| Message ID | 1429964096-11524-28-git-send-email-aik@ozlabs.ru (mailing list archive) |
|---|---|
| State | Superseded |
| Delegated to: | Benjamin Herrenschmidt |
| Headers | show |
On Sat, Apr 25, 2015 at 10:14:51PM +1000, Alexey Kardashevskiy wrote: > This adds a way for the IOMMU user to know how much a new table will > use so it can be accounted in the locked_vm limit before allocation > happens. > > This stores the allocated table size in pnv_pci_create_table() > so the locked_vm counter can be updated correctly when a table is > being disposed. > > This defines an iommu_table_group_ops callback to let VFIO know > how much memory will be locked if a table is created. > > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> > --- > Changes: > v9: > * reimplemented the whole patch > --- > arch/powerpc/include/asm/iommu.h | 5 +++++ > arch/powerpc/platforms/powernv/pci-ioda.c | 14 ++++++++++++ > arch/powerpc/platforms/powernv/pci.c | 36 +++++++++++++++++++++++++++++++ > arch/powerpc/platforms/powernv/pci.h | 2 ++ > 4 files changed, 57 insertions(+) > > diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h > index 1472de3..9844c106 100644 > --- a/arch/powerpc/include/asm/iommu.h > +++ b/arch/powerpc/include/asm/iommu.h > @@ -99,6 +99,7 @@ struct iommu_table { > unsigned long it_size; /* Size of iommu table in entries */ > unsigned long it_indirect_levels; > unsigned long it_level_size; > + unsigned long it_allocated_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 */ > @@ -155,6 +156,10 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, > struct iommu_table_group; > > struct iommu_table_group_ops { > + unsigned long (*get_table_size)( > + __u32 page_shift, > + __u64 window_size, > + __u32 levels); > long (*create_table)(struct iommu_table_group *table_group, > int num, > __u32 page_shift, > diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c > index e0be556..7f548b4 100644 > --- a/arch/powerpc/platforms/powernv/pci-ioda.c > +++ b/arch/powerpc/platforms/powernv/pci-ioda.c > @@ -2062,6 +2062,18 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, > } > > #ifdef CONFIG_IOMMU_API > +static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, > + __u64 window_size, __u32 levels) > +{ > + unsigned long ret = pnv_get_table_size(page_shift, window_size, levels); > + > + if (!ret) > + return ret; > + > + /* Add size of it_userspace */ > + return ret + (window_size >> page_shift) * sizeof(unsigned long); This doesn't make much sense. The userspace view can't possibly be a property of the specific low-level IOMMU model. > +} > + > static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, > int num, __u32 page_shift, __u64 window_size, __u32 levels, > struct iommu_table *tbl) > @@ -2086,6 +2098,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, > > BUG_ON(tbl->it_userspace); > tbl->it_userspace = uas; > + tbl->it_allocated_size += uas_cb; > tbl->it_ops = &pnv_ioda2_iommu_ops; > if (pe->tce_inval_reg) > tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE); > @@ -2160,6 +2173,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) > } > > static struct iommu_table_group_ops pnv_pci_ioda2_ops = { > + .get_table_size = pnv_pci_ioda2_get_table_size, > .create_table = pnv_pci_ioda2_create_table, > .set_window = pnv_pci_ioda2_set_window, > .unset_window = pnv_pci_ioda2_unset_window, > diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c > index fc129c4..1b5b48a 100644 > --- a/arch/powerpc/platforms/powernv/pci.c > +++ b/arch/powerpc/platforms/powernv/pci.c > @@ -662,6 +662,38 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, > tbl->it_type = TCE_PCI; > } > > +unsigned long pnv_get_table_size(__u32 page_shift, > + __u64 window_size, __u32 levels) > +{ > + unsigned long bytes = 0; > + const unsigned window_shift = ilog2(window_size); > + unsigned entries_shift = window_shift - page_shift; > + unsigned table_shift = entries_shift + 3; > + unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift); > + unsigned long direct_table_size; > + > + if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) || > + (window_size > memory_hotplug_max()) || > + !is_power_of_2(window_size)) > + return 0; > + > + /* Calculate a direct table size from window_size and levels */ > + entries_shift = ROUND_UP(entries_shift, levels) / levels; > + table_shift = entries_shift + 3; > + table_shift = max_t(unsigned, table_shift, PAGE_SHIFT); > + direct_table_size = 1UL << table_shift; > + > + for ( ; levels; --levels) { > + bytes += ROUND_UP(tce_table_size, direct_table_size); > + > + tce_table_size /= direct_table_size; > + tce_table_size <<= 3; > + tce_table_size = ROUND_UP(tce_table_size, direct_table_size); > + } > + > + return bytes; > +} > + > static __be64 *pnv_alloc_tce_table_pages(int nid, unsigned shift, > unsigned levels, unsigned long limit, > unsigned long *tce_table_allocated) > @@ -741,6 +773,10 @@ long pnv_pci_create_table(struct iommu_table_group *table_group, int nid, > return -ENOMEM; > } > > + tbl->it_allocated_size = pnv_get_table_size(page_shift, window_size, > + levels); > + WARN_ON(!tbl->it_allocated_size); > + > /* Setup linux iommu table */ > pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset, > page_shift); > diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h > index 3d1ff584..ce4bc3c 100644 > --- a/arch/powerpc/platforms/powernv/pci.h > +++ b/arch/powerpc/platforms/powernv/pci.h > @@ -224,6 +224,8 @@ extern long pnv_pci_create_table(struct iommu_table_group *table_group, int nid, > __u64 bus_offset, __u32 page_shift, __u64 window_size, > __u32 levels, struct iommu_table *tbl); > extern void pnv_pci_free_table(struct iommu_table *tbl); > +extern unsigned long pnv_get_table_size(__u32 page_shift, > + __u64 window_size, __u32 levels); > extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); > extern void pnv_pci_init_ioda_hub(struct device_node *np); > extern void pnv_pci_init_ioda2_phb(struct device_node *np);
