Re: [PATCH kernel v8 04/10] powerpc/vfio_spapr_tce: Add reference counting to iommu_table
On Fri, 10 Mar 2017 14:53:31 +1100 Alexey Kardashevskiywrote: > So far iommu_table obejcts were only used in virtual mode and had > a single owner. We are going to change this by implementing in-kernel > acceleration of DMA mapping requests. The proposed acceleration > will handle requests in real mode and KVM will keep references to tables. > > This adds a kref to iommu_table and defines new helpers to update it. > This replaces iommu_free_table() with iommu_table_put() and makes > iommu_free_table() static. iommu_table_get() is not used in this patch > but it will be in the following patch. > > Since this touches prototypes, this also removes @node_name parameter as > it has never been really useful on powernv and carrying it for > the pseries platform code to iommu_free_table() seems to be quite > useless as well. > > This should cause no behavioral change. > > Signed-off-by: Alexey Kardashevskiy > Reviewed-by: David Gibson > --- > arch/powerpc/include/asm/iommu.h | 5 +++-- > arch/powerpc/kernel/iommu.c | 24 +++- > arch/powerpc/platforms/powernv/pci-ioda.c | 14 +++--- > arch/powerpc/platforms/powernv/pci.c | 1 + > arch/powerpc/platforms/pseries/iommu.c| 3 ++- > arch/powerpc/platforms/pseries/vio.c | 2 +- > drivers/vfio/vfio_iommu_spapr_tce.c | 2 +- > 7 files changed, 34 insertions(+), 17 deletions(-) > > diff --git a/arch/powerpc/include/asm/iommu.h > b/arch/powerpc/include/asm/iommu.h > index 4554699aec02..82e77ebf85f4 100644 > --- a/arch/powerpc/include/asm/iommu.h > +++ b/arch/powerpc/include/asm/iommu.h > @@ -119,6 +119,7 @@ struct iommu_table { > struct list_head it_group_list;/* List of iommu_table_group_link */ > unsigned long *it_userspace; /* userspace view of the table */ > struct iommu_table_ops *it_ops; > + struct krefit_kref; > }; > > #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \ > @@ -151,8 +152,8 @@ static inline void *get_iommu_table_base(struct device > *dev) > > extern int dma_iommu_dma_supported(struct device *dev, u64 mask); > > -/* Frees table for an individual device node */ > -extern void iommu_free_table(struct iommu_table *tbl, const char *node_name); > +extern void iommu_table_get(struct iommu_table *tbl); > +extern void iommu_table_put(struct iommu_table *tbl); > > /* Initializes an iommu_table based in values set in the passed-in > * structure > diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c > index bc142d87130f..d02b8d22fb50 100644 > --- a/arch/powerpc/kernel/iommu.c > +++ b/arch/powerpc/kernel/iommu.c > @@ -711,13 +711,13 @@ struct iommu_table *iommu_init_table(struct iommu_table > *tbl, int nid) > return tbl; > } > > -void iommu_free_table(struct iommu_table *tbl, const char *node_name) > +static void iommu_table_free(struct kref *kref) > { > unsigned long bitmap_sz; > unsigned int order; > + struct iommu_table *tbl; > > - if (!tbl) > - return; > + tbl = container_of(kref, struct iommu_table, it_kref); > > if (tbl->it_ops->free) > tbl->it_ops->free(tbl); > @@ -736,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char > *node_name) > > /* verify that table contains no entries */ > if (!bitmap_empty(tbl->it_map, tbl->it_size)) > - pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name); > + pr_warn("%s: Unexpected TCEs\n", __func__); > > /* calculate bitmap size in bytes */ > bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long); > @@ -748,7 +748,21 @@ void iommu_free_table(struct iommu_table *tbl, const > char *node_name) > /* free table */ > kfree(tbl); > } > -EXPORT_SYMBOL_GPL(iommu_free_table); > + > +void iommu_table_get(struct iommu_table *tbl) > +{ > + kref_get(>it_kref); > +} > +EXPORT_SYMBOL_GPL(iommu_table_get); > + > +void iommu_table_put(struct iommu_table *tbl) > +{ > + if (!tbl) > + return; > + > + kref_put(>it_kref, iommu_table_free); > +} > +EXPORT_SYMBOL_GPL(iommu_table_put); > Maybe an opportunity for less cringe worthy generic names exported from arch code. iommu_tce_table_get/put perhaps? > /* Creates TCEs for a user provided buffer. The user buffer must be > * contiguous real kernel storage (not vmalloc). The address passed here > diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c > b/arch/powerpc/platforms/powernv/pci-ioda.c > index 7916d0cb05fe..ec3e565de511 100644 > --- a/arch/powerpc/platforms/powernv/pci-ioda.c > +++ b/arch/powerpc/platforms/powernv/pci-ioda.c > @@ -1425,7 +1425,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev > *dev, struct pnv_ioda_pe > iommu_group_put(pe->table_group.group); > BUG_ON(pe->table_group.group); > } > - iommu_free_table(tbl,
