[PATCH kernel v9 22/32] powerpc/powernv: Implement multilevel TCE tables
David Gibson
david at gibson.dropbear.id.au
Tue May 5 22:05:58 AEST 2015
On Fri, May 01, 2015 at 07:48:49PM +1000, Alexey Kardashevskiy wrote:
> On 04/29/2015 03:04 PM, David Gibson wrote:
> >On Sat, Apr 25, 2015 at 10:14:46PM +1000, Alexey Kardashevskiy wrote:
> >>TCE tables might get too big in case of 4K IOMMU pages and DDW enabled
> >>on huge guests (hundreds of GB of RAM) so the kernel might be unable to
> >>allocate contiguous chunk of physical memory to store the TCE table.
> >>
> >>To address this, POWER8 CPU (actually, IODA2) supports multi-level TCE tables,
> >>up to 5 levels which splits the table into a tree of smaller subtables.
> >>
> >>This adds multi-level TCE tables support to pnv_pci_create_table()
> >>and pnv_pci_free_table() helpers.
> >>
> >>Signed-off-by: Alexey Kardashevskiy <aik at ozlabs.ru>
> >>---
> >>Changes:
> >>v9:
> >>* moved from ioda2 to common powernv pci code
> >>* fixed cleanup if allocation fails in a middle
> >>* removed check for the size - all boundary checks happen in the calling code
> >>anyway
> >>---
> >> arch/powerpc/include/asm/iommu.h | 2 +
> >> arch/powerpc/platforms/powernv/pci-ioda.c | 15 +++--
> >> arch/powerpc/platforms/powernv/pci.c | 94 +++++++++++++++++++++++++++++--
> >> arch/powerpc/platforms/powernv/pci.h | 4 +-
> >> 4 files changed, 104 insertions(+), 11 deletions(-)
> >>
> >>diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
> >>index 7e7ca0a..0f50ee2 100644
> >>--- a/arch/powerpc/include/asm/iommu.h
> >>+++ b/arch/powerpc/include/asm/iommu.h
> >>@@ -96,6 +96,8 @@ struct iommu_pool {
> >> struct iommu_table {
> >> unsigned long it_busno; /* Bus number this table belongs to */
> >> unsigned long it_size; /* Size of iommu table in entries */
> >>+ unsigned long it_indirect_levels;
> >>+ unsigned long it_level_size;
> >> unsigned long it_offset; /* Offset into global table */
> >> unsigned long it_base; /* mapped address of tce table */
> >> unsigned long it_index; /* which iommu table this is */
> >>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> >>index 59baa15..cc1d09c 100644
> >>--- a/arch/powerpc/platforms/powernv/pci-ioda.c
> >>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> >>@@ -1967,13 +1967,17 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
> >> table_group);
> >> struct pnv_phb *phb = pe->phb;
> >> int64_t rc;
> >>+ const unsigned long size = tbl->it_indirect_levels ?
> >>+ tbl->it_level_size : tbl->it_size;
> >> const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
> >> const __u64 win_size = tbl->it_size << tbl->it_page_shift;
> >>
> >> pe_info(pe, "Setting up window at %llx..%llx "
> >>- "pgsize=0x%x tablesize=0x%lx\n",
> >>+ "pgsize=0x%x tablesize=0x%lx "
> >>+ "levels=%d levelsize=%x\n",
> >> start_addr, start_addr + win_size - 1,
> >>- 1UL << tbl->it_page_shift, tbl->it_size << 3);
> >>+ 1UL << tbl->it_page_shift, tbl->it_size << 3,
> >>+ tbl->it_indirect_levels + 1, tbl->it_level_size << 3);
> >>
> >> tbl->it_table_group = &pe->table_group;
> >>
> >>@@ -1984,9 +1988,9 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
> >> rc = opal_pci_map_pe_dma_window(phb->opal_id,
> >> pe->pe_number,
> >> pe->pe_number << 1,
> >>- 1,
> >>+ tbl->it_indirect_levels + 1,
> >> __pa(tbl->it_base),
> >>- tbl->it_size << 3,
> >>+ size << 3,
> >> 1ULL << tbl->it_page_shift);
> >> if (rc) {
> >> pe_err(pe, "Failed to configure TCE table, err %ld\n", rc);
> >>@@ -2099,7 +2103,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
> >> phb->ioda.m32_pci_base);
> >>
> >> rc = pnv_pci_create_table(&pe->table_group, pe->phb->hose->node,
> >>- 0, IOMMU_PAGE_SHIFT_4K, phb->ioda.m32_pci_base, tbl);
> >>+ 0, IOMMU_PAGE_SHIFT_4K, phb->ioda.m32_pci_base,
> >>+ POWERNV_IOMMU_DEFAULT_LEVELS, tbl);
> >> if (rc) {
> >> pe_err(pe, "Failed to create 32-bit TCE table, err %ld", rc);
> >> return;
> >>diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
> >>index 6bcfad5..fc129c4 100644
> >>--- a/arch/powerpc/platforms/powernv/pci.c
> >>+++ b/arch/powerpc/platforms/powernv/pci.c
> >>@@ -46,6 +46,8 @@
> >> #define cfg_dbg(fmt...) do { } while(0)
> >> //#define cfg_dbg(fmt...) printk(fmt)
> >>
> >>+#define ROUND_UP(x, n) (((x) + (n) - 1ULL) & ~((n) - 1ULL))
> >
> >Use the existing ALIGN_UP macro instead of creating a new one.