On 04/29/2015 04:40 PM, David Gibson wrote: > On Sat, Apr 25, 2015 at 10:14:51PM +1000, Alexey Kardashevskiy wrote: >> This adds a way for the IOMMU user to know how much a new table will >> use so it can be accounted in the locked_vm limit before allocation >> happens. >> >> This stores the allocated table size in pnv_pci_create_table() >> so the locked_vm counter can be updated correctly when a table is >> being disposed. >> >> This defines an iommu_table_group_ops callback to let VFIO know >> how much memory will be locked if a table is created. >> >> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> >> --- >> Changes: >> v9: >> * reimplemented the whole patch >> --- >> arch/powerpc/include/asm/iommu.h | 5 +++++ >> arch/powerpc/platforms/powernv/pci-ioda.c | 14 ++++++++++++ >> arch/powerpc/platforms/powernv/pci.c | 36 +++++++++++++++++++++++++++++++ >> arch/powerpc/platforms/powernv/pci.h | 2 ++ >> 4 files changed, 57 insertions(+) >> >> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h >> index 1472de3..9844c106 100644 >> --- a/arch/powerpc/include/asm/iommu.h >> +++ b/arch/powerpc/include/asm/iommu.h >> @@ -99,6 +99,7 @@ struct iommu_table { >> unsigned long it_size; /* Size of iommu table in entries */ >> unsigned long it_indirect_levels; >> unsigned long it_level_size; >> + unsigned long it_allocated_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 */ >> @@ -155,6 +156,10 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, >> struct iommu_table_group; >> >> struct iommu_table_group_ops { >> + unsigned long (*get_table_size)( >> + __u32 page_shift, >> + __u64 window_size, >> + __u32 levels); >> long (*create_table)(struct iommu_table_group *table_group, >> int num, >> __u32 page_shift, >> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c >> index e0be556..7f548b4 100644 >> --- a/arch/powerpc/platforms/powernv/pci-ioda.c >> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c >> @@ -2062,6 +2062,18 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, >> } >> >> #ifdef CONFIG_IOMMU_API >> +static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, >> + __u64 window_size, __u32 levels) >> +{ >> + unsigned long ret = pnv_get_table_size(page_shift, window_size, levels); >> + >> + if (!ret) >> + return ret; >> + >> + /* Add size of it_userspace */ >> + return ret + (window_size >> page_shift) * sizeof(unsigned long); > > This doesn't make much sense. The userspace view can't possibly be a > property of the specific low-level IOMMU model. This it_userspace thing is all about memory preregistration. I need some way to track how many actual mappings the mm_iommu_table_group_mem_t has in order to decide whether to allow unregistering or not. When I clear TCE, I can read the old value which is host physical address which I cannot use to find the preregistered region and adjust the mappings counter; I can only use userspace addresses for this (not even guest physical addresses as it is VFIO and probably no KVM). So I have to keep userspace addresses somewhere, one per IOMMU page, and the iommu_table seems a natural place for this. > >> +} >> + >> static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, >> int num, __u32 page_shift, __u64 window_size, __u32 levels, >> struct iommu_table *tbl) >> @@ -2086,6 +2098,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, >> >> BUG_ON(tbl->it_userspace); >> tbl->it_userspace = uas; >> + tbl->it_allocated_size += uas_cb; >> tbl->it_ops = &pnv_ioda2_iommu_ops; >> if (pe->tce_inval_reg) >> tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE); >> @@ -2160,6 +2173,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) >> } >> >> static struct iommu_table_group_ops pnv_pci_ioda2_ops = { >> + .get_table_size = pnv_pci_ioda2_get_table_size, >> .create_table = pnv_pci_ioda2_create_table, >> .set_window = pnv_pci_ioda2_set_window, >> .unset_window = pnv_pci_ioda2_unset_window, >> diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c >> index fc129c4..1b5b48a 100644 >> --- a/arch/powerpc/platforms/powernv/pci.c >> +++ b/arch/powerpc/platforms/powernv/pci.c >> @@ -662,6 +662,38 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, >> tbl->it_type = TCE_PCI; >> } >> >> +unsigned long pnv_get_table_size(__u32 page_shift, >> + __u64 window_size, __u32 levels) >> +{ >> + unsigned long bytes = 0; >> + const unsigned window_shift = ilog2(window_size); >> + unsigned entries_shift = window_shift - page_shift; >> + unsigned table_shift = entries_shift + 3; >> + unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift); >> + unsigned long direct_table_size; >> + >> + if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) || >> + (window_size > memory_hotplug_max()) || >> + !is_power_of_2(window_size)) >> + return 0; >> + >> + /* Calculate a direct table size from window_size and levels */ >> + entries_shift = ROUND_UP(entries_shift, levels) / levels; >> + table_shift = entries_shift + 3; >> + table_shift = max_t(unsigned, table_shift, PAGE_SHIFT); >> + direct_table_size = 1UL << table_shift; >> + >> + for ( ; levels; --levels) { >> + bytes += ROUND_UP(tce_table_size, direct_table_size); >> + >> + tce_table_size /= direct_table_size; >> + tce_table_size <<= 3; >> + tce_table_size = ROUND_UP(tce_table_size, direct_table_size); >> + } >> + >> + return bytes; >> +} >> + >> static __be64 *pnv_alloc_tce_table_pages(int nid, unsigned shift, >> unsigned levels, unsigned long limit, >> unsigned long *tce_table_allocated) >> @@ -741,6 +773,10 @@ long