Re: [PATCH kernel v9 23/32] powerpc/powernv/ioda: Define and implement DMA table/window management callbacks
On 04/30/2015 02:37 PM, David Gibson wrote: On Wed, Apr 29, 2015 at 07:44:20PM +1000, Alexey Kardashevskiy wrote: On 04/29/2015 03:30 PM, David Gibson wrote: On Sat, Apr 25, 2015 at 10:14:47PM +1000, Alexey Kardashevskiy wrote: This extends iommu_table_group_ops by a set of callbacks to support dynamic DMA windows management. create_table() creates a TCE table with specific parameters. it receives iommu_table_group to know nodeid in order to allocate TCE table memory closer to the PHB. The exact format of allocated multi-level table might be also specific to the PHB model (not the case now though). This callback calculated the DMA window offset on a PCI bus from @num and stores it in a just created table. set_window() sets the window at specified TVT index + @num on PHB. unset_window() unsets the window from specified TVT. This adds a free() callback to iommu_table_ops to free the memory (potentially a tree of tables) allocated for the TCE table. Doesn't the free callback belong with the previous patch introducing multi-level tables? If I did that, you would say why is it here if nothing calls it on multilevel patch and I see the allocation but I do not see memory release ;) Yeah, fair enough ;) I need some rule of thumb here. I think it is a bit cleaner if the same patch adds a callback for memory allocation and its counterpart, no? On further consideration, yes, I think you're right. create_table() and free() are supposed to be called once per VFIO container and set_window()/unset_window() are supposed to be called for every group in a container. This adds IOMMU capabilities to iommu_table_group such as default 32bit window parameters and others. Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru --- arch/powerpc/include/asm/iommu.h| 19 arch/powerpc/platforms/powernv/pci-ioda.c | 75 ++--- arch/powerpc/platforms/powernv/pci-p5ioc2.c | 12 +++-- 3 files changed, 96 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 0f50ee2..7694546 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -70,6 +70,7 @@ struct iommu_table_ops { /* get() returns a physical address */ unsigned long (*get)(struct iommu_table *tbl, long index); void (*flush)(struct iommu_table *tbl); + void (*free)(struct iommu_table *tbl); }; /* These are used by VIO */ @@ -148,6 +149,17 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, struct iommu_table_group; struct iommu_table_group_ops { + long (*create_table)(struct iommu_table_group *table_group, + int num, + __u32 page_shift, + __u64 window_size, + __u32 levels, + struct iommu_table *tbl); + long (*set_window)(struct iommu_table_group *table_group, + int num, + struct iommu_table *tblnew); + long (*unset_window)(struct iommu_table_group *table_group, + int num); /* * Switches ownership from the kernel itself to an external * user. While onwership is taken, the kernel cannot use IOMMU itself. @@ -160,6 +172,13 @@ struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif + /* Some key properties of IOMMU */ + __u32 tce32_start; + __u32 tce32_size; + __u64 pgsizes; /* Bitmap of supported page sizes */ + __u32 max_dynamic_windows_supported; + __u32 max_levels; With this information, table_group seems even more like a bad name. iommu_state maybe? Please, no. We will never come to agreement then :( And iommu_state is too general anyway, it won't pass. struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; struct iommu_table_group_ops *ops; }; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cc1d09c..4828837 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -24,6 +24,7 @@ #include linux/msi.h #include linux/memblock.h #include linux/iommu.h +#include linux/sizes.h #include asm/sections.h #include asm/io.h @@ -1846,6 +1847,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = { #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, + .free = pnv_pci_free_table, }; static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb, @@ -1936,6 +1938,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); tbl-it_ops = pnv_ioda1_iommu_ops; + pe-table_group.tce32_start = tbl-it_offset tbl-it_page_shift; + pe-table_group.tce32_size = tbl-it_size tbl-it_page_shift; iommu_init_table(tbl, phb-hose-node);
Re: [PATCH kernel v9 23/32] powerpc/powernv/ioda: Define and implement DMA table/window management callbacks
