From c67ddf59ac44adc60649730bf8347e37c516b001 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 15 May 2024 07:50:39 +0200 Subject: [PATCH 1/2] riscv: force PAGE_SIZE linear mapping if debug_pagealloc is enabled debug_pagealloc is a debug feature which clears the valid bit in page table entry for freed pages to detect illegal accesses to freed memory. For this feature to work, virtual mapping must have PAGE_SIZE resolution. (No, we cannot map with huge pages and split them only when needed; because pages can be allocated/freed in atomic context and page splitting cannot be done in atomic context) Force linear mapping to use small pages if debug_pagealloc is enabled. Note that it is not necessary to force the entire linear mapping, but only those that are given to memory allocator. Some parts of memory can keep using huge page mapping (for example, kernel's executable code). But these parts are minority, so keep it simple. This is just a debug feature, some extra overhead should be acceptable. Fixes: 5fde3db5eb02 ("riscv: add ARCH_SUPPORTS_DEBUG_PAGEALLOC support") Signed-off-by: Nam Cao Cc: stable@vger.kernel.org Reviewed-by: Alexandre Ghiti Link: https://lore.kernel.org/r/2e391fa6c6f9b3fcf1b41cefbace02ee4ab4bf59.1715750938.git.namcao@linutronix.de Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index fe8e159394d8..9020844f5189 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -668,6 +668,9 @@ void __init create_pgd_mapping(pgd_t *pgdp, static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va, phys_addr_t size) { + if (debug_pagealloc_enabled()) + return PAGE_SIZE; + if (pgtable_l5_enabled && !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) return P4D_SIZE; From fb1cf0878328fe75d47f0aed0a65b30126fcefc4 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 15 May 2024 07:50:40 +0200 Subject: [PATCH 2/2] riscv: rewrite __kernel_map_pages() to fix sleeping in invalid context __kernel_map_pages() is a debug function which clears the valid bit in page table entry for deallocated pages to detect illegal memory accesses to freed pages. This function set/clear the valid bit using __set_memory(). __set_memory() acquires init_mm's semaphore, and this operation may sleep. This is problematic, because __kernel_map_pages() can be called in atomic context, and thus is illegal to sleep. An example warning that this causes: BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1578 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd preempt_count: 2, expected: 0 CPU: 0 PID: 2 Comm: kthreadd Not tainted 6.9.0-g1d4c6d784ef6 #37 Hardware name: riscv-virtio,qemu (DT) Call Trace: [] dump_backtrace+0x1c/0x24 [] show_stack+0x2c/0x38 [] dump_stack_lvl+0x5a/0x72 [] dump_stack+0x14/0x1c [] __might_resched+0x104/0x10e [] __might_sleep+0x3e/0x62 [] down_write+0x20/0x72 [] __set_memory+0x82/0x2fa [] __kernel_map_pages+0x5a/0xd4 [] __alloc_pages_bulk+0x3b2/0x43a [] __vmalloc_node_range+0x196/0x6ba [] copy_process+0x72c/0x17ec [] kernel_clone+0x60/0x2fe [] kernel_thread+0x82/0xa0 [] kthreadd+0x14a/0x1be [] ret_from_fork+0xe/0x1c Rewrite this function with apply_to_existing_page_range(). It is fine to not have any locking, because __kernel_map_pages() works with pages being allocated/deallocated and those pages are not changed by anyone else in the meantime. Fixes: 5fde3db5eb02 ("riscv: add ARCH_SUPPORTS_DEBUG_PAGEALLOC support") Signed-off-by: Nam Cao Cc: stable@vger.kernel.org Reviewed-by: Alexandre Ghiti Link: https://lore.kernel.org/r/1289ecba9606a19917bc12b6c27da8aa23e1e5ae.1715750938.git.namcao@linutronix.de Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/pageattr.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 410056a50aa9..271d01a5ba4d 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -387,17 +387,33 @@ int set_direct_map_default_noflush(struct page *page) } #ifdef CONFIG_DEBUG_PAGEALLOC +static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data) +{ + int enable = *(int *)data; + + unsigned long val = pte_val(ptep_get(pte)); + + if (enable) + val |= _PAGE_PRESENT; + else + val &= ~_PAGE_PRESENT; + + set_pte(pte, __pte(val)); + + return 0; +} + void __kernel_map_pages(struct page *page, int numpages, int enable) { if (!debug_pagealloc_enabled()) return; - if (enable) - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(_PAGE_PRESENT), __pgprot(0)); - else - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(0), __pgprot(_PAGE_PRESENT)); + unsigned long start = (unsigned long)page_address(page); + unsigned long size = PAGE_SIZE * numpages; + + apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable); + + flush_tlb_kernel_range(start, start + size); } #endif