Re: [PATCH v3 1/3] riscv: Move kernel mapping to vmalloc zone
Hi Zong, Le 5/27/20 à 3:29 AM, Alex Ghiti a écrit : Le 5/27/20 à 2:05 AM, Zong Li a écrit : On Wed, May 27, 2020 at 1:06 AM Alex Ghiti wrote: Hi Zong, Le 5/26/20 à 5:43 AM, Zong Li a écrit : On Sun, May 24, 2020 at 4:54 PM Alexandre Ghiti wrote: This is a preparatory patch for relocatable kernel. The kernel used to be linked at PAGE_OFFSET address and used to be loaded physically at the beginning of the main memory. Therefore, we could use the linear mapping for the kernel mapping. But the relocated kernel base address will be different from PAGE_OFFSET and since in the linear mapping, two different virtual addresses cannot point to the same physical address, the kernel mapping needs to lie outside the linear mapping. In addition, because modules and BPF must be close to the kernel (inside +-2GB window), the kernel is placed at the end of the vmalloc zone minus 2GB, which leaves room for modules and BPF. The kernel could not be placed at the beginning of the vmalloc zone since other vmalloc allocations from the kernel could get all the +-2GB window around the kernel which would prevent new modules and BPF programs to be loaded. Signed-off-by: Alexandre Ghiti --- arch/riscv/boot/loader.lds.S | 3 +- arch/riscv/include/asm/page.h | 10 +- arch/riscv/include/asm/pgtable.h | 37 +--- arch/riscv/kernel/head.S | 3 +- arch/riscv/kernel/module.c | 4 +-- arch/riscv/kernel/vmlinux.lds.S | 3 +- arch/riscv/mm/init.c | 58 +--- arch/riscv/mm/physaddr.c | 2 +- 8 files changed, 87 insertions(+), 33 deletions(-) diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S index 47a5003c2e28..62d94696a19c 100644 --- a/arch/riscv/boot/loader.lds.S +++ b/arch/riscv/boot/loader.lds.S @@ -1,13 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include OUTPUT_ARCH(riscv) ENTRY(_start) SECTIONS { - . = PAGE_OFFSET; + . = KERNEL_LINK_ADDR; .payload : { *(.payload) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 2d50f76efe48..48bb09b6a9b7 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -90,18 +90,26 @@ typedef struct page *pgtable_t; #ifdef CONFIG_MMU extern unsigned long va_pa_offset; +extern unsigned long va_kernel_pa_offset; extern unsigned long pfn_base; #define ARCH_PFN_OFFSET (pfn_base) #else #define va_pa_offset 0 +#define va_kernel_pa_offset 0 #define ARCH_PFN_OFFSET (PAGE_OFFSET >> PAGE_SHIFT) #endif /* CONFIG_MMU */ extern unsigned long max_low_pfn; extern unsigned long min_low_pfn; +extern unsigned long kernel_virt_addr; #define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + va_pa_offset)) -#define __va_to_pa_nodebug(x) ((unsigned long)(x) - va_pa_offset) +#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - va_pa_offset) +#define kernel_mapping_va_to_pa(x) \ + ((unsigned long)(x) - va_kernel_pa_offset) +#define __va_to_pa_nodebug(x) \ + (((x) >= PAGE_OFFSET) ? \ + linear_mapping_va_to_pa(x) : kernel_mapping_va_to_pa(x)) #ifdef CONFIG_DEBUG_VIRTUAL extern phys_addr_t __virt_to_phys(unsigned long x); diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 35b60035b6b0..25213cfaf680 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -11,23 +11,29 @@ #include -#ifndef __ASSEMBLY__ - -/* Page Upper Directory not used in RISC-V */ -#include -#include -#include -#include - -#ifdef CONFIG_MMU +#ifndef CONFIG_MMU +#define KERNEL_VIRT_ADDR PAGE_OFFSET +#define KERNEL_LINK_ADDR PAGE_OFFSET +#else +/* + * Leave 2GB for modules and BPF that must lie within a 2GB range around + * the kernel. + */ +#define KERNEL_VIRT_ADDR (VMALLOC_END - SZ_2G + 1) +#define KERNEL_LINK_ADDR KERNEL_VIRT_ADDR #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) #define BPF_JIT_REGION_SIZE (SZ_128M) -#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) -#define BPF_JIT_REGION_END (VMALLOC_END) +#define BPF_JIT_REGION_START (kernel_virt_addr) +#define BPF_JIT_REGION_END (kernel_virt_addr + BPF_JIT_REGION_SIZE) It seems to have a potential risk here, the region of bpf is overlapping with kernel mapping, so if kernel size is bigger than 128MB, bpf region would be occupied and run out by kernel mapping. Is there the risk as I mentioned? Sorry I forgot to answer this one: I was confident that 128MB was large enough for kernel and BPF. But I see no reason to leave this risk so I'll change kernel_virt_addr for _end so BPF will have its 128MB reserved. Thanks ! Alex
Re: [PATCH v3 1/3] riscv: Move kernel mapping to vmalloc zone
Hi Alexandre, Thank you for the patch! Perhaps something to improve: [auto build test WARNING on powerpc/next] [also build test WARNING on linus/master v5.7-rc7 next-20200526] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system. BTW, we also suggest to use '--base' option to specify the base tree in git format-patch, please see https://stackoverflow.com/a/37406982] url: https://github.com/0day-ci/linux/commits/Alexandre-Ghiti/vmalloc-kernel-mapping-and-relocatable-kernel/20200524-170109 base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next config: riscv-allyesconfig (attached as .config) compiler: riscv64-linux-gcc (GCC) 9.3.0 reproduce (this is a W=1 build): wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross # save the attached .config to linux build tree COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=riscv If you fix the issue, kindly add following tag as appropriate Reported-by: kbuild test robot All warnings (new ones prefixed by >>, old ones prefixed by <<): >> arch/riscv/mm/init.c:383:6: warning: no previous prototype for >> 'create_kernel_page_table' [-Wmissing-prototypes] 383 | void create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size) | ^~~~ vim +/create_kernel_page_table +383 arch/riscv/mm/init.c 382 > 383 void create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size) 384 { 385 uintptr_t va, end_va; 386 387 end_va = kernel_virt_addr + load_sz; 388 for (va = kernel_virt_addr; va < end_va; va += map_size) 389 create_pgd_mapping(pgdir, va, 390 load_pa + (va - kernel_virt_addr), 391 map_size, PAGE_KERNEL_EXEC); 392 } 393 --- 0-DAY CI Kernel Test Service, Intel Corporation https://lists.01.org/hyperkitty/list/kbuild-...@lists.01.org .config.gz Description: application/gzip
Re: [PATCH v3 1/3] riscv: Move kernel mapping to vmalloc zone
Le 5/27/20 à 2:05 AM, Zong Li a écrit : On Wed, May 27, 2020 at 1:06 AM Alex Ghiti wrote: Hi Zong, Le 5/26/20 à 5:43 AM, Zong Li a écrit : On Sun, May 24, 2020 at 4:54 PM Alexandre Ghiti wrote: This is a preparatory patch for relocatable kernel. The kernel used to be linked at PAGE_OFFSET address and used to be loaded physically at the beginning of the main memory. Therefore, we could use the linear mapping for the kernel mapping. But the relocated kernel base address will be different from PAGE_OFFSET and since in the linear mapping, two different virtual addresses cannot point to the same physical address, the kernel mapping needs to lie outside the linear mapping. In addition, because modules and BPF must be close to the kernel (inside +-2GB window), the kernel is placed at the end of the vmalloc zone minus 2GB, which leaves room for modules and BPF. The kernel could not be placed at the beginning of the vmalloc zone since other vmalloc