Re: [PATCH kernel v10 28/34] vfio: powerpc/spapr: powerpc/powernv/ioda: Define and implement DMA windows API

[Alex Williamson <alex.williamson@redhat.com>]

On Tue, 2015-05-12 at 01:39 +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.
> 
> 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. This makes use of new values in
> vfio_iommu_spapr_tce. IODA1/P5IOC2 do not support DDW so they do not
> advertise pagemasks to the userspace.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
> Changes:
> v10:
> * squashed "vfio: powerpc/spapr: Use 32bit DMA window properties from table_group"
> into this
> * shortened the subject
> 
> v9:
> * new in the series - to make the next patch simpler
> ---
>  arch/powerpc/include/asm/iommu.h            | 19 ++++++
>  arch/powerpc/platforms/powernv/pci-ioda.c   | 96 ++++++++++++++++++++++++++---
>  arch/powerpc/platforms/powernv/pci-p5ioc2.c |  7 ++-
>  drivers/vfio/vfio_iommu_spapr_tce.c         | 19 +++---
>  4 files changed, 124 insertions(+), 17 deletions(-)

For vfio:

Acked-by: Alex Williamson <alex.williamson@redhat.com>

> 
> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
> index a902159..2c41115 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 */
> @@ -150,6 +151,17 @@ 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 **ptbl);
> +	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);
>  	/* Switch ownership from platform code to external user (e.g. VFIO) */
>  	void (*take_ownership)(struct iommu_table_group *table_group);
>  	/* Switch ownership from external user (e.g. VFIO) back to core */
> @@ -163,6 +175,13 @@ struct iommu_table_group_link {
>  };
>  
>  struct iommu_table_group {
> +	/* IOMMU properties */
> +	__u32 tce32_start;
> +	__u32 tce32_size;
> +	__u64 pgsizes; /* Bitmap of supported page sizes */
> +	__u32 max_dynamic_windows_supported;
> +	__u32 max_levels;
> +
>  	struct iommu_group *group;
>  	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 d2a1dcd..c1d1aef 100644
> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> @@ -25,6 +25,7 @@
>  #include <linux/memblock.h>
>  #include <linux/iommu.h>
>  #include <linux/rculist.h>
> +#include <linux/sizes.h>
>  
>  #include <asm/sections.h>
>  #include <asm/io.h>
> @@ -1867,6 +1868,12 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
>  		pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
>  }
>  
> +static void pnv_ioda2_table_free(struct iommu_table *tbl)
> +{
> +	pnv_pci_ioda2_table_free_pages(tbl);
> +	iommu_free_table(tbl, "pnv");
> +}
> +
>  static struct iommu_table_ops pnv_ioda2_iommu_ops = {
>  	.set = pnv_ioda2_tce_build,
>  #ifdef CONFIG_IOMMU_API
> @@ -1874,6 +1881,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = {
>  #endif
>  	.clear = pnv_ioda2_tce_free,
>  	.get = pnv_tce_get,
> +	.free = pnv_ioda2_table_free,
>  };
>  
>  static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb,
> @@ -1960,6 +1968,8 @@ 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) {
> @@ -1998,7 +2008,7 @@ 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 %llx..%llx pg=%x\n",
> +	pe_info(pe, "Setting up window#%d %llx..%llx pg=%x\n", num,
>  			start_addr, start_addr + win_size - 1,
>  			1UL << tbl->it_page_shift);
>  
> @@ -2008,7 +2018,7 @@ 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,
> +			(pe->pe_number << 1) + num,
>  			tbl->it_indirect_levels + 1,
>  			__pa(tbl->it_base),
>  			size << 3,
> @@ -2054,6 +2064,66 @@ static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
>  }
>  
>  #ifdef CONFIG_IOMMU_API
> +static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
> +		__u32 page_shift, __u64 window_size, __u32 levels,
> +		struct iommu_table *tbl);
> +
> +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 **ptbl)
> +{
> +	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
> +			table_group);
> +	int nid = pe->phb->hose->node;
> +	__u64 bus_offset = num ? pe->tce_bypass_base : table_group->tce32_start;
> +	long ret;
> +	struct iommu_table *tbl;
> +
> +	tbl = pnv_pci_table_alloc(nid);
> +	if (!tbl)
> +		return -ENOMEM;
> +
> +	ret = pnv_pci_ioda2_table_alloc_pages(nid,
> +			bus_offset, page_shift, window_size,
> +			levels, tbl);
> +	if (ret) {
> +		iommu_free_table(tbl, "pnv");
> +		return ret;
> +	}
> +
> +	tbl->it_ops = &pnv_ioda2_iommu_ops;
> +	if (pe->tce_inval_reg)
> +		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
> +
> +	*ptbl = tbl;
> +
> +	return 0;
> +}
> +
> +static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
> +		int num)
> +{
> +	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
> +			table_group);
> +	struct pnv_phb *phb = pe->phb;
> +	long ret;
> +
> +	pe_info(pe, "Removing DMA window #%d\n", num);
> +
> +	ret = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
> +			(pe->pe_number << 1) + num,
> +			0/* levels */, 0/* table address */,
> +			0/* table size */, 0/* page size */);
> +	if (ret)
> +		pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
> +	else
> +		pnv_pci_ioda2_tvt_invalidate(pe);
> +
> +	pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
> +
> +	return ret;
> +}
> +
>  static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
>  {
>  	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
> @@ -2073,6 +2143,9 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
>  }
>  