>
> Ok. I knew it existed, it is just _ALIGN_UP (with an underscore) and
> PPC-only - this is why I did not find it :)
I'm pretty sure there's a generic one too. I think it's just plain
"ALIGN".
> >> #ifdef CONFIG_PCI_MSI
> >> static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
> >> {
> >>@@ -577,6 +579,19 @@ struct pci_ops pnv_pci_ops = {
> >> static __be64 *pnv_tce(struct iommu_table *tbl, long idx)
> >> {
> >> __be64 *tmp = ((__be64 *)tbl->it_base);
> >>+ int level = tbl->it_indirect_levels;
> >>+ const long shift = ilog2(tbl->it_level_size);
> >>+ unsigned long mask = (tbl->it_level_size - 1) << (level * shift);
> >>+
> >>+ while (level) {
> >>+ int n = (idx & mask) >> (level * shift);
> >>+ unsigned long tce = be64_to_cpu(tmp[n]);
> >>+
> >>+ tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE));
> >>+ idx &= ~mask;
> >>+ mask >>= shift;
> >>+ --level;
> >>+ }
> >>
> >> return tmp + idx;
> >> }
> >>@@ -648,12 +663,18 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
> >> }
> >>
> >> static __be64 *pnv_alloc_tce_table_pages(int nid, unsigned shift,
> >>+ unsigned levels, unsigned long limit,
> >> unsigned long *tce_table_allocated)
> >> {
> >> struct page *tce_mem = NULL;
> >>- __be64 *addr;
> >>+ __be64 *addr, *tmp;
> >> unsigned order = max_t(unsigned, shift, PAGE_SHIFT) - PAGE_SHIFT;
> >> unsigned long local_allocated = 1UL << (order + PAGE_SHIFT);
> >>+ unsigned entries = 1UL << (shift - 3);
> >>+ long i;
> >>+
> >>+ if (limit == *tce_table_allocated)
> >>+ return NULL;
> >
> >If this is for what I think, it seems a bit unsafe. Shouldn't it be
> >>=, otherwise it could fail to trip if the limit isn't exactly a
> >>multiple of the bottom level allocation unit.
>
> Good point, will fix.
>
>
> >> tce_mem = alloc_pages_node(nid, GFP_KERNEL, order);
> >> if (!tce_mem) {
> >>@@ -662,14 +683,33 @@ static __be64 *pnv_alloc_tce_table_pages(int nid, unsigned shift,
> >> }
> >> addr = page_address(tce_mem);
> >> memset(addr, 0, local_allocated);
> >>- *tce_table_allocated = local_allocated;
> >>+
> >>+ --levels;
> >>+ if (!levels) {
> >>+ /* Update tce_table_allocated with bottom level table size only */
> >>+ *tce_table_allocated += local_allocated;
> >>+ return addr;
> >>+ }
> >>+
> >>+ for (i = 0; i < entries; ++i) {
> >>+ tmp = pnv_alloc_tce_table_pages(nid, shift, levels, limit,
> >>+ tce_table_allocated);
> >
> >Urgh.. it's a limited depth so it *might* be ok, but recursion is
> >generally avoided in the kernel, becuase of the very limited stack
> >size.
>
>
> It is 5 levels max 7 64bit values, there should be room for it. Avoiding
> recursion here - I can do that but it is going to look ugly :-/
Yeah, I guess. Probably worth a comment noting why the recusion depth
is limited though.
>
>
> >>+ if (!tmp)
> >>+ break;
> >>+
> >>+ addr[i] = cpu_to_be64(__pa(tmp) |
> >>+ TCE_PCI_READ | TCE_PCI_WRITE);
> >>+ }
> >
> >It also seems like it would make sense for this function ti set
> >it_indirect_levels ant it_level_size, rather than leaving it to the
> >caller.
>
>
> Mmm. Sure? It calls itself in recursion, does not seem like it is the right
> place for setting up it_indirect_levels ant it_level_size.
Yeah, ok, I hadn't properly thought through the recursion.
> >> return addr;
> >> }
> >>
> >>+static void pnv_free_tce_table_pages(unsigned long addr, unsigned long size,
> >>+ unsigned level);
> >>+
> >> long pnv_pci_create_table(struct iommu_table_group *table_group, int nid,
> >> __u64 bus_offset, __u32 page_shift, __u64 window_size,
> >>- struct iommu_table *tbl)
> >>+ __u32 levels, struct iommu_table *tbl)
> >> {
> >> void *addr;
> >> unsigned long tce_table_allocated = 0;
> >>@@ -678,16 +718,34 @@ long pnv_pci_create_table(struct iommu_table_group *table_group, int nid,
> >> unsigned table_shift = entries_shift + 3;
> >> const unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift);
> >>
> >>+ if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS))
> >>+ return -EINVAL;
> >>+
> >> if ((window_size > memory_hotplug_max()) || !is_power_of_2(window_size))
> >> return -EINVAL;
> >>
> >>+ /* Adjust direct table size from window_size and levels */
> >>+ entries_shift = ROUND_UP(entries_shift, levels) / levels;
> >
> >ROUND_UP() only works if the second parameter is a power of 2. Is
> >that always true for levels?
