| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <8988bbb2-b089-5a18-e8d0-1e7339832364@linux.alibaba.com>
Date: Mon, 12 Aug 2019 14:37:57 +0800
From: luoben <luoben@...ux.alibaba.com>
To: Yunsheng Lin <linyunsheng@...wei.com>, tglx@...utronix.de,
alex.williamson@...hat.com, linux-kernel@...r.kernel.org
Cc: tao.ma@...ux.alibaba.com, gerry@...ux.alibaba.com
Subject: Re: [PATCH 2/2] vfio_pci: make use of update_irq_devid and optimize
irq ops
在 2019/8/12 下午1:44, Yunsheng Lin 写道:
> On 2019/8/8 20:07, Ben Luo wrote:
>> When userspace (e.g. qemu) triggers a switch between KVM
>> irqfd and userspace eventfd, only dev_id of irq action
>> (i.e. the "trigger" in this patch's context) will be
>> changed, but a free-then-request-irq action is taken in
>> current code. And, irq affinity setting in VM will also
>> trigger a free-then-request-irq action, which actully
>> changes nothing, but only fires a producer re-registration
>> to update irte in case that posted-interrupt is in use.
>>
>> This patch makes use of update_irq_devid() and optimize
>> both cases above, which reduces the risk of losing interrupt
>> and also cuts some overhead.
>>
>> Signed-off-by: Ben Luo <luoben@...ux.alibaba.com>
>> Reviewed-by: Liu Jiang <gerry@...ux.alibaba.com>
>> ---
>> drivers/vfio/pci/vfio_pci_intrs.c | 100 +++++++++++++++++++++++---------------
>> 1 file changed, 62 insertions(+), 38 deletions(-)
>>
>> diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
>> index 3fa3f72..1323dc8 100644
>> --- a/drivers/vfio/pci/vfio_pci_intrs.c
>> +++ b/drivers/vfio/pci/vfio_pci_intrs.c
>> @@ -285,69 +285,93 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
>> int vector, int fd, bool msix)
>> {
>> struct pci_dev *pdev = vdev->pdev;
>> - struct eventfd_ctx *trigger;
>> + struct eventfd_ctx *trigger = NULL;
> struct eventfd_ctx *trigger = NULL;
> struct pci_dev *pdev = vdev->pdev;
>
> to maintain reverse christmas tree?
ok, keep reverse christmas tree in v2
>
>> int irq, ret;
>>
>> if (vector < 0 || vector >= vdev->num_ctx)
>> return -EINVAL;
>>
>> + if (fd >= 0) {
>> + trigger = eventfd_ctx_fdget(fd);
>> + if (IS_ERR(trigger))
>> + return PTR_ERR(trigger);
> It seems vdev->ctx[vector].trigger is freed even if fd < 0 before
> this patch. If it return here, vdev->ctx[vector].trigger is not free?
if fd < 0, it won't enter here
if fd >= 0, I think it's better to return and leave everything as it
was, and
let the caller to deal with this bad fd case and disable msi to free the
resouces if it wants
>
>> + }
>> +
>> irq = pci_irq_vector(pdev, vector);
>>
>> if (vdev->ctx[vector].trigger) {
>> - free_irq(irq, vdev->ctx[vector].trigger);
>> - irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
>> - kfree(vdev->ctx[vector].name);
>> - eventfd_ctx_put(vdev->ctx[vector].trigger);
>> - vdev->ctx[vector].trigger = NULL;
>> + if (vdev->ctx[vector].trigger != trigger) {
>> + if (trigger) {
>> + ret = update_irq_devid(irq,
>> + vdev->ctx[vector].trigger, trigger);
>> + if (unlikely(ret)) {
>> + dev_info(&pdev->dev,
>> + "update_irq_devid %d (token %p) fails: %d\n",
>> + irq, vdev->ctx[vector].trigger, ret);
>> + eventfd_ctx_put(trigger);
>> + return ret;
>> + }
>> + irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
>> + eventfd_ctx_put(vdev->ctx[vector].trigger);
>> + vdev->ctx[vector].producer.token = trigger;
>> + vdev->ctx[vector].trigger = trigger;
>> + } else {
>> + free_irq(irq, vdev->ctx[vector].trigger);
>> + irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
>> + kfree(vdev->ctx[vector].name);
>> + eventfd_ctx_put(vdev->ctx[vector].trigger);
>> + vdev->ctx[vector].trigger = NULL;
>> + }
>> + } else
>> + irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
>> }
> Maybe adjust it a litte to reduce indent and to improve readability?