>  static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
> +	.create_table = pnv_pci_ioda2_create_table,
> +	.set_window = pnv_pci_ioda2_set_window,
> +	.unset_window = pnv_pci_ioda2_unset_window,
>  	.take_ownership = pnv_ioda2_take_ownership,
>  	.release_ownership = pnv_ioda2_release_ownership,
>  };
> @@ -2207,7 +2280,7 @@ static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl)
>  static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
>  				       struct pnv_ioda_pe *pe)
>  {
> -	struct iommu_table *tbl;
> +	struct iommu_table *tbl = NULL;
>  	int64_t rc;
>  
>  	/* We shouldn't already have a 32-bit DMA associated */
> @@ -2217,10 +2290,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
>  	/* TVE #1 is selected by PCI address bit 59 */
>  	pe->tce_bypass_base = 1ull << 59;
>  
> -	tbl = pnv_pci_table_alloc(phb->hose->node);
>  	iommu_register_group(&pe->table_group, phb->hose->global_number,
>  			pe->pe_number);
> -	pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
>  
>  	pnv_pci_ioda_setup_opal_tce_kill(phb, pe);
>  
> @@ -2230,13 +2301,22 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
>  		phb->ioda.m32_pci_base);
>  
>  	/* Setup linux iommu table */
> -	rc = pnv_pci_ioda2_table_alloc_pages(pe->phb->hose->node,
> -			0, IOMMU_PAGE_SHIFT_4K, phb->ioda.m32_pci_base,
> -			POWERNV_IOMMU_DEFAULT_LEVELS, tbl);
> +	pe->table_group.tce32_start = 0;
> +	pe->table_group.tce32_size = phb->ioda.m32_pci_base;
> +	pe->table_group.max_dynamic_windows_supported =
> +			IOMMU_TABLE_GROUP_MAX_TABLES;
> +	pe->table_group.max_levels = POWERNV_IOMMU_MAX_LEVELS;
> +	pe->table_group.pgsizes = SZ_4K | SZ_64K | SZ_16M;
> +
> +	rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
> +			IOMMU_PAGE_SHIFT_4K,
> +			pe->table_group.tce32_size,
> +			POWERNV_IOMMU_DEFAULT_LEVELS, &tbl);
>  	if (rc) {
>  		pe_err(pe, "Failed to create 32-bit TCE table, err %ld", rc);
>  		goto fail;
>  	}
> +	pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
>  
>  	tbl->it_ops = &pnv_ioda2_iommu_ops;
>  	iommu_init_table(tbl, phb->hose->node);
> diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
> index 94c880c..a295660 100644
> --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
> +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
> @@ -119,6 +119,8 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
>  	u64 phb_id;
>  	int64_t rc;
>  	static int primary = 1;
> +	struct iommu_table_group *table_group;
> +	struct iommu_table *tbl;
>  
>  	pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name);
>  
> @@ -193,7 +195,10 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
>  	 * hotplug or SRIOV on P5IOC2 and therefore iommu_free_table()
>  	 * should not be called for phb->p5ioc2.table_group.tables[0] ever.
>  	 */
> -	phb->p5ioc2.table_group.tables[0] = &phb->p5ioc2.iommu_table;
> +	tbl = phb->p5ioc2.table_group.tables[0] = &phb->p5ioc2.iommu_table;
> +	table_group = &phb->p5ioc2.table_group;
> +	table_group->tce32_start = tbl->it_offset << tbl->it_page_shift;
> +	table_group->tce32_size = tbl->it_size << tbl->it_page_shift;
>  }
>  
>  void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> index 0724ec8..bc4956d 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -135,7 +135,6 @@ static int tce_iommu_enable(struct tce_container *container)
>  {
>  	int ret = 0;
>  	unsigned long locked;
> -	struct iommu_table *tbl;
>  	struct iommu_table_group *table_group;
>  
>  	if (!container->grp)
> @@ -171,13 +170,19 @@ static int tce_iommu_enable(struct tce_container *container)
>  	 * this is that we cannot tell here the amount of RAM used by the guest
>  	 * as this information is only available from KVM and VFIO is
>  	 * KVM agnostic.
> +	 *
> +	 * So we do not allow enabling a container without a group attached
> +	 * as there is no way to know how much we should increment
> +	 * the locked_vm counter.
>  	 */
>  	table_group = iommu_group_get_iommudata(container->grp);
>  	if (!table_group)
>  		return -ENODEV;
>  
> -	tbl = table_group->tables[0];
> -	locked = (tbl->it_size << tbl->it_page_shift) >> PAGE_SHIFT;
> +	if (!table_group->tce32_size)
> +		return -EPERM;
> +
> +	locked = table_group->tce32_size >> PAGE_SHIFT;
>  	ret = try_increment_locked_vm(locked);
>  	if (ret)
>  		return ret;
> @@ -350,7 +355,6 @@ static long tce_iommu_ioctl(void *iommu_data,
>  
>  	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
>  		struct vfio_iommu_spapr_tce_info info;
> -		struct iommu_table *tbl;
>  		struct iommu_table_group *table_group;
>  
>  		if (WARN_ON(!container->grp))
> @@ -358,8 +362,7 @@ static long tce_iommu_ioctl(void *iommu_data,
>  
>  		table_group = iommu_group_get_iommudata(container->grp);
>  
> -		tbl = table_group->tables[0];
> -		if (WARN_ON_ONCE(!tbl))
> +		if (!table_group)
>  			return -ENXIO;
>  
>  		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
> @@ -371,8 +374,8 @@ static long tce_iommu_ioctl(void *iommu_data,
>  		if (info.argsz < minsz)
>  			return -EINVAL;
>  
> -		info.dma32_window_start = tbl->it_offset << tbl->it_page_shift;
> -		info.dma32_window_size = tbl->it_size << tbl->it_page_shift;
> +		info.dma32_window_start = table_group->tce32_start;
> +		info.dma32_window_size = table_group->tce32_size;
>  		info.flags = 0;
>  
>  		if (copy_to_user((void __user *)arg, &info, minsz))