Re: [PATCH v8 09/14] powerpc/vas: Update CSB and notify process for fault CRBs

[Nicholas Piggin <npiggin@gmail.com>]

Haren Myneni's on March 19, 2020 4:17 pm:
> 
> For each fault CRB, update fault address in CRB (fault_storage_addr)
> and translation error status in CSB so that user space can touch the
> fault address and resend the request. If the user space passed invalid
> CSB address send signal to process with SIGSEGV.

This is where the actual fault handling is done? Does this need to be 
split from the other patch? Why not merge them and put it after the
reference counting one?

I'll wait until comments and questions on the first fault handling patch 
are resolved before I look at this one.

Thanks,
Nick

> 
> Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
> Signed-off-by: Haren Myneni <haren@linux.ibm.com>
> ---
>  arch/powerpc/platforms/powernv/vas-fault.c | 115 +++++++++++++++++++++++++++++
>  1 file changed, 115 insertions(+)
> 
> diff --git a/arch/powerpc/platforms/powernv/vas-fault.c b/arch/powerpc/platforms/powernv/vas-fault.c
> index 1c6d5cc..6eceac5d 100644
> --- a/arch/powerpc/platforms/powernv/vas-fault.c
> +++ b/arch/powerpc/platforms/powernv/vas-fault.c
> @@ -11,6 +11,7 @@
>  #include <linux/slab.h>
>  #include <linux/uaccess.h>
>  #include <linux/kthread.h>
> +#include <linux/sched/signal.h>
>  #include <linux/mmu_context.h>
>  #include <asm/icswx.h>
>  
> @@ -26,6 +27,119 @@
>  #define VAS_FAULT_WIN_FIFO_SIZE	(4 << 20)
>  
>  /*
> + * Update the CSB to indicate a translation error.
> + *
> + * If we are unable to update the CSB means copy_to_user failed due to
> + * invalid csb_addr, send a signal to the process.
> + *
> + * Remaining settings in the CSB are based on wait_for_csb() of
> + * NX-GZIP.
> + */
> +static void update_csb(struct vas_window *window,
> +			struct coprocessor_request_block *crb)
> +{
> +	struct coprocessor_status_block csb;
> +	struct kernel_siginfo info;
> +	struct task_struct *tsk;
> +	void __user *csb_addr;
> +	struct pid *pid;
> +	int rc;
> +
> +	/*
> +	 * NX user space windows can not be opened for task->mm=NULL
> +	 * and faults will not be generated for kernel requests.
> +	 */
> +	if (WARN_ON_ONCE(!window->mm || !window->user_win))
> +		return;
> +
> +	csb_addr = (void __user *)be64_to_cpu(crb->csb_addr);
> +
> +	memset(&csb, 0, sizeof(csb));
> +	csb.cc = CSB_CC_TRANSLATION;
> +	csb.ce = CSB_CE_TERMINATION;
> +	csb.cs = 0;
> +	csb.count = 0;
> +
> +	/*
> +	 * NX operates and returns in BE format as defined CRB struct.
> +	 * So return fault_storage_addr in BE as NX pastes in FIFO and
> +	 * expects user space to convert to CPU format.
> +	 */
> +	csb.address = crb->stamp.nx.fault_storage_addr;
> +	csb.flags = 0;
> +
> +	pid = window->pid;
> +	tsk = get_pid_task(pid, PIDTYPE_PID);
> +	/*
> +	 * Send window will be closed after processing all NX requests
> +	 * and process exits after closing all windows. In multi-thread
> +	 * applications, thread may not exists, but does not close FD
> +	 * (means send window) upon exit. Parent thread (tgid) can use
> +	 * and close the window later.
> +	 * pid and mm references are taken when window is opened by
> +	 * process (pid). So tgid is used only when child thread opens
> +	 * a window and exits without closing it in multithread tasks.
> +	 */
> +	if (!tsk) {
> +		pid = window->tgid;
> +		tsk = get_pid_task(pid, PIDTYPE_PID);
> +		/*
> +		 * Parent thread will be closing window during its exit.
> +		 * So should not get here.
> +		 */
> +		if (WARN_ON_ONCE(!tsk))
> +			return;
> +	}
> +
> +	/* Return if the task is exiting. */
> +	if (tsk->flags & PF_EXITING) {
> +		put_task_struct(tsk);
> +		return;
> +	}
> +
> +	use_mm(window->mm);
> +	rc = copy_to_user(csb_addr, &csb, sizeof(csb));
> +	/*
> +	 * User space polls on csb.flags (first byte). So add barrier
> +	 * then copy first byte with csb flags update.
> +	 */
> +	if (!rc) {
> +		csb.flags = CSB_V;
> +		smp_mb();
> +		rc = copy_to_user(csb_addr, &csb, sizeof(u8));
> +	}
> +	unuse_mm(window->mm);
> +	put_task_struct(tsk);
> +
> +	/* Success */
> +	if (!rc)
> +		return;
> +
> +	pr_debug("Invalid CSB address 0x%p signalling pid(%d)\n",
> +			csb_addr, pid_vnr(pid));
> +
> +	clear_siginfo(&info);
> +	info.si_signo = SIGSEGV;
> +	info.si_errno = EFAULT;
> +	info.si_code = SEGV_MAPERR;
> +	info.si_addr = csb_addr;
> +
> +	/*
> +	 * process will be polling on csb.flags after request is sent to
> +	 * NX. So generally CSB update should not fail except when an
> +	 * application does not follow the process properly. So an error
> +	 * message will be displayed and leave it to user space whether
> +	 * to ignore or handle this signal.
> +	 */
> +	rcu_read_lock();
> +	rc = kill_pid_info(SIGSEGV, &info, pid);
> +	rcu_read_unlock();
> +
> +	pr_devel("%s(): pid %d kill_proc_info() rc %d\n", __func__,
> +			pid_vnr(pid), rc);
> +}
> +
> +/*
>   * Process valid CRBs in fault FIFO.
>   */
>  irqreturn_t vas_fault_thread_fn(int irq, void *data)
> @@ -111,6 +225,7 @@ irqreturn_t vas_fault_thread_fn(int irq, void *data)
>  			return IRQ_HANDLED;
>  		}
>  
> +		update_csb(window, crb);
>  	} while (true);
>  }
>  
> -- 
> 1.8.3.1
> 
> 
> 
>