pnv_pci_create_table(struct iommu_table_group *table_group, int nid, >> return -ENOMEM; >> } >> >> + tbl->it_allocated_size = pnv_get_table_size(page_shift, window_size, >> + levels); >> + WARN_ON(!tbl->it_allocated_size); >> + >> /* Setup linux iommu table */ >> pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset, >> page_shift); >> diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h >> index 3d1ff584..ce4bc3c 100644 >> --- a/arch/powerpc/platforms/powernv/pci.h >> +++ b/arch/powerpc/platforms/powernv/pci.h >> @@ -224,6 +224,8 @@ extern long pnv_pci_create_table(struct iommu_table_group *table_group, int nid, >> __u64 bus_offset, __u32 page_shift, __u64 window_size, >> __u32 levels, struct iommu_table *tbl); >> extern void pnv_pci_free_table(struct iommu_table *tbl); >> +extern unsigned long pnv_get_table_size(__u32 page_shift, >> + __u64 window_size, __u32 levels); >> extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); >> extern void pnv_pci_init_ioda_hub(struct device_node *np); >> extern void pnv_pci_init_ioda2_phb(struct device_node *np); >
On Fri, May 01, 2015 at 02:10:58PM +1000, Alexey Kardashevskiy wrote: > On 04/29/2015 04:40 PM, David Gibson wrote: > >On Sat, Apr 25, 2015 at 10:14:51PM +1000, Alexey Kardashevskiy wrote: > >>This adds a way for the IOMMU user to know how much a new table will > >>use so it can be accounted in the locked_vm limit before allocation > >>happens. > >> > >>This stores the allocated table size in pnv_pci_create_table() > >>so the locked_vm counter can be updated correctly when a table is > >>being disposed. > >> > >>This defines an iommu_table_group_ops callback to let VFIO know > >>how much memory will be locked if a table is created. > >> > >>Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> > >>--- > >>Changes: > >>v9: > >>* reimplemented the whole patch > >>--- > >> arch/powerpc/include/asm/iommu.h | 5 +++++ > >> arch/powerpc/platforms/powernv/pci-ioda.c | 14 ++++++++++++ > >> arch/powerpc/platforms/powernv/pci.c | 36 +++++++++++++++++++++++++++++++ > >> arch/powerpc/platforms/powernv/pci.h | 2 ++ > >> 4 files changed, 57 insertions(+) > >> > >>diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h > >>index 1472de3..9844c106 100644 > >>--- a/arch/powerpc/include/asm/iommu.h > >>+++ b/arch/powerpc/include/asm/iommu.h > >>@@ -99,6 +99,7 @@ struct iommu_table { > >> unsigned long it_size; /* Size of iommu table in entries */ > >> unsigned long it_indirect_levels; > >> unsigned long it_level_size; > >>+ unsigned long it_allocated_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 */ > >>@@ -155,6 +156,10 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, > >> struct iommu_table_group; > >> > >> struct iommu_table_group_ops { > >>+ unsigned long (*get_table_size)( > >>+ __u32 page_shift, > >>+ __u64 window_size, > >>+ __u32 levels); > >> long (*create_table)(struct iommu_table_group *table_group, > >> int num, > >> __u32 page_shift, > >>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c > >>index e0be556..7f548b4 100644 > >>--- a/arch/powerpc/platforms/powernv/pci-ioda.c > >>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c > >>@@ -2062,6 +2062,18 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, > >> } > >> > >> #ifdef CONFIG_IOMMU_API > >>+static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, > >>+ __u64 window_size, __u32 levels) > >>+{ > >>+ unsigned long ret = pnv_get_table_size(page_shift, window_size, levels); > >>+ > >>+ if (!ret) > >>+ return ret; > >>+ > >>+ /* Add size of it_userspace */ > >>+ return ret + (window_size >> page_shift) * sizeof(unsigned long); > > > >This doesn't make much sense. The userspace view can't possibly be a > >property of the specific low-level IOMMU model. > > > This it_userspace thing is all about memory preregistration. > > I need some way to track how many actual mappings the > mm_iommu_table_group_mem_t has in order to decide whether to allow > unregistering or not. > > When I clear TCE, I can read the old value which is host physical address > which I cannot use to find the preregistered region and adjust the mappings > counter; I can only use userspace addresses for this (not even guest > physical addresses as it is VFIO and probably no KVM). > > So I have to keep userspace addresses somewhere, one per IOMMU page, and the > iommu_table seems a natural place for this. Well.. sort of. But as noted elsewhere this pulls VFIO specific constraints into a platform code structure. And whether you get this table depends on the platform IOMMU type rather than on what VFIO wants to do with it, which doesn't make sense. What might make more sense is an opaque pointer io iommu_table for use by the table "owner" (in the take_ownership sense). The pointer would be stored in iommu_table, but VFIO is responsible for populating and managing its contents. Or you could just put the userspace mappings in the container. Although you might want a different data structure in that case. The other thing to bear in mind is that registered regions are likely to be large contiguous blocks in user addresses, though obviously not contiguous in physical addr. So you might be able to compaticfy this information by storing it as a list of variable length blocks in userspace address space, rather than a per-page address.. But.. isn't there a bigger problem here. As Paulus was pointing out, there's nothing guaranteeing the page tables continue to contain the same page as was there at gup() time. What's going to happen if you REGISTER a memory region, then mremap() over it? Then attempt to PUT_TCE a page in the region? Or what if you mremap() it to someplace else then try to PUT_TCE a page there? Or REGISTER it again in its new location?
