HWPOISON: Add code to handle "action required" errors. (7329bbeb) · Commits · e / devices / android_kernel_oneplus_sm8150

include/linux/mm.h

+1 −0

Original line number	Original line	Diff line number	Diff line
	@@ -1606,6 +1606,7 @@ void vmemmap_populate_print_last(void);

	enum mf_flags {		enum mf_flags {
	MF_COUNT_INCREASED = 1 << 0,		MF_COUNT_INCREASED = 1 << 0,
			MF_ACTION_REQUIRED = 1 << 1,
	};		};
	extern int memory_failure(unsigned long pfn, int trapno, int flags);		extern int memory_failure(unsigned long pfn, int trapno, int flags);
	extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);		extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);

mm/memory-failure.c

+29 −21

Original line number	Original line	Diff line number	Diff line
	@@ -187,33 +187,40 @@ int hwpoison_filter(struct page *p)
	EXPORT_SYMBOL_GPL(hwpoison_filter);		EXPORT_SYMBOL_GPL(hwpoison_filter);

	/*		/*
	* Send all the processes who have the page mapped an ``action optional''		* Send all the processes who have the page mapped a signal.
	* signal.		* ``action optional'' if they are not immediately affected by the error
			* ``action required'' if error happened in current execution context
	*/		*/
	static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,		static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
	unsigned long pfn, struct page *page)		unsigned long pfn, struct page *page, int flags)
	{		{
	struct siginfo si;		struct siginfo si;
	int ret;		int ret;

	printk(KERN_ERR		printk(KERN_ERR
	"MCE %#lx: Killing %s:%d early due to hardware memory corruption\n",		"MCE %#lx: Killing %s:%d due to hardware memory corruption\n",
	pfn, t->comm, t->pid);		pfn, t->comm, t->pid);
	si.si_signo = SIGBUS;		si.si_signo = SIGBUS;
	si.si_errno = 0;		si.si_errno = 0;
	si.si_code = BUS_MCEERR_AO;
	si.si_addr = (void *)addr;		si.si_addr = (void *)addr;
	#ifdef __ARCH_SI_TRAPNO		#ifdef __ARCH_SI_TRAPNO
	si.si_trapno = trapno;		si.si_trapno = trapno;
	#endif		#endif
	si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;		si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;

			if ((flags & MF_ACTION_REQUIRED) && t == current) {
			si.si_code = BUS_MCEERR_AR;
			ret = force_sig_info(SIGBUS, &si, t);
			} else {
	/*		/*
	* Don't use force here, it's convenient if the signal		* Don't use force here, it's convenient if the signal
	* can be temporarily blocked.		* can be temporarily blocked.
	* This could cause a loop when the user sets SIGBUS		* This could cause a loop when the user sets SIGBUS
	* to SIG_IGN, but hopefully no one will do that?		* to SIG_IGN, but hopefully no one will do that?
	*/		*/
			si.si_code = BUS_MCEERR_AO;
	ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */		ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */
			}
	if (ret < 0)		if (ret < 0)
	printk(KERN_INFO "MCE: Error sending signal to %s:%d: %d\n",		printk(KERN_INFO "MCE: Error sending signal to %s:%d: %d\n",
	t->comm, t->pid, ret);		t->comm, t->pid, ret);
	@@ -338,8 +345,9 @@ static void add_to_kill(struct task_struct tsk, struct page p,
	* Also when FAIL is set do a force kill because something went		* Also when FAIL is set do a force kill because something went
	* wrong earlier.		* wrong earlier.
	*/		*/
	static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,		static void kill_procs(struct list_head *to_kill, int doit, int trapno,
	int fail, struct page *page, unsigned long pfn)		int fail, struct page *page, unsigned long pfn,
			int flags)
	{		{
	struct to_kill tk, next;		struct to_kill tk, next;

	@@ -363,8 +371,8 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
	* check for that, but we need to tell the		* check for that, but we need to tell the
	* process anyways.		* process anyways.
	*/		*/
	else if (kill_proc_ao(tk->tsk, tk->addr, trapno,		else if (kill_proc(tk->tsk, tk->addr, trapno,
	pfn, page) < 0)		pfn, page, flags) < 0)
	printk(KERN_ERR		printk(KERN_ERR
	"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",		"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
	pfn, tk->tsk->comm, tk->tsk->pid);		pfn, tk->tsk->comm, tk->tsk->pid);
	@@ -844,7 +852,7 @@ static int page_action(struct page_state ps, struct page p,
	* the pages and send SIGBUS to the processes if the data was dirty.		* the pages and send SIGBUS to the processes if the data was dirty.
	*/		*/
	static int hwpoison_user_mappings(struct page *p, unsigned long pfn,		static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
	int trapno)		int trapno, int flags)
	{		{
	enum ttu_flags ttu = TTU_UNMAP \| TTU_IGNORE_MLOCK \| TTU_IGNORE_ACCESS;		enum ttu_flags ttu = TTU_UNMAP \| TTU_IGNORE_MLOCK \| TTU_IGNORE_ACCESS;
	struct address_space *mapping;		struct address_space *mapping;
	@@ -962,8 +970,8 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
	* use a more force-full uncatchable kill to prevent		* use a more force-full uncatchable kill to prevent
	* any accesses to the poisoned memory.		* any accesses to the poisoned memory.
	*/		*/
	kill_procs_ao(&tokill, !!PageDirty(ppage), trapno,		kill_procs(&tokill, !!PageDirty(ppage), trapno,
	ret != SWAP_SUCCESS, p, pfn);		ret != SWAP_SUCCESS, p, pfn, flags);

	return ret;		return ret;
	}		}
	@@ -1148,7 +1156,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
	* Now take care of user space mappings.		* Now take care of user space mappings.
	* Abort on fail: __delete_from_page_cache() assumes unmapped page.		* Abort on fail: __delete_from_page_cache() assumes unmapped page.
	*/		*/
	if (hwpoison_user_mappings(p, pfn, trapno) != SWAP_SUCCESS) {		if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
	printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);		printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
	res = -EBUSY;		res = -EBUSY;
	goto out;		goto out;