| Message ID | 1462254105-24128-8-git-send-email-gwshan@linux.vnet.ibm.com (mailing list archive) |
|---|---|
| State | Accepted |
| Headers | show |
On Tue, 3 May 2016 15:41:26 Gavin Shan wrote: > There are two arrays for IO and M32 segment maps on every PHB. > The index of the arrays are segment number and the value stored > in the corresponding element is PE number, indicating the segment > is assigned to the PE. Initially, all elements in those two arrays > are zeroes, meaning all segments are assigned to PE#0. It's wrong. > > This fixes the initial values in the elements of those two arrays > to IODA_INVALID_PE, meaning all segments aren't assigned to any > PE. > > Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com> > --- > arch/powerpc/platforms/powernv/pci-ioda.c | 8 +++++++- > 1 file changed, 7 insertions(+), 1 deletion(-) > > diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c > index 4aa6cdf..59b20e5 100644 > --- a/arch/powerpc/platforms/powernv/pci-ioda.c > +++ b/arch/powerpc/platforms/powernv/pci-ioda.c > @@ -3240,6 +3240,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, > const __be64 *prop64; > const __be32 *prop32; > int len; > + unsigned int segno; > u64 phb_id; > void *aux; > long rc; > @@ -3334,8 +3335,13 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, > aux = memblock_virt_alloc(size, 0); > phb->ioda.pe_alloc = aux; > phb->ioda.m32_segmap = aux + m32map_off; > - if (phb->type == PNV_PHB_IODA1) > + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) These arrays are indexed by segment number but the upper bound is the total number of PEs. Does IODA1 & IODA2 hardware always have the same number of PE#s and segments? Is there any chance there could be more or less PE#s (total_pe_num) than segments? - Alistair > + phb->ioda.m32_segmap[segno] = IODA_INVALID_PE; > + if (phb->type == PNV_PHB_IODA1) { > phb->ioda.io_segmap = aux + iomap_off; > + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) > + phb->ioda.io_segmap[segno] = IODA_INVALID_PE; > + } > phb->ioda.pe_array = aux + pemap_off; > set_bit(phb->ioda.reserved_pe_idx, phb->ioda.pe_alloc); > >
On Wed, May 04, 2016 at 01:31:04PM +1000, Alistair Popple wrote: >On Tue, 3 May 2016 15:41:26 Gavin Shan wrote: >> There are two arrays for IO and M32 segment maps on every PHB. >> The index of the arrays are segment number and the value stored >> in the corresponding element is PE number, indicating the segment >> is assigned to the PE. Initially, all elements in those two arrays >> are zeroes, meaning all segments are assigned to PE#0. It's wrong. >> >> This fixes the initial values in the elements of those two arrays >> to IODA_INVALID_PE, meaning all segments aren't assigned to any >> PE. >> >> Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com> >> --- >> arch/powerpc/platforms/powernv/pci-ioda.c | 8 +++++++- >> 1 file changed, 7 insertions(+), 1 deletion(-) >> >> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c >b/arch/powerpc/platforms/powernv/pci-ioda.c >> index 4aa6cdf..59b20e5 100644 >> --- a/arch/powerpc/platforms/powernv/pci-ioda.c >> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c >> @@ -3240,6 +3240,7 @@ static void __init pnv_pci_init_ioda_phb(struct >device_node *np, >> const __be64 *prop64; >> const __be32 *prop32; >> int len; >> + unsigned int segno; >> u64 phb_id; >> void *aux; >> long rc; >> @@ -3334,8 +3335,13 @@ static void __init pnv_pci_init_ioda_phb(struct >device_node *np, >> aux = memblock_virt_alloc(size, 0); >> phb->ioda.pe_alloc = aux; >> phb->ioda.m32_segmap = aux + m32map_off; >> - if (phb->type == PNV_PHB_IODA1) >> + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) > >These arrays are indexed by segment number but the upper bound is the total >number of PEs. Does IODA1 & IODA2 hardware always have the same number of PE#s >and segments? Is there any chance there could be more or less PE#s >(total_pe_num) than segments? > Alistair, thanks for review the code in time. The total number of M32 segments and PEs are always equal on IODA1/IODA2. Thanks, Gavin >- Alistair > >> + phb->ioda.m32_segmap[segno] = IODA_INVALID_PE; >> + if (phb->type == PNV_PHB_IODA1) { >> phb->ioda.io_segmap = aux + iomap_off; >> + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) >> + phb->ioda.io_segmap[segno] = IODA_INVALID_PE; >> + } >> phb->ioda.pe_array = aux + pemap_off; >> set_bit(phb->ioda.reserved_pe_idx, phb->ioda.pe_alloc); >> >> >
On 05/03/2016 03:41 PM, Gavin Shan wrote: > There are two arrays for IO and M32 segment maps on every PHB. > The index of the arrays are segment number and the value stored > in the corresponding element is PE number, indicating the segment > is assigned to the PE. Initially, all elements in those two arrays > are zeroes, meaning all segments are assigned to PE#0. It's wrong. > > This fixes the initial values in the elements of those two arrays > to IODA_INVALID_PE, meaning all segments aren't assigned to any > PE. > > Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru> > --- > arch/powerpc/platforms/powernv/pci-ioda.c | 8 +++++++- > 1 file changed, 7 insertions(+), 1 deletion(-) > > diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c > index 4aa6cdf..59b20e5 100644 > --- a/arch/powerpc/platforms/powernv/pci-ioda.c > +++ b/arch/powerpc/platforms/powernv/pci-ioda.c > @@ -3240,6 +3240,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, > const __be64 *prop64; > const __be32 *prop32; > int len; > + unsigned int segno; > u64 phb_id; > void *aux; > long rc; > @@ -3334,8 +3335,13 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, > aux = memblock_virt_alloc(size, 0); > phb->ioda.pe_alloc = aux; > phb->ioda.m32_segmap = aux + m32map_off; > - if (phb->type == PNV_PHB_IODA1) > + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) > + phb->ioda.m32_segmap[segno] = IODA_INVALID_PE; > + if (phb->type == PNV_PHB_IODA1) { > phb->ioda.io_segmap = aux + iomap_off; > + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) > + phb->ioda.io_segmap[segno] = IODA_INVALID_PE; > + } > phb->ioda.pe_array = aux + pemap_off; > set_bit(phb->ioda.reserved_pe_idx, phb->ioda.pe_alloc); > >
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 4aa6cdf..59b20e5 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3240,6 +3240,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, const __be64 *prop64; const __be32 *prop32; int len; + unsigned int segno; u64 phb_id; void *aux; long rc; @@ -3334,8 +3335,13 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, aux = memblock_virt_alloc(size, 0); phb->ioda.pe_alloc = aux; phb->ioda.m32_segmap = aux + m32map_off; - if (phb->type == PNV_PHB_IODA1) + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) + phb->ioda.m32_segmap[segno] = IODA_INVALID_PE; + if (phb->type == PNV_PHB_IODA1) { phb->ioda.io_segmap = aux + iomap_off; + for (segno = 0; segno < phb->ioda.total_pe_num; segno++) + phb->ioda.io_segmap[segno] = IODA_INVALID_PE; + } phb->ioda.pe_array = aux + pemap_off; set_bit(phb->ioda.reserved_pe_idx, phb->ioda.pe_alloc);
There are two arrays for IO and M32 segment maps on every PHB. The index of the arrays are segment number and the value stored in the corresponding element is PE number, indicating the segment is assigned to the PE. Initially, all elements in those two arrays are zeroes, meaning all segments are assigned to PE#0. It's wrong. This fixes the initial values in the elements of those two arrays to IODA_INVALID_PE, meaning all segments aren't assigned to any PE. Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com> --- arch/powerpc/platforms/powernv/pci-ioda.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)