[PATCH kernel v8 04/10] powerpc/vfio_spapr_tce: Add reference counting to iommu_table
So far iommu_table obejcts were only used in virtual mode and had a single owner. We are going to change this by implementing in-kernel acceleration of DMA mapping requests. The proposed acceleration will handle requests in real mode and KVM will keep references to tables. This adds a kref to iommu_table and defines new helpers to update it. This replaces iommu_free_table() with iommu_table_put() and makes iommu_free_table() static. iommu_table_get() is not used in this patch but it will be in the following patch. Since this touches prototypes, this also removes @node_name parameter as it has never been really useful on powernv and carrying it for the pseries platform code to iommu_free_table() seems to be quite useless as well. This should cause no behavioral change. Signed-off-by: Alexey KardashevskiyReviewed-by: David Gibson --- arch/powerpc/include/asm/iommu.h | 5 +++-- arch/powerpc/kernel/iommu.c | 24 +++- arch/powerpc/platforms/powernv/pci-ioda.c | 14 +++--- arch/powerpc/platforms/powernv/pci.c | 1 + arch/powerpc/platforms/pseries/iommu.c| 3 ++- arch/powerpc/platforms/pseries/vio.c | 2 +- drivers/vfio/vfio_iommu_spapr_tce.c | 2 +- 7 files changed, 34 insertions(+), 17 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 4554699aec02..82e77ebf85f4 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -119,6 +119,7 @@ struct iommu_table { struct list_head it_group_list;/* List of iommu_table_group_link */ unsigned long *it_userspace; /* userspace view of the table */ struct iommu_table_ops *it_ops; + struct krefit_kref; }; #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \ @@ -151,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev) extern int dma_iommu_dma_supported(struct device *dev, u64 mask); -/* Frees table for an individual device node */ -extern void iommu_free_table(struct iommu_table *tbl, const char *node_name); +extern void iommu_table_get(struct iommu_table *tbl); +extern void iommu_table_put(struct iommu_table *tbl); /* Initializes an iommu_table based in values set in the passed-in * structure diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index bc142d87130f..d02b8d22fb50 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -711,13 +711,13 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) return tbl; } -void iommu_free_table(struct iommu_table *tbl, const char *node_name) +static void iommu_table_free(struct kref *kref) { unsigned long bitmap_sz; unsigned int order; + struct iommu_table *tbl; - if (!tbl) - return; + tbl = container_of(kref, struct iommu_table, it_kref); if (tbl->it_ops->free) tbl->it_ops->free(tbl); @@ -736,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) /* verify that table contains no entries */ if (!bitmap_empty(tbl->it_map, tbl->it_size)) - pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name); + pr_warn("%s: Unexpected TCEs\n", __func__); /* calculate bitmap size in bytes */ bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long); @@ -748,7 +748,21 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) /* free table */ kfree(tbl); } -EXPORT_SYMBOL_GPL(iommu_free_table); + +void iommu_table_get(struct iommu_table *tbl) +{ + kref_get(>it_kref); +} +EXPORT_SYMBOL_GPL(iommu_table_get); + +void iommu_table_put(struct iommu_table *tbl) +{ + if (!tbl) + return; + + kref_put(>it_kref, iommu_table_free); +} +EXPORT_SYMBOL_GPL(iommu_table_put); /* Creates TCEs for a user provided buffer. The user buffer must be * contiguous real kernel storage (not vmalloc). The address passed here diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 7916d0cb05fe..ec3e565de511 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1425,7 +1425,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe iommu_group_put(pe->table_group.group); BUG_ON(pe->table_group.group); } - iommu_free_table(tbl, of_node_full_name(dev->dev.of_node)); + iommu_table_put(tbl); } static void pnv_ioda_release_vf_PE(struct pci_dev *pdev) @@ -2226,7 +2226,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(tce32_segsz * segs)); if (tbl) { pnv_pci_unlink_table_and_group(tbl, >table_group); -