mm, hwpoison: when copy-on-write hits poison, take page offline

Cannot call memory_failure() directly from the fault handler because
mmap_lock (and others) are held.

It is important, but not urgent, to mark the source page as h/w poisoned
and unmap it from other tasks.

Use memory_failure_queue() to request a call to memory_failure() for the
page with the error.

Also provide a stub version for CONFIG_MEMORY_FAILURE=n

Link: https://lkml.kernel.org/r/20221021200120.175753-3-tony.luck@intel.comSigned-off-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/mm.h

@@ -3280,7 +3280,6 @@ enum mf_flags {
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
 extern int memory_failure(unsigned long pfn, int flags);
-extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
 extern int sysctl_memory_failure_early_kill;
@@ -3289,11 +3288,16 @@ extern void shake_page(struct page *p);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);
 #ifdef CONFIG_MEMORY_FAILURE
+extern void memory_failure_queue(unsigned long pfn, int flags);
 extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 					bool *migratable_cleared);
 void num_poisoned_pages_inc(unsigned long pfn);
 void num_poisoned_pages_sub(unsigned long pfn, long i);
 #else
+static inline void memory_failure_queue(unsigned long pfn, int flags)
+{
+}
+
 static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 					bool *migratable_cleared)
 {

mm/memory.c

@@ -2816,8 +2816,10 @@ static inline int __wp_page_copy_user(struct page *dst, struct page *src,
 	unsigned long addr = vmf->address;
 
 	if (likely(src)) {
-		if (copy_mc_user_highpage(dst, src, addr, vma))
+		if (copy_mc_user_highpage(dst, src, addr, vma)) {
+			memory_failure_queue(page_to_pfn(src), 0);
 			return -EHWPOISON;
+		}
 		return 0;
 	}