Re: [PATCH v4 15/21] powerpc/pci: Delay creating pci_dn

From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: Gavin Shan <gwshan@linux.vnet.ibm.com>, linuxppc-dev@lists.ozlabs.org
Cc: linux-pci@vger.kernel.org, benh@kernel.crashing.org, bhelgaas@google.com
Subject: Re: [PATCH v4 15/21] powerpc/pci: Delay creating pci_dn
Date: Sun, 10 May 2015 00:55:51 +1000	[thread overview]
Message-ID: <554E1FF7.5020203@ozlabs.ru> (raw)
In-Reply-To: <1430460188-31343-16-git-send-email-gwshan@linux.vnet.ibm.com>

On 05/01/2015 04:03 PM, Gavin Shan wrote:
> The pci_dn instances are allocated from memblock or bootmem when
> creating PCI controller (hoses) in setup_arch(). The PCI hotplug,
> which will be supported by proceeding patches, will release PCI
> device nodes and their corresponding pci_dn on unplugging event.
> The pci_dn instance memory chunks alloed from memblock or bootmem
> are hard to reused after being released.
>
> The patch delay creating pci_dn so that they can be allocated from
> slab. In turn, the memory chunks for them can be reused after being
> released without problem. The creation of eeh_dev instances, which
> depends on pci_dn, is delayed a bit as well.
>
> Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
> ---
>   arch/powerpc/include/asm/ppc-pci.h     |  1 -
>   arch/powerpc/kernel/eeh_dev.c          |  2 +-
>   arch/powerpc/kernel/pci_dn.c           | 40 +++++++++++++++++++---------------
>   arch/powerpc/platforms/maple/pci.c     | 35 +++++++++++++++++------------
>   arch/powerpc/platforms/pasemi/pci.c    |  3 ---
>   arch/powerpc/platforms/powermac/pci.c  | 39 ++++++++++++++++++++-------------
>   arch/powerpc/platforms/powernv/pci.c   |  3 ---
>   arch/powerpc/platforms/pseries/setup.c |  1 -
>   8 files changed, 68 insertions(+), 56 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
> index 4122a86..7388316 100644
> --- a/arch/powerpc/include/asm/ppc-pci.h
> +++ b/arch/powerpc/include/asm/ppc-pci.h
> @@ -40,7 +40,6 @@ void *traverse_pci_dn(struct pci_dn *root,
>   		      void *(*fn)(struct pci_dn *, void *),
>   		      void *data);
>
> -extern void pci_devs_phb_init(void);
>   extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
>
>   /* From rtas_pci.h */
> diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
> index aabba94..f33ce5b 100644
> --- a/arch/powerpc/kernel/eeh_dev.c
> +++ b/arch/powerpc/kernel/eeh_dev.c
> @@ -110,4 +110,4 @@ static int __init eeh_dev_phb_init(void)
>   	return 0;
>   }
>
> -core_initcall(eeh_dev_phb_init);
> +core_initcall_sync(eeh_dev_phb_init);
> diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
> index b3b4df9..d3833af 100644
> --- a/arch/powerpc/kernel/pci_dn.c
> +++ b/arch/powerpc/kernel/pci_dn.c
> @@ -277,7 +277,7 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
>   	struct device_node *parent;
>   	struct pci_dn *pdn;
>
> -	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
> +	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
>   	if (pdn == NULL)
>   		return NULL;
>   	dn->data = pdn;
> @@ -442,33 +442,37 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
>   	traverse_pci_devices(dn, update_dn_pci_info, phb);
>   }
>
> -/**
> +static void pci_dev_pdn_setup(struct pci_dev *pdev)
> +{
> +	struct pci_dn *pdn;
> +
> +	if (pdev->dev.archdata.pci_data)
> +		return;
> +
> +	/* Setup the fast path */
> +	pdn = pci_get_pdn(pdev);
> +	pdev->dev.archdata.pci_data = pdn;
> +}
> +DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup);

How does moving of the chunk above help to "Delay creating pci_dn"?