On 05/01/2015 03:12 PM, David Gibson wrote: > On Fri, May 01, 2015 at 02:10:58PM +1000, Alexey Kardashevskiy wrote: >> On 04/29/2015 04:40 PM, David Gibson wrote: >>> On Sat, Apr 25, 2015 at 10:14:51PM +1000, Alexey Kardashevskiy wrote: >>>> This adds a way for the IOMMU user to know how much a new table will >>>> use so it can be accounted in the locked_vm limit before allocation >>>> happens. >>>> >>>> This stores the allocated table size in pnv_pci_create_table() >>>> so the locked_vm counter can be updated correctly when a table is >>>> being disposed. >>>> >>>> This defines an iommu_table_group_ops callback to let VFIO know >>>> how much memory will be locked if a table is created. >>>> >>>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> >>>> --- >>>> Changes: >>>> v9: >>>> * reimplemented the whole patch >>>> --- >>>> arch/powerpc/include/asm/iommu.h | 5 +++++ >>>> arch/powerpc/platforms/powernv/pci-ioda.c | 14 ++++++++++++ >>>> arch/powerpc/platforms/powernv/pci.c | 36 +++++++++++++++++++++++++++++++ >>>> arch/powerpc/platforms/powernv/pci.h | 2 ++ >>>> 4 files changed, 57 insertions(+) >>>> >>>> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h >>>> index 1472de3..9844c106 100644 >>>> --- a/arch/powerpc/include/asm/iommu.h >>>> +++ b/arch/powerpc/include/asm/iommu.h >>>> @@ -99,6 +99,7 @@ struct iommu_table { >>>> unsigned long it_size; /* Size of iommu table in entries */ >>>> unsigned long it_indirect_levels; >>>> unsigned long it_level_size; >>>> + unsigned long it_allocated_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 */ >>>> @@ -155,6 +156,10 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, >>>> struct iommu_table_group; >>>> >>>> struct iommu_table_group_ops { >>>> + unsigned long (*get_table_size)( >>>> + __u32 page_shift, >>>> + __u64 window_size, >>>> + __u32 levels); >>>> long (*create_table)(struct iommu_table_group *table_group, >>>> int num, >>>> __u32 page_shift, >>>> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c >>>> index e0be556..7f548b4 100644 >>>> --- a/arch/powerpc/platforms/powernv/pci-ioda.c >>>> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c >>>> @@ -2062,6 +2062,18 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, >>>> } >>>> >>>> #ifdef CONFIG_IOMMU_API >>>> +static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, >>>> + __u64 window_size, __u32 levels) >>>> +{ >>>> + unsigned long ret = pnv_get_table_size(page_shift, window_size, levels); >>>> + >>>> + if (!ret) >>>> + return ret; >>>> + >>>> + /* Add size of it_userspace */ >>>> + return ret + (window_size >> page_shift) * sizeof(unsigned long); >>> >>> This doesn't make much sense. The userspace view can't possibly be a >>> property of the specific low-level IOMMU model. >> >> >> This it_userspace thing is all about memory preregistration. >> >> I need some way to track how many actual mappings the >> mm_iommu_table_group_mem_t has in order to decide whether to allow >> unregistering or not. >> >> When I clear TCE, I can read the old value which is host physical address >> which I cannot use to find the preregistered region and adjust the mappings >> counter; I can only use userspace addresses for this (not even guest >> physical addresses as it is VFIO and probably no KVM). >> >> So I have to keep userspace addresses somewhere, one per IOMMU page, and the >> iommu_table seems a natural place for this. > > Well.. sort of. But as noted elsewhere this pulls VFIO specific > constraints into a platform code structure. And whether you get this > table depends on the platform IOMMU type rather than on what VFIO > wants to do with it, which doesn't make sense. > > What might make more sense is an opaque pointer io iommu_table for use > by the table "owner" (in the take_ownership sense). The pointer would > be stored in iommu_table, but VFIO is responsible for populating and > managing its contents. > > Or you could just put the userspace mappings in the container. > Although you might want a different data structure in that case. Nope. I need this table in in-kernel acceleration to update the mappings counter per mm_iommu_table_group_mem_t. In KVM's real mode handlers, I only have IOMMU tables, not containers or groups. QEMU creates a guest view of the table (KVM_CREATE_SPAPR_TCE) specifying a LIOBN, and then attaches TCE tables to it via set of ioctls (one per IOMMU group) to VFIO KVM device. So if I call it it_opaque (instead of it_userspace), I will still need a common place (visible to VFIO and PowerKVM) for this to put: #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) So far this place was arch/powerpc/include/asm/iommu.h and the iommu_table struct. > The other thing to bear in mind is that registered regions are likely > to be large contiguous blocks in user addresses, though obviously not > contiguous in physical addr. So you might be able to compaticfy this > information by storing it as a list of variable length blocks in > userspace address space, rather than a per-page address.. It is 8 bytes per system page - 8/65536 = 0.00012 (or 26MB for 200GB guest) - very little overhead. > But.. isn't there a