allocations from the kernel could get all the +-2GB window around the kernel which would prevent new modules and BPF programs to be loaded. Signed-off-by: Alexandre Ghiti --- arch/riscv/boot/loader.lds.S | 3 +- arch/riscv/include/asm/page.h| 10 +- arch/riscv/include/asm/pgtable.h | 37 +--- arch/riscv/kernel/head.S | 3 +- arch/riscv/kernel/module.c | 4 +-- arch/riscv/kernel/vmlinux.lds.S | 3 +- arch/riscv/mm/init.c | 58 +--- arch/riscv/mm/physaddr.c | 2 +- 8 files changed, 87 insertions(+), 33 deletions(-) diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S index 47a5003c2e28..62d94696a19c 100644 --- a/arch/riscv/boot/loader.lds.S +++ b/arch/riscv/boot/loader.lds.S @@ -1,13 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include OUTPUT_ARCH(riscv) ENTRY(_start) SECTIONS { - . = PAGE_OFFSET; + . = KERNEL_LINK_ADDR; .payload : { *(.payload) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 2d50f76efe48..48bb09b6a9b7 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -90,18 +90,26 @@ typedef struct page *pgtable_t; #ifdef CONFIG_MMU extern unsigned long va_pa_offset; +extern unsigned long va_kernel_pa_offset; extern unsigned long pfn_base; #define ARCH_PFN_OFFSET(pfn_base) #else #define va_pa_offset 0 +#define va_kernel_pa_offset0 #define ARCH_PFN_OFFSET(PAGE_OFFSET >> PAGE_SHIFT) #endif /* CONFIG_MMU */ extern unsigned long max_low_pfn; extern unsigned long min_low_pfn; +extern unsigned long kernel_virt_addr; #define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + va_pa_offset)) -#define __va_to_pa_nodebug(x) ((unsigned long)(x) - va_pa_offset) +#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - va_pa_offset) +#define kernel_mapping_va_to_pa(x) \ + ((unsigned long)(x) - va_kernel_pa_offset) +#define __va_to_pa_nodebug(x) \ + (((x) >= PAGE_OFFSET) ? \ + linear_mapping_va_to_pa(x) : kernel_mapping_va_to_pa(x)) #ifdef CONFIG_DEBUG_VIRTUAL extern phys_addr_t __virt_to_phys(unsigned long x); diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 35b60035b6b0..25213cfaf680 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -11,23 +11,29 @@ #include -#ifndef __ASSEMBLY__ - -/* Page Upper Directory not used in RISC-V */ -#include -#include -#include -#include - -#ifdef CONFIG_MMU +#ifndef CONFIG_MMU +#define KERNEL_VIRT_ADDR PAGE_OFFSET +#define KERNEL_LINK_ADDR PAGE_OFFSET +#else +/* + * Leave 2GB for modules and BPF that must lie within a 2GB range around + * the kernel. + */ +#define KERNEL_VIRT_ADDR (VMALLOC_END - SZ_2G + 1) +#define KERNEL_LINK_ADDR KERNEL_VIRT_ADDR #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START(PAGE_OFFSET - VMALLOC_SIZE) #define BPF_JIT_REGION_SIZE(SZ_128M) -#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) -#define BPF_JIT_REGION_END (VMALLOC_END) +#define BPF_JIT_REGION_START (kernel_virt_addr) +#define BPF_JIT_REGION_END (kernel_virt_addr + BPF_JIT_REGION_SIZE) It seems to have a potential risk here, the region of bpf is overlapping with kernel mapping, so if kernel size is bigger than 128MB, bpf region would be occupied and run out by kernel mapping. Is there the risk as I mentioned? Sorry I forgot to answer this one: I was confident that 128MB was large enough for kernel and BPF. But I see no reason to leave this risk so I'll change kernel_virt_addr for _end so BPF will have its 128MB reserved. Thanks ! Alex + +#ifdef CONFIG_64BIT +#define VMALLOC_MODULE_START BPF_JIT_REGION_END
Re: [PATCH v3 1/3] riscv: Move kernel mapping to vmalloc zone