> >
> >For division rounding up, the usual idiom is just ((a + (b - 1)) / b)
>
>
> Yes, I think this is what I actually wanted.
>
>
> >>+ table_shift = entries_shift + 3;
> >>+ table_shift = max_t(unsigned, table_shift, PAGE_SHIFT);
> >
> >Does the PAGE_SHIFT rounding make sense any more? I would have
> >thought you'd round the level size up to page size, rather than the
> >whole thing.
>
>
> At this point in the code @table_shift is level_shift but it is not that
> obvious :) I'll rework it. Thanks.
>
>
> >> /* Allocate TCE table */
> >> addr = pnv_alloc_tce_table_pages(nid, table_shift,
> >>- &tce_table_allocated);
> >>+ levels, tce_table_size, &tce_table_allocated);
> >>+ if (!addr)
> >>+ return -ENOMEM;
> >>+
> >>+ if (tce_table_size != tce_table_allocated) {
> >>+ pnv_free_tce_table_pages((unsigned long) addr,
> >>+ tbl->it_level_size, tbl->it_indirect_levels);
> >>+ return -ENOMEM;
> >>+ }
> >>
> >> /* Setup linux iommu table */
> >> pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset,
> >> page_shift);
> >>+ tbl->it_level_size = 1ULL << (table_shift - 3);
> >>+ tbl->it_indirect_levels = levels - 1;
> >>
> >> pr_info("Created TCE table: window size = %08llx, "
> >> "tablesize = %lx (%lx), start @%08llx\n",
> >>@@ -697,12 +755,38 @@ long pnv_pci_create_table(struct iommu_table_group *table_group, int nid,
> >> return 0;
> >> }
> >>
> >>+static void pnv_free_tce_table_pages(unsigned long addr, unsigned long size,
> >>+ unsigned level)
> >>+{
> >>+ addr &= ~(TCE_PCI_READ | TCE_PCI_WRITE);
> >>+
> >>+ if (level) {
> >>+ long i;
> >>+ u64 *tmp = (u64 *) addr;
> >>+
> >>+ for (i = 0; i < size; ++i) {
> >>+ unsigned long hpa = be64_to_cpu(tmp[i]);
> >>+
> >>+ if (!(hpa & (TCE_PCI_READ | TCE_PCI_WRITE)))
> >>+ continue;
> >>+
> >>+ pnv_free_tce_table_pages((unsigned long) __va(hpa),
> >>+ size, level - 1);
> >>+ }
> >>+ }
> >>+
> >>+ free_pages(addr, get_order(size << 3));
> >>+}
> >>+
> >> void pnv_pci_free_table(struct iommu_table *tbl)
> >> {
> >>+ const unsigned long size = tbl->it_indirect_levels ?
> >>+ tbl->it_level_size : tbl->it_size;
> >>+
> >> if (!tbl->it_size)
> >> return;
> >>
> >>- free_pages(tbl->it_base, get_order(tbl->it_size << 3));
> >>+ pnv_free_tce_table_pages(tbl->it_base, size, tbl->it_indirect_levels);
> >> iommu_reset_table(tbl, "pnv");
> >> }
> >>
> >>diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
> >>index e6cbbec..3d1ff584 100644
> >>--- a/arch/powerpc/platforms/powernv/pci.h
> >>+++ b/arch/powerpc/platforms/powernv/pci.h
> >>@@ -218,9 +218,11 @@ int pnv_pci_cfg_write(struct pci_dn *pdn,
> >> extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
> >> void *tce_mem, u64 tce_size,
> >> u64 dma_offset, unsigned page_shift);
> >>+#define POWERNV_IOMMU_DEFAULT_LEVELS 1
> >>+#define POWERNV_IOMMU_MAX_LEVELS 5
> >> extern long pnv_pci_create_table(struct iommu_table_group *table_group, int nid,
> >> __u64 bus_offset, __u32 page_shift, __u64 window_size,
> >>- struct iommu_table *tbl);
> >>+ __u32 levels, struct iommu_table *tbl);
> >> extern void pnv_pci_free_table(struct iommu_table *tbl);
> >> extern void pnv_pci_init_p5ioc2_hub(struct device_node *np);
> >> extern void pnv_pci_init_ioda_hub(struct device_node *np);
> >
>
>
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 819 bytes
Desc: not available
URL: <http://lists.ozlabs.org/pipermail/linuxppc-dev/attachments/20150505/37be98b0/attachment-0001.sig>
More information about the Linuxppc-dev
mailing list