bigger problem here. As Paulus was pointing out, > there's nothing guaranteeing the page tables continue to contain the > same page as was there at gup() time. This can happen if the userspace remaps memory which it registered/mapped for DMA via VFIO, no? If so, then the userspace just should not do this, it is DMA, it cannot be moved like this. What am I missing here? > What's going to happen if you REGISTER a memory region, then mremap() > over it? The registered pages will remain pinned and PUT_TCE will use that region for translation (and this will fail as the userspace addresses changed). I do not see how it is different from the situation when the userspace mapped a page and mremap()ed it while it is DMA-mapped. > Then attempt to PUT_TCE a page in the region? Or what if you > mremap() it to someplace else then try to PUT_TCE a page there? This will fail - a new userspace address has to be preregistered. > Or REGISTER it again in its new location? It will be pinned twice + some memory overhead to store the same host physical address(es) twice.
On Fri, May 01, 2015 at 04:53:08PM +1000, Alexey Kardashevskiy wrote: > On 05/01/2015 03:12 PM, David Gibson wrote: > >On Fri, May 01, 2015 at 02:10:58PM +1000, Alexey Kardashevskiy wrote: > >>On 04/29/2015 04:40 PM, David Gibson wrote: > >>>On Sat, Apr 25, 2015 at 10:14:51PM +1000, Alexey Kardashevskiy wrote: > >>>>This adds a way for the IOMMU user to know how much a new table will > >>>>use so it can be accounted in the locked_vm limit before allocation > >>>>happens. > >>>> > >>>>This stores the allocated table size in pnv_pci_create_table() > >>>>so the locked_vm counter can be updated correctly when a table is > >>>>being disposed. > >>>> > >>>>This defines an iommu_table_group_ops callback to let VFIO know > >>>>how much memory will be locked if a table is created. > >>>> > >>>>Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> > >>>>--- > >>>>Changes: > >>>>v9: > >>>>* reimplemented the whole patch > >>>>--- > >>>> arch/powerpc/include/asm/iommu.h | 5 +++++ > >>>> arch/powerpc/platforms/powernv/pci-ioda.c | 14 ++++++++++++ > >>>> arch/powerpc/platforms/powernv/pci.c | 36 +++++++++++++++++++++++++++++++ > >>>> arch/powerpc/platforms/powernv/pci.h | 2 ++ > >>>> 4 files changed, 57 insertions(+) > >>>> > >>>>diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h > >>>>index 1472de3..9844c106 100644 > >>>>--- a/arch/powerpc/include/asm/iommu.h > >>>>+++ b/arch/powerpc/include/asm/iommu.h > >>>>@@ -99,6 +99,7 @@ struct iommu_table { > >>>> unsigned long it_size; /* Size of iommu table in entries */ > >>>> unsigned long it_indirect_levels; > >>>> unsigned long it_level_size; > >>>>+ unsigned long it_allocated_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 */ > >>>>@@ -155,6 +156,10 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, > >>>> struct iommu_table_group; > >>>> > >>>> struct iommu_table_group_ops { > >>>>+ unsigned long (*get_table_size)( > >>>>+ __u32 page_shift, > >>>>+ __u64 window_size, > >>>>+ __u32 levels); > >>>> long (*create_table)(struct iommu_table_group *table_group, > >>>> int num, > >>>> __u32 page_shift, > >>>>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c > >>>>index e0be556..7f548b4 100644 > >>>>--- a/arch/powerpc/platforms/powernv/pci-ioda.c > >>>>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c > >>>>@@ -2062,6 +2062,18 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, > >>>> } > >>>> > >>>> #ifdef CONFIG_IOMMU_API > >>>>+static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, > >>>>+ __u64 window_size, __u32 levels) > >>>>+{ > >>>>+ unsigned long ret = pnv_get_table_size(page_shift, window_size, levels); > >>>>+ > >>>>+ if (!ret) > >>>>+ return ret; > >>>>+ > >>>>+ /* Add size of it_userspace */ > >>>>+ return ret + (window_size >> page_shift) * sizeof(unsigned long); > >>> > >>>This doesn't make much sense. The userspace view can't possibly be a > >>>property of the specific low-level IOMMU model. > >> > >> > >>This it_userspace thing is all about memory preregistration. > >> > >>I need some way to track how many actual mappings the > >>mm_iommu_table_group_mem_t has in order to decide whether to allow > >>unregistering or not. > >> > >>When I clear TCE, I can read the old value which is host physical address > >>which I cannot use to find the preregistered region and adjust the mappings > >>counter; I can only use userspace addresses for this (not even guest > >>physical addresses as it is VFIO and probably no KVM). > >> > >>So I have to keep userspace addresses somewhere, one per IOMMU page, and the > >>iommu_table seems a natural place for this. > > > >Well.. sort of. But as noted elsewhere this pulls VFIO specific > >constraints into a platform code structure. And whether you get this > >table depends on the platform IOMMU type rather than on what VFIO > >wants to do with it, which doesn't make sense. > > > >What might make more sense is an opaque pointer io iommu_table for use > >by the table "owner" (in the take_ownership sense). The pointer would > >be stored in iommu_table, but VFIO is responsible for populating and > >managing its contents. > > > >Or you could just put the userspace mappings in the container. > >Although you might want a different data structure in that case. > > Nope. I need this table in in-kernel acceleration to update the mappings > counter per mm_iommu_table_group_mem_t. In KVM's real mode handlers, I only > have IOMMU tables, not containers or groups. QEMU creates a guest view of > the table (KVM_CREATE_SPAPR_TCE) specifying a LIOBN, and then attaches TCE > tables to it via set of ioctls (one per IOMMU group) to VFIO KVM device. > > So if I call it it_opaque (instead of it_userspace), I will still need a > common place (visible to VFIO and PowerKVM) for this to put: > #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) I think it should be in a VFIO header. If I'm understanding right this part of the PowerKVM code is explicitly VFIO aware - that's kind of the point. > So far this place was arch/powerpc/include/asm/iommu.h and the iommu_table > struct. > > > >The other thing to bear in mind is that registered regions are likely > >to be large contiguous blocks in user addresses, though obviously not > >contiguous in physical addr. So you might be able to compaticfy this > >information by storing it as a list of variable length blocks in > >userspace address space, rather than a per-page address.. > > It is 8 bytes per system page - 8/65536 = 0.00012 (or 26MB for 200GB guest) > - very little overhead. > > > >But.. isn't there a bigger problem here. As Paulus was pointing out, > >there's nothing guaranteeing the page tables continue to contain the > >same page as was there at gup() time. > > This can happen if the userspace remaps memory which it registered/mapped > for DMA via VFIO, no? If so, then the userspace just should not do this, it > is DMA, it cannot be moved like this. What am I missing here? > > > >What's going to happen if you REGISTER a memory region, then mremap() > >over it? > > The registered pages will remain pinned and PUT_TCE will use that region for > translation (and this will fail as the userspace addresses changed). > > I do not see how it is different from the situation when the userspace > mapped a page and mremap()ed it while it is DMA-mapped. True, it's basically the same. Hrm, so what guarantees a dma_map, mremap() dma_unmap will unreference the correct pages. > >Then attempt to PUT_TCE a page in the region? Or what if you > >mremap() it to someplace else then try to PUT_TCE a page there? > > This will fail - a new userspace address has to be preregistered. > > >Or REGISTER it again in its new location? > > It will be pinned twice + some memory overhead to store the same host > physical address(es) twice. > > >
On 05/05/2015 09:58 PM, David Gibson wrote: > On Fri, May 01, 2015 at 04:53:08PM +1000, Alexey Kardashevskiy wrote: >> On 05/01/2015 03:12 PM, David Gibson wrote: >>> On Fri, May 01, 2015 at 02:10:58PM +1000, Alexey Kardashevskiy wrote: >>>> On 04/29/2015 04:40 PM, David Gibson wrote: >>>>> On Sat, Apr 25, 2015 at 10:14:51PM +1000, Alexey Kardashevskiy wrote: >>>>>> This adds a way for the IOMMU user to know how much a new table will >>>>>> use so it can be accounted in the locked_vm limit before allocation >>>>>> happens. >>>>>> >>>>>> This stores the allocated table size in pnv_pci_create_table() >>>>>> so the locked_vm counter can be updated correctly when a table is >>>>>> being disposed. >>>>>> >>>>>> This defines an iommu_table_group_ops callback to let VFIO know >>>>>> how much memory will be locked if a table is created. >>>>>> >>>>>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> >>>>>> --- >>>>>> Changes: >>>>>> v9: >>>>>> * reimplemented the whole patch >>>>>> --- >>>>>> arch/powerpc/include/asm/iommu.h | 5 +++++ >>>>>> arch/powerpc/platforms/powernv/pci-ioda.c | 14 ++++++++++++ >>>>>> arch/powerpc/platforms/powernv/pci.c | 36 +++++++++++++++++++++++++++++++ >>>>>> arch/powerpc/platforms/powernv/pci.h | 2 ++ >>>>>> 4 files changed, 57 insertions(+) >>>>>> >>>>>> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h >>>>>> index 1472de3..9844c106 100644 >>>>>> --- a/arch/powerpc/include/asm/iommu.h >>>>>> +++ b/arch/powerpc/include/asm/iommu.h >>>>>> @@ -99,6 +99,7 @@ struct iommu_table { >>>>>> unsigned long it_size; /* Size of iommu table in entries */ >>>>>> unsigned long it_indirect_levels; >>>>>> unsigned long it_level_size; >>>>>> + unsigned long it_allocated_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 */ >>>>>> @@ -155,6 +156,10 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, >>>>>> struct iommu_table_group; >>>>>> >>>>>> struct iommu_table_group_ops { >>>>>> + unsigned long (*get_table_size)( >>>>>> + __u32 page_shift, >>>>>> + __u64 window_size, >>>>>> + __u32 levels); >>>>>> long (*create_table)(struct iommu_table_group *table_group, >>>>>> int num, >>>>>> __u32 page_shift, >>>>>> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c >>>>>> index e0be556..7f548b4 100644 >>>>>> --- a/arch/powerpc/platforms/powernv/pci-ioda.c >>>>>> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c >>>>>> @@ -2062,6 +2062,18 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, >>>>>> } >>>>>> >>>>>> #ifdef