On Wed, May 27, 2020 at 1:06 AM Alex Ghiti wrote: > > Hi Zong, > > Le 5/26/20 à 5:43 AM, Zong Li a écrit : > > On Sun, May 24, 2020 at 4:54 PM Alexandre Ghiti wrote: > >> This is a preparatory patch for relocatable kernel. > >> > >> The kernel used to be linked at PAGE_OFFSET address and used to be loaded > >> physically at the beginning of the main memory. Therefore, we could use > >> the linear mapping for the kernel mapping. > >> > >> But the relocated kernel base address will be different from PAGE_OFFSET > >> and since in the linear mapping, two different virtual addresses cannot > >> point to the same physical address, the kernel mapping needs to lie outside > >> the linear mapping. > >> > >> In addition, because modules and BPF must be close to the kernel (inside > >> +-2GB window), the kernel is placed at the end of the vmalloc zone minus > >> 2GB, which leaves room for modules and BPF. The kernel could not be > >> placed at the beginning of the vmalloc zone since other vmalloc > >> allocations from the kernel could get all the +-2GB window around the > >> kernel which would prevent new modules and BPF programs to be loaded. > >> > >> Signed-off-by: Alexandre Ghiti > >> --- > >> arch/riscv/boot/loader.lds.S | 3 +- > >> arch/riscv/include/asm/page.h| 10 +- > >> arch/riscv/include/asm/pgtable.h | 37 +--- > >> arch/riscv/kernel/head.S | 3 +- > >> arch/riscv/kernel/module.c | 4 +-- > >> arch/riscv/kernel/vmlinux.lds.S | 3 +- > >> arch/riscv/mm/init.c | 58 +--- > >> arch/riscv/mm/physaddr.c | 2 +- > >> 8 files changed, 87 insertions(+), 33 deletions(-) > >> > >> diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S > >> index 47a5003c2e28..62d94696a19c 100644 > >> --- a/arch/riscv/boot/loader.lds.S > >> +++ b/arch/riscv/boot/loader.lds.S > >> @@ -1,13 +1,14 @@ > >> /* SPDX-License-Identifier: GPL-2.0 */ > >> > >> #include > >> +#include > >> > >> OUTPUT_ARCH(riscv) > >> ENTRY(_start) > >> > >> SECTIONS > >> { > >> - . = PAGE_OFFSET; > >> + . = KERNEL_LINK_ADDR; > >> > >> .payload : { > >> *(.payload) > >> diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h > >> index 2d50f76efe48..48bb09b6a9b7 100644 > >> --- a/arch/riscv/include/asm/page.h > >> +++ b/arch/riscv/include/asm/page.h > >> @@ -90,18 +90,26 @@ typedef struct page *pgtable_t; > >> > >> #ifdef CONFIG_MMU > >> extern unsigned long va_pa_offset; > >> +extern unsigned long va_kernel_pa_offset; > >> extern unsigned long pfn_base; > >> #define ARCH_PFN_OFFSET(pfn_base) > >> #else > >> #define va_pa_offset 0 > >> +#define va_kernel_pa_offset0 > >> #define ARCH_PFN_OFFSET(PAGE_OFFSET >> PAGE_SHIFT) > >> #endif /* CONFIG_MMU */ > >> > >> extern unsigned long max_low_pfn; > >> extern unsigned long min_low_pfn; > >> +extern unsigned long kernel_virt_addr; > >> > >> #define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + > >> va_pa_offset)) > >> -#define __va_to_pa_nodebug(x) ((unsigned long)(x) - va_pa_offset) > >> +#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - va_pa_offset) > >> +#define kernel_mapping_va_to_pa(x) \ > >> + ((unsigned long)(x) - va_kernel_pa_offset) > >> +#define __va_to_pa_nodebug(x) \ > >> + (((x) >= PAGE_OFFSET) ? \ > >> + linear_mapping_va_to_pa(x) : kernel_mapping_va_to_pa(x)) > >> > >> #ifdef CONFIG_DEBUG_VIRTUAL > >> extern phys_addr_t __virt_to_phys(unsigned long x); > >> diff --git a/arch/riscv/include/asm/pgtable.h > >> b/arch/riscv/include/asm/pgtable.h > >> index 35b60035b6b0..25213cfaf680 100644 > >> --- a/arch/riscv/include/asm/pgtable.h > >> +++ b/arch/riscv/include/asm/pgtable.h > >> @@ -11,23 +11,29 @@ > >> > >> #include > >> > >> -#ifndef __ASSEMBLY__ > >> - > >> -/* Page Upper Directory not used in RISC-V */ > >> -#include > >> -#include > >> -#include > >> -#include > >> - > >> -#ifdef CONFIG_MMU > >> +#ifndef CONFIG_MMU > >> +#define KERNEL_VIRT_ADDR PAGE_OFFSET > >> +#define KERNEL_LINK_ADDR PAGE_OFFSET > >> +#else > >> +/* > >> + * Leave 2GB for modules and BPF that must lie within a 2GB range around > >> + * the kernel. > >> + */ > >> +#define KERNEL_VIRT_ADDR (VMALLOC_END - SZ_2G + 1) > >> +#define KERNEL_LINK_ADDR KERNEL_VIRT_ADDR > >> > >> #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) > >> #define VMALLOC_END (PAGE_OFFSET - 1) > >> #define VMALLOC_START(PAGE_OFFSET - VMALLOC_SIZE) > >> > >> #define BPF_JIT_REGION_SIZE(SZ_128M) > >> -#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) > >> -#define BPF_JIT_REGION_END (VMALLOC_END) > >> +#define BPF_JIT_REGION_START (kernel_virt_addr) > >> +#define BPF_JIT_REGION_END (kernel_virt_addr + BPF_JIT_REGION_SIZE) > > It seems to have a
Re: [PATCH v3 1/3] riscv: Move kernel mapping to vmalloc zone
Hi Zong, Le 5/26/20 à 5:43 AM, Zong Li a écrit : On Sun, May 24, 2020 at 4:54 PM Alexandre Ghiti wrote: This is a preparatory patch for relocatable kernel. The kernel used to be linked at PAGE_OFFSET address and used to be loaded physically at the beginning of the main memory. Therefore, we could use the linear mapping for the kernel mapping. But the relocated kernel base address will be different from PAGE_OFFSET and since in the linear mapping, two different virtual addresses cannot point to the same physical address, the kernel mapping needs to lie outside the linear mapping. In addition, because modules and BPF must be close to the kernel (inside +-2GB window), the kernel is placed at the end of the vmalloc zone minus 2GB, which leaves room for modules and BPF. The kernel could not be placed at the beginning of the vmalloc zone since other vmalloc allocations from the kernel could get all the +-2GB window around the kernel which would prevent new modules and BPF programs to be loaded. Signed-off-by: Alexandre Ghiti --- arch/riscv/boot/loader.lds.S | 3 +- arch/riscv/include/asm/page.h| 10 +- arch/riscv/include/asm/pgtable.h | 37 +--- arch/riscv/kernel/head.S | 3 +- arch/riscv/kernel/module.c | 4 +-- arch/riscv/kernel/vmlinux.lds.S | 3 +- arch/riscv/mm/init.c | 58 +--- arch/riscv/mm/physaddr.c | 2 +- 8 files changed, 87 insertions(+), 33 deletions(-) diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S index 47a5003c2e28..62d94696a19c 100644 --- a/arch/riscv/boot/loader.lds.S +++ b/arch/riscv/boot/loader.lds.S @@ -1,13 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include OUTPUT_ARCH(riscv) ENTRY(_start) SECTIONS { - . = PAGE_OFFSET; + . = KERNEL_LINK_ADDR; .payload : { *(.payload) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 2d50f76efe48..48bb09b6a9b7 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -90,18 +90,26 @@ typedef struct page *pgtable_t; #ifdef CONFIG_MMU extern unsigned long va_pa_offset; +extern unsigned long va_kernel_pa_offset; extern unsigned long pfn_base; #define ARCH_PFN_OFFSET(pfn_base) #else #define va_pa_offset 0 +#define va_kernel_pa_offset0 #define ARCH_PFN_OFFSET(PAGE_OFFSET >> PAGE_SHIFT) #endif /* CONFIG_MMU */ extern unsigned long max_low_pfn; extern unsigned long min_low_pfn; +extern unsigned long kernel_virt_addr; #define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + va_pa_offset)) -#define __va_to_pa_nodebug(x) ((unsigned long)(x) - va_pa_offset) +#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - va_pa_offset) +#define kernel_mapping_va_to_pa(x) \ + ((unsigned long)(x) - va_kernel_pa_offset) +#define __va_to_pa_nodebug(x) \ + (((x) >= PAGE_OFFSET) ? \ + linear_mapping_va_to_pa(x) : kernel_mapping_va_to_pa(x)) #ifdef CONFIG_DEBUG_VIRTUAL extern phys_addr_t __virt_to_phys(unsigned long x); diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 35b60035b6b0..25213cfaf680 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -11,23 +11,29 @@ #include -#ifndef __ASSEMBLY__ - -/* Page Upper Directory not used in RISC-V */ -#include -#include -#include -#include - -#ifdef CONFIG_MMU +#ifndef CONFIG_MMU +#define KERNEL_VIRT_ADDR PAGE_OFFSET +#define KERNEL_LINK_ADDR PAGE_OFFSET +#else +/* + * Leave 2GB for modules and BPF that must lie within a 2GB range around + * the kernel. + */ +#define KERNEL_VIRT_ADDR (VMALLOC_END - SZ_2G + 1) +#define KERNEL_LINK_ADDR KERNEL_VIRT_ADDR #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START(PAGE_OFFSET - VMALLOC_SIZE) #define BPF_JIT_REGION_SIZE(SZ_128M) -#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) -#define BPF_JIT_REGION_END (VMALLOC_END) +#define BPF_JIT_REGION_START (kernel_virt_addr) +#define BPF_JIT_REGION_END (kernel_virt_addr + BPF_JIT_REGION_SIZE) It seems to have a potential risk here, the region of bpf is overlapping with kernel mapping, so if kernel size is bigger than 128MB, bpf region would be occupied and run out by kernel mapping. + +#ifdef CONFIG_64BIT +#define VMALLOC_MODULE_START BPF_JIT_REGION_END +#define VMALLOC_MODULE_END VMALLOC_END +#endif Although kernel_virt_addr is a fixed address now, I think it could be changed for the purpose of relocatable or KASLR, so if kernel_virt_addr is moved to far from VMALLOC_END than 2G, the region of module would be too big. Yes you're right, that's wrong to allow modules to lie outside the 2G window, thanks for noticing. In addition, the region
Re: [PATCH v3 1/3] riscv: Move kernel mapping to vmalloc zone
On Sun, May 24, 2020 at 4:54 PM Alexandre Ghiti wrote: > > This is a preparatory patch for relocatable kernel. > > The kernel used to be linked at PAGE_OFFSET address and used to be loaded > physically at the beginning of the main memory. Therefore, we could use > the linear mapping for the kernel mapping. > > But the relocated kernel base address will be different from PAGE_OFFSET > and since in the linear mapping, two different virtual addresses cannot > point to the same physical address, the kernel mapping needs to lie outside > the linear mapping. > > In addition, because modules and BPF must be close to the kernel (inside > +-2GB window), the kernel is placed at the end of the vmalloc zone minus > 2GB, which leaves room for modules and BPF. The kernel could not be > placed at the beginning of the vmalloc zone since other vmalloc > allocations from the kernel could get all the +-2GB window around the > kernel which would prevent new modules and BPF programs to be loaded. > > Signed-off-by: Alexandre Ghiti > --- > arch/riscv/boot/loader.lds.S | 3 +- > arch/riscv/include/asm/page.h| 10 +- > arch/riscv/include/asm/pgtable.h | 37 +--- > arch/riscv/kernel/head.S | 3 +- > arch/riscv/kernel/module.c | 4 +-- > arch/riscv/kernel/vmlinux.lds.S | 3 +- > arch/riscv/mm/init.c | 58 +--- > arch/riscv/mm/physaddr.c | 2 +- > 8 files changed, 87 insertions(+), 33 deletions(-) > > diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S > index 47a5003c2e28..62d94696a19c 100644 > --- a/arch/riscv/boot/loader.lds.S > +++ b/arch/riscv/boot/loader.lds.S > @@ -1,13 +1,14 @@ > /* SPDX-License-Identifier: GPL-2.0 */ > > #include > +#include > > OUTPUT_ARCH(riscv) > ENTRY(_start) > > SECTIONS > { > - . = PAGE_OFFSET; > + . = KERNEL_LINK_ADDR; > > .payload : { > *(.payload) > diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h > index 2d50f76efe48..48bb09b6a9b7 100644 > --- a/arch/riscv/include/asm/page.h > +++ b/arch/riscv/include/asm/page.h > @@ -90,18 +90,26 @@ typedef struct page *pgtable_t; > > #ifdef CONFIG_MMU > extern unsigned long va_pa_offset; > +extern unsigned long va_kernel_pa_offset; > extern unsigned long pfn_base; > #define ARCH_PFN_OFFSET(pfn_base) > #else > #define va_pa_offset 0 > +#define va_kernel_pa_offset0 > #define ARCH_PFN_OFFSET(PAGE_OFFSET >> PAGE_SHIFT) > #endif /* CONFIG_MMU */ > > extern unsigned long max_low_pfn; > extern unsigned long min_low_pfn; > +extern unsigned long kernel_virt_addr; > > #define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + va_pa_offset)) > -#define __va_to_pa_nodebug(x) ((unsigned long)(x) - va_pa_offset) > +#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - va_pa_offset) > +#define kernel_mapping_va_to_pa(x) \ > + ((unsigned long)(x) - va_kernel_pa_offset) > +#define __va_to_pa_nodebug(x) \ > + (((x) >= PAGE_OFFSET) ? \ > + linear_mapping_va_to_pa(x) : kernel_mapping_va_to_pa(x)) > > #ifdef CONFIG_DEBUG_VIRTUAL > extern phys_addr_t __virt_to_phys(unsigned long x); > diff --git a/arch/riscv/include/asm/pgtable.h > b/arch/riscv/include/asm/pgtable.h > index 35b60035b6b0..25213cfaf680 100644 > --- a/arch/riscv/include/asm/pgtable.h > +++ b/arch/riscv/include/asm/pgtable.h > @@ -11,23 +11,29 @@ > > #include > > -#ifndef __ASSEMBLY__ > - > -/* Page Upper Directory not used in RISC-V */ > -#include > -#include > -#include > -#include > - > -#ifdef CONFIG_MMU > +#ifndef CONFIG_MMU > +#define KERNEL_VIRT_ADDR PAGE_OFFSET > +#define KERNEL_LINK_ADDR PAGE_OFFSET > +#else > +/* > + * Leave 2GB for modules and BPF that must lie within a 2GB range around > + * the kernel. > + */ > +#define KERNEL_VIRT_ADDR (VMALLOC_END - SZ_2G + 1) > +#define KERNEL_LINK_ADDR KERNEL_VIRT_ADDR > > #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) > #define VMALLOC_END (PAGE_OFFSET - 1) > #define VMALLOC_START(PAGE_OFFSET - VMALLOC_SIZE) > > #define BPF_JIT_REGION_SIZE(SZ_128M) > -#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) > -#define BPF_JIT_REGION_END (VMALLOC_END) > +#define BPF_JIT_REGION_START (kernel_virt_addr) > +#define BPF_JIT_REGION_END (kernel_virt_addr + BPF_JIT_REGION_SIZE) It seems to have a potential risk here, the region of bpf is overlapping with kernel mapping, so if kernel size is bigger than 128MB, bpf region would be occupied and run out by kernel mapping. > + > +#ifdef CONFIG_64BIT > +#define VMALLOC_MODULE_START BPF_JIT_REGION_END > +#define VMALLOC_MODULE_END VMALLOC_END > +#endif > Although kernel_virt_addr is a fixed address now, I think it could be changed for the purpose of relocatable or KASLR, so if kernel_virt_addr is moved to far from VMALLOC_END than 2G, the region of module
[PATCH v3 1/3] riscv: Move kernel mapping to vmalloc zone
This is a preparatory patch for relocatable kernel. The kernel used to be linked at PAGE_OFFSET address and used to be loaded physically at the beginning of the main memory. Therefore, we could use the linear mapping for the kernel mapping. But the relocated kernel base address will be different from PAGE_OFFSET and since in the linear mapping, two different virtual addresses cannot point to the same physical address, the kernel mapping needs to lie outside the linear mapping. In addition, because modules and BPF must be close to the kernel (inside +-2GB window), the kernel is placed at the end of the vmalloc zone minus 2GB, which leaves room for modules and BPF. The kernel could not be placed at the beginning of the vmalloc zone