +46,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end);void flush_pmd_tlb_range (struct vm_area_struct *vma,unsigned long start,unsigned long end);#endif +void local_flush_tlb_kernel_range (unsigned long start,unsigned long end);#else /* CONFIG_SMP && CONFIG_MMU */ #define flush_tlb_all () local_flush_tlb_all()@@ -66,6 +67,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,#define flush_tlb_mm (mm) flush_tlb_all()#define flush_tlb_mm_range (mm, start, end, page_size) flush_tlb_all() +#define local_flush_tlb_kernel_range (start, end) flush_tlb_all()#endif /* !CONFIG_SMP || !CONFIG_MMU */ #endif /* _ASM_RISCV_TLBFLUSH_H */ arch/riscv/mm/init.c +5
-0@@ -1377,6 +1377,10 @@ void __init misc_mem_init(void)early_memtest (min_low_pfn <<PAGE_SHIFT , max_low_pfn <<PAGE_SHIFT );arch_numa_init ();sparse_init (); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +/* The entire VMEMMAP region has been populated. Flush TLB for this region */ +local_flush_tlb_kernel_range (VMEMMAP_START ,VMEMMAP_END ); +#endif zone_sizes_init ();arch_reserve_crashkernel ();memblock_dump_all ();@@ -1386,6 +1390,7 @@ void __init misc_mem_init(void)int __meminit vmemmap_populate (unsigned long start,unsigned long end,int node,struct vmem_altmap *altmap) { +/* Defer the required TLB flush until the entire VMEMMAP region has been populated */ return vmemmap_populate_basepages (start, end, node,NULL ); }#endif arch/riscv/mm/tlbflush.c +6
-1@@ -193,6 +193,12 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)__flush_tlb_range (NULL , start, end - start,PAGE_SIZE ); } +/* Flush a range of kernel pages without broadcasting */ +void local_flush_tlb_kernel_range (unsigned long start,unsigned long end) +{ +local_flush_tlb_range_asid (start, end - start,PAGE_SIZE ,FLUSH_TLB_NO_ASID ); +} +#ifdef CONFIG_TRANSPARENT_HUGEPAGE void flush_pmd_tlb_range (struct vm_area_struct *vma,unsigned long start,unsigned long end) --2.34.1
Quoted 4 lines
Quoted 4 lines
_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
Hi Alexandre,
Quoted 52 lines · Alexandre Ghiti
Hi Prabhakar,
Quoted 47 lines · Prabhakar
Hi Vincent,
Thank you for the patch.
Quoted 13 lines · Vincent Chen
The
spare_init()callsmemmap_populate()many times to create VA to PA mapping for the VMEMMAP area, where all "struct page" are located onceCONFIG_SPARSEMEM_VMEMMAPis defined. These "struct page" are later initialized in thezone_sizes_init()function. However, during this process, no sfence.vma instruction is executed for this VMEMMAP area. This omission may cause the hart to fail to perform page table walk because some data related to the address translation is invisible to the hart. To solve this issue, thelocal_flush_tlb_kernel_range()is called right after thesparse_init()to execute a sfence.vma instruction for this VMEMMAP area, ensuring that all data related to the address translation is visible to the hart.Quoted 9 lines
Fixes d95f1a542c3d ("RISC-V: Implement sparsemem")Signed-off-by Vincent Chen <[email protected]>Reviewed-by Alexandre Ghiti <[email protected]>--- arch/riscv/include/asm/tlbflush.h | 2 ++ arch/riscv/mm/init.c | 5 +++++ arch/riscv/mm/tlbflush.c | 6 ++++++ 3 files changed, 13 insertions(+)I get below build issue with this patch applied:
arch/riscv/mm/tlbflush.c:207:6: error: redefinition of 'local_flush_tlb_kernel_range'
207 | void local_flush_tlb_kernel_range(unsigned long start,
unsigned long end)| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
arch/riscv/mm/tlbflush.c:69:6: note: previous definition of 'local_flush_tlb_kernel_range' with type 'void(long unsigned int, long unsigned int)'
69 | void local_flush_tlb_kernel_range(unsigned long start,
unsigned long end)| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~make[4]: *** [
scripts/Makefile.build:243:arch/riscv/mm/tlbflush.o] Error 1 make[4]: *** Waiting for unfinished jobs....
CCkernel/resource.o
make[3]: *** [scripts/Makefile.build:481:arch/riscv/mm] Error 2 make[3]: *** Waiting for unfinished jobs....
Quoted 7 lines
Quoted 2 lines
I have attached the defconfig file.
Indeed, we recently added the same function, you can find a rebased version of this patch on top of 6.8 here:
https://github.com/AlexGhiti/linux-riscv/commit/756d1871f58edac455773db0bb996f8d064a6b06
Thanks for the pointer.
Cheers,
Prabhakar
_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
This patch was applied to riscv/linux.git (fixes) by Palmer Dabbelt <[email protected]>:
Hello:
This patch was applied to riscv/linux.git (fixes)
by Palmer Dabbelt <[email protected]>:
Quoted 12 lines · On Wed, 17 Jan 2024 22:03:33 +0800 you wrote:
The
spare_init()callsmemmap_populate()many times to create VA to PA mapping for the VMEMMAP area, where all "struct page" are located onceCONFIG_SPARSEMEM_VMEMMAPis defined. These "struct page" are later initialized in thezone_sizes_init()function. However, during this process, no sfence.vma instruction is executed for this VMEMMAP area. This omission may cause the hart to fail to perform page table walk because some data related to the address translation is invisible to the hart. To solve this issue, thelocal_flush_tlb_kernel_range()is called right after thesparse_init()to execute a sfence.vma instruction for this VMEMMAP area, ensuring that all data related to the address translation is visible to the hart.
Quoted 1 line
[...]
Here is the summary with links:
- [v6] riscv: mm: execute local TLB flush after populating vmemmap
https://git.kernel.org/riscv/c/d9807d60c145
You are awesome, thank you!
Signature · 9 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html _______________________________________________ linux-riscv mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-riscv