RE: [PATCH 2/4] fsl_pci: Add a workaround for PCI 5 errata in MPC8548

2012-03-08 Thread Zhao Chenhui-B35336
> On Mar 6, 2012, at 3:10 AM, Zhao Chenhui wrote: > > > + if ((fsl_svr_is(SVR_8548) || fsl_svr_is(SVR_8548_E)) && > > Should this also have 8547, 8547E, 8545, 8545E, 8543, & 8543E? Yes. I will include these chips. -Chenhui > > > + !early_find_capability(hose, 0, 0, PCI

Re: [PATCH 2/4] fsl_pci: Add a workaround for PCI 5 errata in MPC8548

2012-03-06 Thread Kumar Gala
On Mar 6, 2012, at 3:10 AM, Zhao Chenhui wrote: > + if ((fsl_svr_is(SVR_8548) || fsl_svr_is(SVR_8548_E)) && Should this also have 8547, 8547E, 8545, 8545E, 8543, & 8543E? > + !early_find_capability(hose, 0, 0, PCI_CAP_ID_PCIX)) { > + early_read_co

[PATCH 2/4] fsl_pci: Add a workaround for PCI 5 errata in MPC8548

2012-03-06 Thread Zhao Chenhui
From: chenhui zhao Issue: As a master, the PCI IP block can combine a memory write to the last PCI double word (4 bytes) of a cacheline with a 4 byte memory write to the first PCI double word of the subsequent cacheline. This affects 32-bit PCI target devices that blindly assert STOP on memory-wr