On Mon, 2015-01-05 at 12:03 +0100, Bart Van Assche wrote:
> Avoid that the following warning is reported when a SCSI LLD kernel
> module is unloaded:
>
> WARNING: CPU: 5 PID: 228 at kernel/module.c:954 module_put+0x207/0x220()
> Call Trace:
> [<ffffffff814d1fcf>] dump_stack+0x4c/0x65
> [<ffffffff81053ada>] warn_slowpath_common+0x8a/0xc0
> [<ffffffff81053bca>] warn_slowpath_null+0x1a/0x20
> [<ffffffff810d0507>] module_put+0x207/0x220
> [<ffffffffa000bea8>] scsi_device_put+0x48/0x50 [scsi_mod]
> [<ffffffffa03676d2>] scsi_disk_put+0x32/0x50 [sd_mod]
> [<ffffffffa0368d4c>] sd_shutdown+0x8c/0x150 [sd_mod]
> [<ffffffffa0368e79>] sd_remove+0x69/0xc0 [sd_mod]
> [<ffffffff813457ef>] __device_release_driver+0x7f/0xf0
> [<ffffffff81345885>] device_release_driver+0x25/0x40
> [<ffffffff81345134>] bus_remove_device+0x124/0x1b0
> [<ffffffff8134189e>] device_del+0x13e/0x250
> [<ffffffffa001cdcd>] __scsi_remove_device+0xcd/0xe0 [scsi_mod]
> [<ffffffffa001b39f>] scsi_forget_host+0x6f/0x80 [scsi_mod]
> [<ffffffffa000d5f6>] scsi_remove_host+0x86/0x140 [scsi_mod]
> [<ffffffffa07d5c0b>] srp_remove_work+0x9b/0x210 [ib_srp]
> [<ffffffff8106fd28>] process_one_work+0x1d8/0x780
> [<ffffffff810703eb>] worker_thread+0x11b/0x4a0
> [<ffffffff81075a6f>] kthread+0xef/0x110
> [<ffffffff814dad6c>] ret_from_fork+0x7c/0xb0
>
> See also patch "module: Remove stop_machine from module unloading"
> (Masami Hiramatsu; commit e513cc1c07e2; kernel v3.19-rc1).
>
> Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
> Cc: Christoph Hellwig <hch@xxxxxx>
> Cc: Hannes Reinecke <hare@xxxxxxx>
> ---
> drivers/scsi/hosts.c | 1 +
> drivers/scsi/scsi.c | 13 ++++---------
> include/scsi/scsi_host.h | 3 +++
> 3 files changed, 8 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
> index 8bb173e..e9155d0 100644
> --- a/drivers/scsi/hosts.c
> +++ b/drivers/scsi/hosts.c
> @@ -380,6 +380,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
>
> shost->host_lock = &shost->default_lock;
> spin_lock_init(shost->host_lock);
> + atomic_set(&shost->module_refcnt, 0);
> shost->shost_state = SHOST_CREATED;
> INIT_LIST_HEAD(&shost->__devices);
> INIT_LIST_HEAD(&shost->__targets);
> diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
> index e028854..ed325d1 100644
> --- a/drivers/scsi/scsi.c
> +++ b/drivers/scsi/scsi.c
> @@ -988,7 +988,8 @@ int scsi_device_get(struct scsi_device *sdev)
> return -ENXIO;
> /* We can fail this if we're doing SCSI operations
> * from module exit (like cache flush) */
> - try_module_get(sdev->host->hostt->module);
> + if (try_module_get(sdev->host->hostt->module))
> + atomic_inc(&sdev->host->module_refcnt);
>
> return 0;
> }
> @@ -1004,14 +1005,8 @@ EXPORT_SYMBOL(scsi_device_get);
> */
> void scsi_device_put(struct scsi_device *sdev)
> {
> -#ifdef CONFIG_MODULE_UNLOAD
> - struct module *module = sdev->host->hostt->module;
> -
> - /* The module refcount will be zero if scsi_device_get()
> - * was called from a module removal routine */
> - if (module && module_refcount(module) != 0)
> - module_put(module);
> -#endif
> + if (atomic_dec_if_positive(&sdev->host->module_refcnt) >= 0)
> + module_put(sdev->host->hostt->module);
> put_device(&sdev->sdev_gendev);
> }
> EXPORT_SYMBOL(scsi_device_put);
> diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
> index 019e668..b8e6f01 100644
> --- a/include/scsi/scsi_host.h
> +++ b/include/scsi/scsi_host.h
> @@ -566,6 +566,9 @@ struct Scsi_Host {
> struct scsi_host_template *hostt;
> struct scsi_transport_template *transportt;
>
> + /* Number of LLD kernel module references held by the SCSI core. */
> + atomic_t module_refcnt;
> +
> /*
> * Area to keep a shared tag map (if needed, will be
> * NULL if not).
This is a bit over coded for a fix. We don't need to duplicate the
module reference, merely take into account that in the remove code
module_refcnt() can now return -1, which we're not expecting.
Masami, this looks like a nasty unintended consequence of
commit e513cc1c07e2ab93a4514eec9833e031df3e30bb
Author: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Date: Mon Nov 10 09:30:29 2014 +1030
module: Remove stop_machine from module unloading
Are you sure we all should have to alter our module refcounting in
removal routines like this? I think the better fix is having
module_refcount() never return a negative number:
unsigned long module_refcount(struct module *mod)
{
unsigned long ret = (unsigned long)atomic_read(&mod->refcnt);
if (ret == 0)
return ret
return ret - MODULE_REF_BASE;
}
James
---
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index e028854..90dcb2f 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -1009,7 +1009,7 @@ void scsi_device_put(struct scsi_device *sdev)
/* The module refcount will be zero if scsi_device_get()
* was called from a module removal routine */
- if (module && module_refcount(module) != 0)
+ if (module && module_refcount(module) > 0)
module_put(module);
#endif
put_device(&sdev->sdev_gendev);
��.n��������+%������w��{.n�����{������ܨ}���Ơz�j:+v�����w����ޙ��&�)ߡ�a����z�ޗ���ݢj��w�f