CONFIG_IOMMU_API >>>>>> +static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, >>>>>> + __u64 window_size, __u32 levels) >>>>>> +{ >>>>>> + unsigned long ret = pnv_get_table_size(page_shift, window_size, levels); >>>>>> + >>>>>> + if (!ret) >>>>>> + return ret; >>>>>> + >>>>>> + /* Add size of it_userspace */ >>>>>> + return ret + (window_size >> page_shift) * sizeof(unsigned long); >>>>> >>>>> This doesn't make much sense. The userspace view can't possibly be a >>>>> property of the specific low-level IOMMU model. >>>> >>>> >>>> This it_userspace thing is all about memory preregistration. >>>> >>>> I need some way to track how many actual mappings the >>>> mm_iommu_table_group_mem_t has in order to decide whether to allow >>>> unregistering or not. >>>> >>>> When I clear TCE, I can read the old value which is host physical address >>>> which I cannot use to find the preregistered region and adjust the mappings >>>> counter; I can only use userspace addresses for this (not even guest >>>> physical addresses as it is VFIO and probably no KVM). >>>> >>>> So I have to keep userspace addresses somewhere, one per IOMMU page, and the >>>> iommu_table seems a natural place for this. >>> >>> Well.. sort of. But as noted elsewhere this pulls VFIO specific >>> constraints into a platform code structure. And whether you get this >>> table depends on the platform IOMMU type rather than on what VFIO >>> wants to do with it, which doesn't make sense. >>> >>> What might make more sense is an opaque pointer io iommu_table for use >>> by the table "owner" (in the take_ownership sense). The pointer would >>> be stored in iommu_table, but VFIO is responsible for populating and >>> managing its contents. >>> >>> Or you could just put the userspace mappings in the container. >>> Although you might want a different data structure in that case. >> >> Nope. I need this table in in-kernel acceleration to update the mappings >> counter per mm_iommu_table_group_mem_t. In KVM's real mode handlers, I only >> have IOMMU tables, not containers or groups. QEMU creates a guest view of >> the table (KVM_CREATE_SPAPR_TCE) specifying a LIOBN, and then attaches TCE >> tables to it via set of ioctls (one per IOMMU group) to VFIO KVM device. >> >> So if I call it it_opaque (instead of it_userspace), I will still need a >> common place (visible to VFIO and PowerKVM) for this to put: >> #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) > > I think it should be in a VFIO header. If I'm understanding right > this part of the PowerKVM code is explicitly VFIO aware - that's kind > of the point. Well. 2 points against it are: 1. arch/powerpc/kvm/book3s_64_vio_hv.c and arch/powerpc/kvm/book3s_64_vio.c are not including any of vfio headers now (all required liobn<->iommu hooking bits are in virt/kvm/vfio.c), and I kind of like it. 2. for me it seems like a good idea to keep an accessor close to what it provides the access to. Since I cannot move it_userspace somewhere else, I should not move IOMMU_TABLE_USERSPACE_ENTRY() either. >> So far this place was arch/powerpc/include/asm/iommu.h and the iommu_table >> struct. >> >> >>> The other thing to bear in mind is that registered regions are likely >>> to be large contiguous blocks in user addresses, though obviously not >>> contiguous in physical addr. So you might be able to compaticfy this >>> information by storing it as a list of variable length blocks in >>> userspace address space, rather than a per-page address.. >> >> It is 8 bytes per system page - 8/65536 = 0.00012 (or 26MB for 200GB guest) >> - very little overhead. >> >> >>> But.. isn't there a bigger problem here. As Paulus was pointing out, >>> there's nothing guaranteeing the page tables continue to contain the >>> same page as was there at gup() time. >> >> This can happen if the userspace remaps memory which it registered/mapped >> for DMA via VFIO, no? If so, then the userspace just should not do this, it >> is DMA, it cannot be moved like this. What am I missing here? >> >> >>> What's going to happen if you REGISTER a memory region, then mremap() >>> over it? >> >> The registered pages will remain pinned and PUT_TCE will use that region for >> translation (and this will fail as the userspace addresses changed). >> >> I do not see how it is different from the situation when the userspace >> mapped a page and mremap()ed it while it is DMA-mapped. > > True, it's basically the same. Hrm, so what guarantees a dma_map, > mremap() dma_unmap will unreference the correct pages. The original page will remain pinned, wrong one will be unpinned, access to it will produce EEH, the process exit will do cleanup. What is the problem here? Inability for the userspace to dma_map() and then remap()? I do not think x86 (or anything else) can and should cope with this well, it is DMA, you just cannot do certain things when you work with DMA... >>> Then attempt to PUT_TCE a page in the region? Or what if you >>> mremap() it to someplace else then try to PUT_TCE a page there? >> >> This will fail - a new userspace address has to be preregistered. >> >>> Or REGISTER it again in its new location? >> >> It will be pinned twice + some memory overhead to store the same host >> physical address(es) twice. >> >> >> >
