summaryrefslogtreecommitdiff
path: root/arch/riscv
diff options
context:
space:
mode:
authorNam Cao <namcao@linutronix.de>2024-05-15 08:50:40 +0300
committerPalmer Dabbelt <palmer@rivosinc.com>2024-05-22 19:15:09 +0300
commitfb1cf0878328fe75d47f0aed0a65b30126fcefc4 (patch)
tree834d5f74fb2f13de3a4e0355c053d8c8ebccae78 /arch/riscv
parentc67ddf59ac44adc60649730bf8347e37c516b001 (diff)
downloadlinux-fb1cf0878328fe75d47f0aed0a65b30126fcefc4.tar.xz
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: [<ffffffff800060dc>] dump_backtrace+0x1c/0x24 [<ffffffff8091ef6e>] show_stack+0x2c/0x38 [<ffffffff8092baf8>] dump_stack_lvl+0x5a/0x72 [<ffffffff8092bb24>] dump_stack+0x14/0x1c [<ffffffff8003b7ac>] __might_resched+0x104/0x10e [<ffffffff8003b7f4>] __might_sleep+0x3e/0x62 [<ffffffff8093276a>] down_write+0x20/0x72 [<ffffffff8000cf00>] __set_memory+0x82/0x2fa [<ffffffff8000d324>] __kernel_map_pages+0x5a/0xd4 [<ffffffff80196cca>] __alloc_pages_bulk+0x3b2/0x43a [<ffffffff8018ee82>] __vmalloc_node_range+0x196/0x6ba [<ffffffff80011904>] copy_process+0x72c/0x17ec [<ffffffff80012ab4>] kernel_clone+0x60/0x2fe [<ffffffff80012f62>] kernel_thread+0x82/0xa0 [<ffffffff8003552c>] kthreadd+0x14a/0x1be [<ffffffff809357de>] 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 <namcao@linutronix.de> Cc: stable@vger.kernel.org Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> Link: https://lore.kernel.org/r/1289ecba9606a19917bc12b6c27da8aa23e1e5ae.1715750938.git.namcao@linutronix.de Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
Diffstat (limited to 'arch/riscv')
-rw-r--r--arch/riscv/mm/pageattr.c28
1 files 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