riscv: mm: Fix the out of bound issue of vmemmap address

commit f754f27e98f88428aaf6be6e00f5cbce97f62d4b upstream.

In sparse vmemmap model, the virtual address of vmemmap is calculated as:
((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)).
And the struct page's va can be calculated with an offset:
(vmemmap + (pfn)).

However, when initializing struct pages, kernel actually starts from the
first page from the same section that phys_ram_base belongs to. If the
first page's physical address is not (phys_ram_base >> PAGE_SHIFT), then
we get an va below VMEMMAP_START when calculating va for it's struct page.

For example, if phys_ram_base starts from 0x82000000 with pfn 0x82000, the
first page in the same section is actually pfn 0x80000. During
init_unavailable_range(), we will initialize struct page for pfn 0x80000
with virtual address ((struct page *)VMEMMAP_START - 0x2000), which is
below VMEMMAP_START as well as PCI_IO_END.

This commit fixes this bug by introducing a new variable
'vmemmap_start_pfn' which is aligned with memory section size and using
it to calculate vmemmap address instead of phys_ram_base.

Fixes: a11dd49dcb93 ("riscv: Sparse-Memory/vmemmap out-of-bounds fix")
Signed-off-by: Xu Lu <luxu.kernel@bytedance.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Link: https://lore.kernel.org/r/20241209122617.53341-1-luxu.kernel@bytedance.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Zhaoyang Li <lizy04@hust.edu.cn>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 86048c60f7002b152beba7d1718c1d227410badc..fd861ac47a890d608e8330a11627540d3b7d6eca 100644 (file)
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -115,6 +115,7 @@ struct kernel_mapping {
 
 extern struct kernel_mapping kernel_map;
 extern phys_addr_t phys_ram_base;
+extern unsigned long vmemmap_start_pfn;
 
 #define is_kernel_mapping(x)   \
        ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size))

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 7d1688f850c31f7cb840b79866a27aa8ddd2bf9d..bb19a643c5c2aae2b52fc24eb800c0b78a3aea62 100644 (file)
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -79,7 +79,7 @@
  * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel
  * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled.
  */
-#define vmemmap                ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT))
+#define vmemmap                ((struct page *)VMEMMAP_START - vmemmap_start_pfn)
 
 #define PCI_IO_SIZE      SZ_16M
 #define PCI_IO_END       VMEMMAP_START

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index ba2210b553f9cf5c59804024fb4d763d7097c2d1..72b3462babbf98649698cb4426c218262fb23aa3 100644 (file)
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -22,6 +22,7 @@
 #include <linux/hugetlb.h>
 
 #include <asm/fixmap.h>
+#include <asm/sparsemem.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/soc.h>
@@ -52,6 +53,13 @@ EXPORT_SYMBOL(pgtable_l5_enabled);
 phys_addr_t phys_ram_base __ro_after_init;
 EXPORT_SYMBOL(phys_ram_base);
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#define VMEMMAP_ADDR_ALIGN     (1ULL << SECTION_SIZE_BITS)
+
+unsigned long vmemmap_start_pfn __ro_after_init;
+EXPORT_SYMBOL(vmemmap_start_pfn);
+#endif
+
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
                                                        __page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
@@ -210,8 +218,12 @@ static void __init setup_bootmem(void)
        memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
        phys_ram_end = memblock_end_of_DRAM();
-       if (!IS_ENABLED(CONFIG_XIP_KERNEL))
+       if (!IS_ENABLED(CONFIG_XIP_KERNEL)) {
                phys_ram_base = memblock_start_of_DRAM();
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+               vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT;
+#endif
+}
        /*
         * Reserve physical address space that would be mapped to virtual
         * addresses greater than (void *)(-PAGE_SIZE) because:
@@ -946,6 +958,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
        kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
 
        phys_ram_base = CONFIG_PHYS_RAM_BASE;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+       vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT;
+#endif
        kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
        kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start);