On Thu, Apr 30, 2015 at 07:56:17PM +1000, Alexey Kardashevskiy wrote: On 04/30/2015 02:37 PM, David Gibson wrote: On Wed, Apr 29, 2015 at 07:44:20PM +1000, Alexey Kardashevskiy wrote: On 04/29/2015 03:30 PM, David Gibson wrote: On Sat, Apr 25, 2015 at 10:14:47PM +1000, Alexey Kardashevskiy wrote: This extends iommu_table_group_ops by a set of callbacks to support dynamic DMA windows management. create_table() creates a TCE table with specific parameters. it receives iommu_table_group to know nodeid in order to allocate TCE table memory closer to the PHB. The exact format of allocated multi-level table might be also specific to the PHB model (not the case now though). This callback calculated the DMA window offset on a PCI bus from @num and stores it in a just created table. set_window() sets the window at specified TVT index + @num on PHB. unset_window() unsets the window from specified TVT. This adds a free() callback to iommu_table_ops to free the memory (potentially a tree of tables) allocated for the TCE table. Doesn't the free callback belong with the previous patch introducing multi-level tables? If I did that, you would say why is it here if nothing calls it on multilevel patch and I see the allocation but I do not see memory release ;) Yeah, fair enough ;) I need some rule of thumb here. I think it is a bit cleaner if the same patch adds a callback for memory allocation and its counterpart, no? On further consideration, yes, I think you're right. create_table() and free() are supposed to be called once per VFIO container and set_window()/unset_window() are supposed to be called for every group in a container. This adds IOMMU capabilities to iommu_table_group such as default 32bit window parameters and others. Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru --- arch/powerpc/include/asm/iommu.h| 19 arch/powerpc/platforms/powernv/pci-ioda.c | 75 ++--- arch/powerpc/platforms/powernv/pci-p5ioc2.c | 12 +++-- 3 files changed, 96 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 0f50ee2..7694546 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -70,6 +70,7 @@ struct iommu_table_ops { /* get() returns a physical address */ unsigned long (*get)(struct iommu_table *tbl, long index); void (*flush)(struct iommu_table *tbl); + void (*free)(struct iommu_table *tbl); }; /* These are used by VIO */ @@ -148,6 +149,17 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, struct iommu_table_group; struct iommu_table_group_ops { + long (*create_table)(struct iommu_table_group *table_group, + int num, + __u32 page_shift, + __u64 window_size, + __u32 levels, + struct iommu_table *tbl); + long (*set_window)(struct iommu_table_group *table_group, + int num, + struct iommu_table *tblnew); + long (*unset_window)(struct iommu_table_group *table_group, + int num); /* * Switches ownership from the kernel itself to an external * user. While onwership is taken, the kernel cannot use IOMMU itself. @@ -160,6 +172,13 @@ struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif + /* Some key properties of IOMMU */ + __u32 tce32_start; + __u32 tce32_size; + __u64 pgsizes; /* Bitmap of supported page sizes */ + __u32 max_dynamic_windows_supported; + __u32 max_levels; With this information, table_group seems even more like a bad name. iommu_state maybe? Please, no. We will never come to agreement then :( And iommu_state is too general anyway, it won't pass. struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; struct iommu_table_group_ops *ops; }; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cc1d09c..4828837 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -24,6 +24,7 @@ #include linux/msi.h #include linux/memblock.h #include linux/iommu.h +#include linux/sizes.h #include asm/sections.h #include asm/io.h @@ -1846,6 +1847,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = { #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, + .free = pnv_pci_free_table, }; static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb, @@ -1936,6 +1938,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); tbl-it_ops = pnv_ioda1_iommu_ops; + pe-table_group.tce32_start = tbl-it_offset tbl-it_page_shift; +
Re: [PATCH kernel v9 23/32] powerpc/powernv/ioda: Define and implement DMA table/window management callbacks
On 04/29/2015 03:30 PM, David Gibson wrote: On Sat, Apr 25, 2015 at 10:14:47PM +1000, Alexey Kardashevskiy wrote: This extends iommu_table_group_ops by a set of callbacks to support dynamic DMA windows management. create_table() creates a TCE table with specific parameters. it receives iommu_table_group to know nodeid in order to allocate TCE table memory closer to the PHB. The exact format of allocated multi-level table might be also specific to the PHB model (not the case now though). This callback calculated the DMA window offset on a PCI bus from @num and stores it in a just created table. set_window() sets the window at specified TVT index + @num on PHB. unset_window() unsets the window from specified TVT. This adds a free() callback to iommu_table_ops to free the memory (potentially a tree of tables) allocated for the TCE table. Doesn't the free callback belong with the previous patch introducing multi-level tables? If I did that, you would say why is it here if nothing calls it on multilevel patch and I see the allocation but I do not see memory release ;) I need some rule of thumb here. I think it is a bit cleaner if the same patch adds a callback for memory allocation and its counterpart, no? create_table() and free() are supposed to be called once per VFIO container and set_window()/unset_window() are supposed to be called for every group in a container. This adds IOMMU capabilities to iommu_table_group such as default 32bit window parameters and others. Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru --- arch/powerpc/include/asm/iommu.h| 19 arch/powerpc/platforms/powernv/pci-ioda.c | 75 ++--- arch/powerpc/platforms/powernv/pci-p5ioc2.c | 12 +++-- 3 files changed, 96 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 0f50ee2..7694546 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -70,6 +70,7 @@ struct iommu_table_ops { /* get() returns a physical address */ unsigned long (*get)(struct iommu_table *tbl, long index); void (*flush)(struct iommu_table *tbl); + void (*free)(struct iommu_table *tbl); }; /* These are used by VIO */ @@ -148,6 +149,17 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, struct iommu_table_group; struct iommu_table_group_ops { + long (*create_table)(struct iommu_table_group *table_group, + int num, + __u32 page_shift, + __u64 window_size, + __u32 levels, + struct iommu_table *tbl); + long (*set_window)(struct iommu_table_group *table_group, + int num, + struct iommu_table *tblnew); + long (*unset_window)(struct iommu_table_group *table_group, + int num); /* * Switches ownership from the kernel itself to an external * user. While onwership is taken, the kernel cannot use IOMMU itself. @@ -160,6 +172,13 @@ struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif + /* Some key properties of IOMMU */ + __u32 tce32_start; + __u32 tce32_size; + __u64 pgsizes; /* Bitmap of supported page sizes */ + __u32 max_dynamic_windows_supported; + __u32 max_levels; With this information, table_group seems even more like a bad name. iommu_state maybe? Please, no. We will never come to agreement then :( And iommu_state is too general anyway, it won't pass. struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; struct iommu_table_group_ops *ops; }; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cc1d09c..4828837 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -24,6 +24,7 @@ #include linux/msi.h #include linux/memblock.h #include linux/iommu.h +#include linux/sizes.h #include asm/sections.h #include asm/io.h @@ -1846,6 +1847,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = { #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, + .free = pnv_pci_free_table, }; static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb, @@ -1936,6 +1938,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); tbl-it_ops = pnv_ioda1_iommu_ops; + pe-table_group.tce32_start = tbl-it_offset tbl-it_page_shift; + pe-table_group.tce32_size = tbl-it_size tbl-it_page_shift; iommu_init_table(tbl, phb-hose-node); if (pe-flags PNV_IODA_PE_DEV) { @@ -1961,7 +1965,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, } static long pnv_pci_ioda2_set_window(struct
Re: [PATCH kernel v9 23/32] powerpc/powernv/ioda: Define and implement DMA table/window management callbacks
On Wed, Apr 29, 2015 at 07:44:20PM +1000, Alexey Kardashevskiy wrote: On 04/29/2015 03:30 PM, David Gibson wrote: On Sat, Apr 25, 2015 at 10:14:47PM +1000, Alexey Kardashevskiy wrote: This extends iommu_table_group_ops by a set of callbacks to support dynamic DMA windows management. create_table() creates a TCE table with specific parameters. it receives iommu_table_group to know nodeid in order to allocate TCE table memory closer to the PHB. The exact format of allocated multi-level table might be also specific to the PHB model (not the case now though). This callback calculated the DMA window offset on a PCI bus from @num and stores it in a just created table. set_window() sets the window at specified TVT index + @num on PHB. unset_window() unsets the window from specified TVT. This adds a free() callback to iommu_table_ops to free the memory (potentially a tree of tables) allocated for the TCE table. Doesn't the free callback belong with the previous patch introducing multi-level tables? If I did that, you would say why is it here if nothing calls it on multilevel patch and I see the allocation but I do not see memory release ;) Yeah, fair enough ;) I need some rule of thumb here. I think it is a bit cleaner if the same patch adds a callback for memory allocation and its counterpart, no? On further consideration, yes, I think you're right. create_table() and free() are supposed to be called once per VFIO container and set_window()/unset_window() are supposed to be called for every group in a container. This adds IOMMU capabilities to iommu_table_group such as default 32bit window parameters and others. Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru --- arch/powerpc/include/asm/iommu.h| 19 arch/powerpc/platforms/powernv/pci-ioda.c | 75 ++--- arch/powerpc/platforms/powernv/pci-p5ioc2.c | 12 +++-- 3 files changed, 96 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 0f50ee2..7694546 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -70,6 +70,7 @@ struct iommu_table_ops { /* get() returns a physical address */ unsigned long (*get)(struct iommu_table *tbl, long index); void (*flush)(struct iommu_table *tbl); + void (*free)(struct iommu_table *tbl); }; /* These are used by VIO */ @@ -148,6 +149,17 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, struct iommu_table_group; struct iommu_table_group_ops { + long (*create_table)(struct iommu_table_group *table_group, + int num, + __u32 page_shift, + __u64 window_size, + __u32 levels, + struct iommu_table *tbl); + long (*set_window)(struct iommu_table_group *table_group, + int num, + struct iommu_table *tblnew); + long (*unset_window)(struct iommu_table_group *table_group, + int num); /* * Switches ownership from the kernel itself to an external * user. While onwership is taken, the kernel cannot use IOMMU itself. @@ -160,6 +172,13 @@ struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif + /* Some key properties of IOMMU */ + __u32 tce32_start; + __u32 tce32_size; + __u64 pgsizes; /* Bitmap of supported page sizes */ + __u32 max_dynamic_windows_supported; + __u32 max_levels; With this information, table_group seems even more like a bad name. iommu_state maybe? Please, no. We will never come to agreement then :( And iommu_state is too general anyway, it won't pass. struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; struct iommu_table_group_ops *ops; }; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cc1d09c..4828837 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -24,6 +24,7 @@ #include linux/msi.h #include linux/memblock.h #include linux/iommu.h +#include linux/sizes.h #include asm/sections.h #include asm/io.h @@ -1846,6 +1847,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = { #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, + .free = pnv_pci_free_table, }; static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb, @@ -1936,6 +1938,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); tbl-it_ops = pnv_ioda1_iommu_ops; + pe-table_group.tce32_start = tbl-it_offset tbl-it_page_shift; + pe-table_group.tce32_size = tbl-it_size tbl-it_page_shift; iommu_init_table(tbl, phb-hose-node); if (pe-flags PNV_IODA_PE_DEV) { @@ -1961,7 +1965,7 @@
Re: [PATCH kernel v9 23/32] powerpc/powernv/ioda: Define and implement DMA table/window management callbacks
On Sat, Apr 25, 2015 at 10:14:47PM +1000, Alexey Kardashevskiy wrote: This extends iommu_table_group_ops by a set of callbacks to support dynamic DMA windows management. create_table() creates a TCE table with specific parameters. it receives iommu_table_group to know nodeid in order to allocate TCE table memory closer to the PHB. The exact format of allocated multi-level table might be also specific to the PHB model (not the case now though). This callback calculated the DMA window offset on a PCI bus from @num and stores it in a just created table. set_window() sets the window at specified TVT index + @num on PHB. unset_window() unsets the window from specified TVT. This adds a free() callback to iommu_table_ops to free the memory (potentially a tree of tables) allocated for the TCE table. Doesn't the free callback belong with the previous patch introducing multi-level tables? create_table() and free() are supposed to be called once per VFIO container and set_window()/unset_window() are supposed to be called for every group in a container. This adds IOMMU capabilities to iommu_table_group such as default 32bit window parameters and others. Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru --- arch/powerpc/include/asm/iommu.h| 19 arch/powerpc/platforms/powernv/pci-ioda.c | 75 ++--- arch/powerpc/platforms/powernv/pci-p5ioc2.c | 12 +++-- 3 files changed, 96 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 0f50ee2..7694546 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -70,6 +70,7 @@ struct iommu_table_ops { /* get() returns a physical address */ unsigned long (*get)(struct iommu_table *tbl, long index); void (*flush)(struct iommu_table *tbl); + void (*free)(struct iommu_table *tbl); }; /* These are used by VIO */ @@ -148,6 +149,17 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, struct iommu_table_group; struct iommu_table_group_ops { + long (*create_table)(struct iommu_table_group *table_group, + int num, + __u32 page_shift, + __u64 window_size, + __u32 levels, + struct iommu_table *tbl); + long (*set_window)(struct iommu_table_group *table_group, + int num, + struct iommu_table *tblnew); + long (*unset_window)(struct iommu_table_group *table_group, + int num); /* * Switches ownership from the kernel itself to an external * user. While onwership is taken, the kernel cannot use IOMMU itself. @@ -160,6 +172,13 @@ struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif + /* Some key properties of IOMMU */ + __u32 tce32_start; + __u32 tce32_size; + __u64 pgsizes; /* Bitmap of supported page sizes */ + __u32 max_dynamic_windows_supported; + __u32 max_levels; With this information, table_group seems even more like a bad name. iommu_state maybe? struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; struct iommu_table_group_ops *ops; }; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cc1d09c..4828837 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -24,6 +24,7 @@ #include linux/msi.h #include linux/memblock.h #include linux/iommu.h +#include linux/sizes.h #include asm/sections.h #include asm/io.h @@ -1846,6 +1847,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = { #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, + .free = pnv_pci_free_table, }; static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb, @@ -1936,6 +1938,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); tbl-it_ops = pnv_ioda1_iommu_ops; + pe-table_group.tce32_start = tbl-it_offset tbl-it_page_shift; + pe-table_group.tce32_size = tbl-it_size tbl-it_page_shift; iommu_init_table(tbl, phb-hose-node); if (pe-flags PNV_IODA_PE_DEV) { @@ -1961,7 +1965,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, } static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group, - struct iommu_table *tbl) + int num, struct iommu_table *tbl) { struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, table_group); @@ -1972,9 +1976,10 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group, const __u64 start_addr = tbl-it_offset tbl-it_page_shift; const __u64 win_size =
[PATCH kernel v9 23/32] powerpc/powernv/ioda: Define and implement DMA table/window management callbacks
This extends iommu_table_group_ops by a set of callbacks to support dynamic DMA windows management. create_table() creates a TCE table with specific parameters. it receives iommu_table_group to know nodeid in order to allocate TCE table memory closer to the PHB. The exact format of allocated multi-level table might be also specific to the PHB model (not the case now though). This callback calculated the DMA window offset on a PCI bus from @num and stores it in a just created table. set_window() sets the window at specified TVT index + @num on PHB. unset_window() unsets the window from specified TVT. This adds a free() callback to iommu_table_ops to free the memory (potentially a tree of tables) allocated for the TCE table. create_table() and free() are supposed to be called once per VFIO container and set_window()/unset_window() are supposed to be called for every group in a container. This adds IOMMU capabilities to iommu_table_group such as default 32bit window parameters and others. Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru --- arch/powerpc/include/asm/iommu.h| 19 arch/powerpc/platforms/powernv/pci-ioda.c | 75 ++--- arch/powerpc/platforms/powernv/pci-p5ioc2.c | 12 +++-- 3 files changed, 96 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 0f50ee2..7694546 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -70,6 +70,7 @@ struct iommu_table_ops { /* get() returns a physical address */ unsigned long (*get)(struct iommu_table *tbl, long index); void (*flush)(struct iommu_table *tbl); + void (*free)(struct iommu_table *tbl); }; /* These are used by VIO */ @@ -148,6 +149,17 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, struct iommu_table_group; struct iommu_table_group_ops { + long (*create_table)(struct iommu_table_group *table_group, + int num, + __u32 page_shift, + __u64 window_size, + __u32 levels, + struct iommu_table *tbl); + long (*set_window)(struct iommu_table_group *table_group, + int num, + struct iommu_table *tblnew); + long (*unset_window)(struct iommu_table_group *table_group, + int num); /* * Switches ownership from the kernel itself to an external * user. While onwership is taken, the kernel cannot use IOMMU itself. @@ -160,6 +172,13 @@ struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif + /* Some key properties of IOMMU */ + __u32 tce32_start; + __u32 tce32_size; + __u64 pgsizes; /* Bitmap of supported page sizes */ + __u32 max_dynamic_windows_supported; + __u32 max_levels; + struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; struct iommu_table_group_ops *ops; }; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cc1d09c..4828837 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -24,6 +24,7 @@ #include linux/msi.h #include linux/memblock.h #include linux/iommu.h +#include linux/sizes.h #include asm/sections.h #include asm/io.h @@ -1846,6 +1847,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = { #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, + .free = pnv_pci_free_table, }; static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb, @@ -1936,6 +1938,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, TCE_PCI_SWINV_PAIR); tbl-it_ops = pnv_ioda1_iommu_ops; + pe-table_group.tce32_start = tbl-it_offset tbl-it_page_shift; + pe-table_group.tce32_size = tbl-it_size tbl-it_page_shift; iommu_init_table(tbl, phb-hose-node); if (pe-flags PNV_IODA_PE_DEV) { @@ -1961,7 +1965,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, } static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group, - struct iommu_table *tbl) + int num, struct iommu_table *tbl) { struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, table_group); @@ -1972,9 +1976,10 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group, 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 + pe_info(pe, Setting up window#%d at %llx..%llx pgsize=0x%x tablesize=0x%lx levels=%d levelsize=%x\n, + num,