RE: [PATCH V2 1/3] NTB: Add AMD PCI-Express NTB driver

2016-01-06 Thread Yu, Xiangliang
> > > >> > +#define ndev_pdev(ndev) ((ndev)->ntb.pdev) #define > ndev_name(ndev) > >> > +pci_name(ndev_pdev(ndev)) #define ndev_dev(ndev) > >> > +(&ndev_pdev(ndev)->dev) #define ntb_ndev(ntb) container_of(ntb, > >> > +struct amd_ntb_dev, ntb) #define hb_ndev(work) container_of(work, > >> > +struct

RE: [PATCH V2 1/3] NTB: Add AMD PCI-Express NTB driver

2016-01-06 Thread Yu, Xiangliang
> > + > > +#definePCI_DEVICE_ID_AMD_NTB 0x145B > > This looks like a tab and not a space I'll update it. > > > +#define AMD_LINK_HB_TIMEOUTmsecs_to_jiffies(1000) > > +#define AMD_LINK_STATUS_OFFSET 0x68 > > +#define NTB_LIN_STA_ACTIVE_BIT 0x0002 > > +#define NTB_LNK_STA_SPEED_

Re: [PATCH V2 1/3] NTB: Add AMD PCI-Express NTB driver

2016-01-06 Thread Jon Mason
On Wed, Jan 6, 2016 at 11:52 AM, Hubbe, Allen wrote: > From: Jon Mason : >> On Wed, Dec 23, 2015 at 8:42 AM, Xiangliang Yu >> wrote: > >> > +#define ndev_pdev(ndev) ((ndev)->ntb.pdev) >> > +#define ndev_name(ndev) pci_name(ndev_pdev(ndev)) >> > +#define ndev_dev(ndev) (&ndev_pdev(ndev)->dev) >> >

RE: [PATCH V2 1/3] NTB: Add AMD PCI-Express NTB driver

2016-01-06 Thread Hubbe, Allen
From: Jon Mason : > On Wed, Dec 23, 2015 at 8:42 AM, Xiangliang Yu > wrote: > > +#define ndev_pdev(ndev) ((ndev)->ntb.pdev) > > +#define ndev_name(ndev) pci_name(ndev_pdev(ndev)) > > +#define ndev_dev(ndev) (&ndev_pdev(ndev)->dev) > > +#define ntb_ndev(ntb) container_of(ntb, struct amd_ntb_dev, n

Re: [PATCH V2 1/3] NTB: Add AMD PCI-Express NTB driver

2016-01-06 Thread Jon Mason
On Wed, Dec 23, 2015 at 8:42 AM, Xiangliang Yu wrote: > AMD NTB support following main features: > (1) Three memory windows; > (2) Sixteen 32-bit scratch pad; > (3) Two 16-bit doorbell interrupt; > (4) Five event interrupts; > (5) One system can wake up opposite system of NTB; > (6) Flush previous

Re: [PATCH V2 1/3] NTB: Add AMD PCI-Express NTB driver

2015-12-23 Thread Christoph Hellwig
Just curious, what do you actually use NTB for? Seems like we're adding a giant subsystem without actual consumers, or did I miss something? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http