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 1472de3..9844c106 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -99,6 +99,7 @@ struct iommu_table { unsigned long it_size; /* Size of iommu table in entries */ unsigned long it_indirect_levels; unsigned long it_level_size; + unsigned long it_allocated_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 */ @@ -155,6 +156,10 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, struct iommu_table_group; struct iommu_table_group_ops { + unsigned long (*get_table_size)( + __u32 page_shift, + __u64 window_size, + __u32 levels); long (*create_table)(struct iommu_table_group *table_group, int num, __u32 page_shift, diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index e0be556..7f548b4 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2062,6 +2062,18 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, } #ifdef CONFIG_IOMMU_API +static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, + __u64 window_size, __u32 levels) +{ + unsigned long ret = pnv_get_table_size(page_shift, window_size, levels); + + if (!ret) + return ret; + + /* Add size of it_userspace */ + return ret + (window_size >> page_shift) * sizeof(unsigned long); +} + static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, int num, __u32 page_shift, __u64 window_size, __u32 levels, struct iommu_table *tbl) @@ -2086,6 +2098,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, BUG_ON(tbl->it_userspace); tbl->it_userspace = uas; + tbl->it_allocated_size += uas_cb; tbl->it_ops = &pnv_ioda2_iommu_ops; if (pe->tce_inval_reg) tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE); @@ -2160,6 +2173,7 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) } static struct iommu_table_group_ops pnv_pci_ioda2_ops = { + .get_table_size = pnv_pci_ioda2_get_table_size, .create_table = pnv_pci_ioda2_create_table, .set_window = pnv_pci_ioda2_set_window, .unset_window = pnv_pci_ioda2_unset_window, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index fc129c4..1b5b48a 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -662,6 +662,38 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl, tbl->it_type = TCE_PCI; } +unsigned long pnv_get_table_size(__u32 page_shift, + __u64 window_size, __u32 levels) +{ + unsigned long bytes = 0; + const unsigned window_shift = ilog2(window_size); + unsigned entries_shift = window_shift - page_shift; + unsigned table_shift = entries_shift + 3; + unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift); + unsigned long direct_table_size; + + if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) || + (window_size > memory_hotplug_max()) || + !is_power_of_2(window_size)) + return 0; + + /* Calculate a direct table size from window_size and levels */ + entries_shift = ROUND_UP(entries_shift, levels) / levels; + table_shift = entries_shift + 3; + table_shift = max_t(unsigned, table_shift, PAGE_SHIFT); + direct_table_size = 1UL << table_shift; + + for ( ; levels; --levels) { + bytes += ROUND_UP(tce_table_size, direct_table_size); + + tce_table_size /= direct_table_size; + tce_table_size <<= 3; + tce_table_size = ROUND_UP(tce_table_size, direct_table_size); + } + + return bytes; +} + static __be64 *pnv_alloc_tce_table_pages(int nid, unsigned shift, unsigned levels, unsigned long limit, unsigned long *tce_table_allocated) @@ -741,6 +773,10 @@ long pnv_pci_create_table(struct iommu_table_group *table_group, int nid, return -ENOMEM; } + tbl->it_allocated_size = pnv_get_table_size(page_shift, window_size, + levels); + WARN_ON(!tbl->it_allocated_size); + /* Setup linux iommu table */ pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset, page_shift); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 3d1ff584..ce4bc3c 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -224,6 +224,8 @@ extern long pnv_pci_create_table(struct iommu_table_group *table_group, int nid, __u64 bus_offset, __u32 page_shift, __u64 window_size, __u32 levels, struct iommu_table *tbl); extern void pnv_pci_free_table(struct iommu_table *tbl); +extern unsigned long pnv_get_table_size(__u32 page_shift, + __u64 window_size, __u32 levels); extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np);
This adds a way for the IOMMU user to know how much a new table will use so it can be accounted in the locked_vm limit before allocation happens. This stores the allocated table size in pnv_pci_create_table() so the locked_vm counter can be updated correctly when a table is being disposed. This defines an iommu_table_group_ops callback to let VFIO know how much memory will be locked if a table is created. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> --- Changes: v9: * reimplemented the whole patch --- arch/powerpc/include/asm/iommu.h | 5 +++++ arch/powerpc/platforms/powernv/pci-ioda.c | 14 ++++++++++++ arch/powerpc/platforms/powernv/pci.c | 36 +++++++++++++++++++++++++++++++ arch/powerpc/platforms/powernv/pci.h | 2 ++ 4 files changed, 57 insertions(+)