since other vmalloc allocations from the kernel could get all the +-2GB window around the kernel which would prevent new modules and BPF programs to be loaded. Signed-off-by: Alexandre Ghiti --- arch/riscv/boot/loader.lds.S | 3 +- arch/riscv/include/asm/page.h| 10 +- arch/riscv/include/asm/pgtable.h | 37 +--- arch/riscv/kernel/head.S | 3 +- arch/riscv/kernel/module.c | 4 +-- arch/riscv/kernel/vmlinux.lds.S | 3 +- arch/riscv/mm/init.c | 58 +--- arch/riscv/mm/physaddr.c | 2 +- 8 files changed, 87 insertions(+), 33 deletions(-) diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S index 47a5003c2e28..62d94696a19c 100644 --- a/arch/riscv/boot/loader.lds.S +++ b/arch/riscv/boot/loader.lds.S @@ -1,13 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include OUTPUT_ARCH(riscv) ENTRY(_start) SECTIONS { - . = PAGE_OFFSET; + . = KERNEL_LINK_ADDR; .payload : { *(.payload) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 2d50f76efe48..48bb09b6a9b7 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -90,18 +90,26 @@ typedef struct page *pgtable_t; #ifdef CONFIG_MMU extern unsigned long va_pa_offset; +extern unsigned long va_kernel_pa_offset; extern unsigned long pfn_base; #define ARCH_PFN_OFFSET(pfn_base) #else #define va_pa_offset 0 +#define va_kernel_pa_offset0 #define ARCH_PFN_OFFSET(PAGE_OFFSET >> PAGE_SHIFT) #endif /* CONFIG_MMU */ extern unsigned long max_low_pfn; extern unsigned long min_low_pfn; +extern unsigned long kernel_virt_addr; #define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + va_pa_offset)) -#define __va_to_pa_nodebug(x) ((unsigned long)(x) - va_pa_offset) +#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - va_pa_offset) +#define kernel_mapping_va_to_pa(x) \ + ((unsigned long)(x) - va_kernel_pa_offset) +#define __va_to_pa_nodebug(x) \ + (((x) >= PAGE_OFFSET) ? \ + linear_mapping_va_to_pa(x) : kernel_mapping_va_to_pa(x)) #ifdef CONFIG_DEBUG_VIRTUAL extern phys_addr_t __virt_to_phys(unsigned long x); diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 35b60035b6b0..25213cfaf680 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -11,23 +11,29 @@ #include -#ifndef __ASSEMBLY__ - -/* Page Upper Directory not used in RISC-V */ -#include -#include -#include -#include - -#ifdef CONFIG_MMU +#ifndef CONFIG_MMU +#define KERNEL_VIRT_ADDR PAGE_OFFSET +#define KERNEL_LINK_ADDR PAGE_OFFSET +#else +/* + * Leave 2GB for modules and BPF that must lie within a 2GB range around + * the kernel. + */ +#define KERNEL_VIRT_ADDR (VMALLOC_END - SZ_2G + 1) +#define KERNEL_LINK_ADDR KERNEL_VIRT_ADDR #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START(PAGE_OFFSET - VMALLOC_SIZE) #define BPF_JIT_REGION_SIZE(SZ_128M) -#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) -#define BPF_JIT_REGION_END (VMALLOC_END) +#define BPF_JIT_REGION_START (kernel_virt_addr) +#define BPF_JIT_REGION_END (kernel_virt_addr + BPF_JIT_REGION_SIZE) + +#ifdef CONFIG_64BIT +#define VMALLOC_MODULE_START BPF_JIT_REGION_END +#define VMALLOC_MODULE_END VMALLOC_END +#endif /* * Roughly size the vmemmap space to be large enough to fit enough @@ -57,9 +63,16 @@ #define FIXADDR_SIZE PGDIR_SIZE #endif #define FIXADDR_START(FIXADDR_TOP - FIXADDR_SIZE) - #endif +#ifndef __ASSEMBLY__ + +/* Page Upper Directory not used in RISC-V */ +#include +#include +#include +#include + #ifdef CONFIG_64BIT #include #else diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 98a406474e7d..8f5bb7731327 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -49,7 +49,8 @@ ENTRY(_start) #ifdef CONFIG_MMU relocate: /* Relocate return address */ - li a1, PAGE_OFFSET + la a1,