>
> if (vdev->ctx[vector].trigger && vdev->ctx[vector].trigger == trigger) {
> irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
> } else if (vdev->ctx[vector].trigger && !trigger) {
> free_irq(irq, vdev->ctx[vector].trigger);
> irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
> kfree(vdev->ctx[vector].name);
> eventfd_ctx_put(vdev->ctx[vector].trigger);
> vdev->ctx[vector].trigger = NULL;
> } else if (vdev->ctx[vector].trigger) {
> ret = update_irq_devid(irq, vdev->ctx[vector].trigger, trigger);
> if (unlikely(ret)) {
> dev_info(&pdev->dev,
> "update_irq_devid %d (token %p) fails: %d\n",
> irq, vdev->ctx[vector].trigger, ret);
> eventfd_ctx_put(trigger);
> return ret;
> }
> irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
> eventfd_ctx_put(vdev->ctx[vector].trigger);
> vdev->ctx[vector].producer.token = trigger;
> vdev->ctx[vector].trigger = trigger;
> }
>
I will reformat this chunk in v2
>>
>> if (fd < 0)
>> return 0;
>>
>> - vdev->ctx[vector].name = kasprintf(GFP_KERNEL, "vfio-msi%s[%d](%s)",
>> - msix ? "x" : "", vector,
>> - pci_name(pdev));
>> - if (!vdev->ctx[vector].name)
>> - return -ENOMEM;
>> + if (vdev->ctx[vector].trigger == NULL) {
> It may be common to use the below check to do NULL checking:
> If (!vdev->ctx[vector].trigger)
ok, make it this way in v2
>
>> + vdev->ctx[vector].name = kasprintf(GFP_KERNEL, "vfio-msi%s[%d](%s)",
>> + msix ? "x" : "", vector,
>> + pci_name(pdev));
>> + if (!vdev->ctx[vector].name) {
>> + eventfd_ctx_put(trigger);
>> + return -ENOMEM;
>> + }
>>
>> - trigger = eventfd_ctx_fdget(fd);
>> - if (IS_ERR(trigger)) {
>> - kfree(vdev->ctx[vector].name);
>> - return PTR_ERR(trigger);
>> - }
>> + /*
>> + * The MSIx vector table resides in device memory which may be cleared
>> + * via backdoor resets. We don't allow direct access to the vector
>> + * table so even if a userspace driver attempts to save/restore around
>> + * such a reset it would be unsuccessful. To avoid this, restore the
>> + * cached value of the message prior to enabling.
>> + */
>> + if (msix) {
>> + struct msi_msg msg;
>>
>> - /*
>> - * The MSIx vector table resides in device memory which may be cleared
>> - * via backdoor resets. We don't allow direct access to the vector
>> - * table so even if a userspace driver attempts to save/restore around
>> - * such a reset it would be unsuccessful. To avoid this, restore the
>> - * cached value of the message prior to enabling.
>> - */
>> - if (msix) {
>> - struct msi_msg msg;
>> + get_cached_msi_msg(irq, &msg);
>> + pci_write_msi_msg(irq, &msg);
>> + }
>>
>> - get_cached_msi_msg(irq, &msg);
>> - pci_write_msi_msg(irq, &msg);
>> - }
>> + ret = request_irq(irq, vfio_msihandler, 0,
>> + vdev->ctx[vector].name, trigger);
>> + if (ret) {
>> + kfree(vdev->ctx[vector].name);
>> + eventfd_ctx_put(trigger);
>> + return ret;
>> + }
>>
>> - ret = request_irq(irq, vfio_msihandler, 0,
>> - vdev->ctx[vector].name, trigger);
>> - if (ret) {
>> - kfree(vdev->ctx[vector].name);
>> - eventfd_ctx_put(trigger);
>> - return ret;
>> + vdev->ctx[vector].producer.token = trigger;
>> + vdev->ctx[vector].producer.irq = irq;
>> + vdev->ctx[vector].trigger = trigger;
>> }
>>
>> - vdev->ctx[vector].producer.token = trigger;
>> - vdev->ctx[vector].producer.irq = irq;
>> + /* always update irte for posted mode */
>> ret = irq_bypass_register_producer(&vdev->ctx[vector].producer);
>> if (unlikely(ret))
>> dev_info(&pdev->dev,
>> "irq bypass producer (token %p) registration fails: %d\n",
>> vdev->ctx[vector].producer.token, ret);
>>
>> - vdev->ctx[vector].trigger = trigger;
>> -
>> return 0;
>> }
>>
Thanks,
Ben
Powered by blists - more mailing lists