[PATCH v3 4/6] powerpc/pseries/iommu: Remove default DMA window before creating DDW

[Alexey Kardashevskiy]

On 03/07/2020 16:18, Leonardo Bras wrote:
> On LoPAR "DMA Window Manipulation Calls", it's recommended to remove the
> default DMA window for the device, before attempting to configure a DDW,
> in order to make the maximum resources available for the next DDW to be
> created.
> 
> This is a requirement for using DDW on devices in which hypervisor
> allows only one DMA window.
> 
> If setting up a new DDW fails anywhere after the removal of this
> default DMA window, it's needed to restore the default DMA window.
> For this, an implementation of ibm,reset-pe-dma-windows rtas call is
> needed:
> 
> Platforms supporting the DDW option starting with LoPAR level 2.7 implement
> ibm,ddw-extensions. The first extension available (index 2) carries the
> token for ibm,reset-pe-dma-windows rtas call, which is used to restore
> the default DMA window for a device, if it has been deleted.
> 
> It does so by resetting the TCE table allocation for the PE to it's
> boot time value, available in "ibm,dma-window" device tree node.
> 
> Signed-off-by: Leonardo Bras <leobras.c at gmail.com>
> ---
>  arch/powerpc/platforms/pseries/iommu.c | 83 +++++++++++++++++++++-----
>  1 file changed, 69 insertions(+), 14 deletions(-)
> 
> diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
> index 4e33147825cc..5b520ac354c6 100644
> --- a/arch/powerpc/platforms/pseries/iommu.c
> +++ b/arch/powerpc/platforms/pseries/iommu.c
> @@ -1066,6 +1066,38 @@ static phys_addr_t ddw_memory_hotplug_max(void)
>  	return max_addr;
>  }
>  
> +/*
> + * Platforms supporting the DDW option starting with LoPAR level 2.7 implement
> + * ibm,ddw-extensions, which carries the rtas token for
> + * ibm,reset-pe-dma-windows.
> + * That rtas-call can be used to restore the default DMA window for the device.
> + */
> +static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
> +{
> +	int ret;
> +	u32 cfg_addr, reset_dma_win;
> +	u64 buid;
> +	struct device_node *dn;
> +	struct pci_dn *pdn;
> +
> +	ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win);
> +	if (ret)
> +		return;
> +
> +	dn = pci_device_to_OF_node(dev);
> +	pdn = PCI_DN(dn);
> +	buid = pdn->phb->buid;
> +	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
> +
> +	ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid),
> +			BUID_LO(buid));
> +	if (ret)
> +		dev_info(&dev->dev,
> +			 "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ",
> +			 reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
> +			 ret);
> +}
> +
>  /*
>   * If the PE supports dynamic dma windows, and there is space for a table
>   * that can map all pages in a linear offset, then setup such a table,
> @@ -1079,7 +1111,7 @@ static phys_addr_t ddw_memory_hotplug_max(void)
>   */
>  static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
>  {
> -	int len, ret;
> +	int len, ret, reset_win_ext;

Make it "reset_token".

>  	struct ddw_query_response query;
>  	struct ddw_create_response create;
>  	int page_shift;
> @@ -1087,7 +1119,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
>  	struct device_node *dn;
>  	u32 ddw_avail[DDW_APPLICABLE_SIZE];
>  	struct direct_window *window;
> -	struct property *win64;
> +	struct property *win64, *default_win = NULL;
>  	struct dynamic_dma_window_prop *ddwprop;
>  	struct failed_ddw_pdn *fpdn;
>  
> @@ -1122,7 +1154,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
>  	if (ret)
>  		goto out_failed;
>  
> -       /*
> +	/*
>  	 * Query if there is a second window of size to map the
>  	 * whole partition.  Query returns number of windows, largest
>  	 * block assigned to PE (partition endpoint), and two bitmasks
> @@ -1133,14 +1165,34 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
>  	if (ret != 0)
>  		goto out_failed;
>  
> +	/*
> +	 * If there is no window available, remove the default DMA window,
> +	 * if it's present. This will make all the resources available to the
> +	 * new DDW window.
> +	 * If anything fails after this, we need to restore it, so also check
> +	 * for extensions presence.
> +	 */
>  	if (query.windows_available == 0) {
> -		/*
> -		 * no additional windows are available for this device.
> -		 * We might be able to reallocate the existing window,
> -		 * trading in for a larger page size.
> -		 */
> -		dev_dbg(&dev->dev, "no free dynamic windows");
> -		goto out_failed;
> +		default_win = of_find_property(pdn, "ibm,dma-window", NULL);
> +		if (!default_win)
> +			goto out_failed;
> +
> +		reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL);
> +		if (reset_win_ext)
> +			goto out_failed;
> +
> +		remove_dma_window(pdn, ddw_avail, default_win);
> +
> +		/* Query again, to check if the window is available */
> +		ret = query_ddw(dev, ddw_avail, &query, pdn);
> +		if (ret != 0)
> +			goto out_restore_defwin;
> +
> +		if (query.windows_available == 0) {
> +			/* no windows are available for this device. */
> +			dev_dbg(&dev->dev, "no free dynamic windows");
> +			goto out_restore_defwin;
> +		}
>  	}
>  	if (query.page_size & 4) {
>  		page_shift = 24; /* 16MB */
> @@ -1151,7 +1203,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
>  	} else {
>  		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
>  			  query.page_size);
> -		goto out_failed;
> +		goto out_restore_defwin;
>  	}
>  	/* verify the window * number of ptes will map the partition */
>  	/* check largest block * page size > max memory hotplug addr */
> @@ -1160,14 +1212,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
>  		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu "
>  			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
>  			  1ULL << page_shift);
> -		goto out_failed;
> +		goto out_restore_defwin;
>  	}
>  	len = order_base_2(max_addr);
>  	win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
>  	if (!win64) {
>  		dev_info(&dev->dev,
>  			"couldn't allocate property for 64bit dma window\n");
> -		goto out_failed;
> +		goto out_restore_defwin;
>  	}
>  	win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL);
>  	win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL);
> @@ -1230,8 +1282,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
>  	kfree(win64->value);
>  	kfree(win64);
>  
> -out_failed:
> +out_restore_defwin:
> +	if (default_win && reset_win_ext == 0)


reset_win_ext potentially may be uninitialized here. Yeah I know it is
tied to default_win but still.

After looking at this function for a few minutes, it could use some
refactoring (way too many gotos)  such as:

1. move (query.page_size & xx) checks before "if
(query.windows_available == 0)"

2. move "win64 = kzalloc(sizeof(struct property), GFP_KERNEL)" before
"if (query.windows_available == 0)"

3. call "reset_dma_window(dev, pdn)" inside the "if
(query.windows_available == 0)" branch.

Then you can drop all "goto out_restore_defwin" and move default_win and
reset_win_ext inside "if (query.windows_available == 0)".

The rest of the series is good as it is, however it may conflict with
https://patchwork.ozlabs.org/project/linuxppc-dev/patch/20200713062348.100552-1-aik@ozlabs.ru/
and the patchset it is made on top of -
https://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=188385 .
thanks,


> +		reset_dma_window(dev, pdn);
>  
> +out_failed:
>  	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
>  	if (!fpdn)
>  		goto out_unlock;
> 

-- 
Alexey