> +
> +/*
>    * pci_devs_phb_init - Initialize phbs and pci devs under them.
> - *
> - * This routine walks over all phb's (pci-host bridges) on the
> - * system, and sets up assorted pci-related structures
> + *
> + * This routine walks over all phb's (pci-host bridges) on
> + * the system, and sets up assorted pci-related structures
>    * (including pci info in the device node structs) for each
>    * pci device found underneath.  This routine runs once,
>    * early in the boot sequence.
>    */
> -void __init pci_devs_phb_init(void)
> +static int __init pci_devs_phb_init(void)
>   {
>   	struct pci_controller *phb, *tmp;
>
>   	/* This must be done first so the device nodes have valid pci info! */
>   	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
>   		pci_devs_phb_init_dynamic(phb);
> -}
> -
> -static void pci_dev_pdn_setup(struct pci_dev *pdev)
> -{
> -	struct pci_dn *pdn;
>
> -	if (pdev->dev.archdata.pci_data)
> -		return;
> -
> -	/* Setup the fast path */
> -	pdn = pci_get_pdn(pdev);
> -	pdev->dev.archdata.pci_data = pdn;
> +	return 0;
>   }
> -DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup);
> +
> +core_initcall(pci_devs_phb_init);
> diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
> index a923230..04a69a8 100644
> --- a/arch/powerpc/platforms/maple/pci.c
> +++ b/arch/powerpc/platforms/maple/pci.c
> @@ -568,6 +568,26 @@ void maple_pci_irq_fixup(struct pci_dev *dev)
>   	DBG(" <- maple_pci_irq_fixup\n");
>   }
>
> +static int maple_pci_root_bridge_prepare(struct pci_host_bridge *bridge)
> +{
> +	struct pci_controller *hose = pci_bus_to_host(bridge->bus);
> +	struct device_node *np, *child;
> +
> +	if (hose != u3_agp)
> +		return 0;
> +
> +	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
> +	 * assume there is no P2P bridge on the AGP bus, which should be a
> +	 * safe assumptions hopefully.
> +	 */
> +	np = hose->dn;
> +	PCI_DN(np)->busno = 0xf0;
> +	for_each_child_of_node(np, child)
> +		PCI_DN(child)->busno = 0xf0;
> +
> +	return 0;
> +}
> +
>   void __init maple_pci_init(void)
>   {
>   	struct device_node *np, *root;
> @@ -605,20 +625,7 @@ void __init maple_pci_init(void)
>   	if (ht && maple_add_bridge(ht) != 0)
>   		of_node_put(ht);
>
> -	/* Setup the linkage between OF nodes and PHBs */
> -	pci_devs_phb_init();
> -
> -	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
> -	 * assume there is no P2P bridge on the AGP bus, which should be a
> -	 * safe assumptions hopefully.
> -	 */
> -	if (u3_agp) {
> -		struct device_node *np = u3_agp->dn;
> -		PCI_DN(np)->busno = 0xf0;
> -		for (np = np->child; np; np = np->sibling)
> -			PCI_DN(np)->busno = 0xf0;
> -	}
> -
> +	ppc_md.pcibios_root_bridge_prepare = maple_pci_root_bridge_prepare;
>   	/* Tell pci.c to not change any resource allocations.  */
>   	pci_add_flags(PCI_PROBE_ONLY);
>   }
> diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c
> index f3a68a0..10c4e8f 100644
> --- a/arch/powerpc/platforms/pasemi/pci.c
> +++ b/arch/powerpc/platforms/pasemi/pci.c
> @@ -229,9 +229,6 @@ void __init pas_pci_init(void)
>   			of_node_get(np);
>
>   	of_node_put(root);
> -
> -	/* Setup the linkage between OF nodes and PHBs */
> -	pci_devs_phb_init();
>   }
>
>   void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset)
> diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
> index 59ab16f..368716f 100644
> --- a/arch/powerpc/platforms/powermac/pci.c
> +++ b/arch/powerpc/platforms/powermac/pci.c
> @@ -878,6 +878,29 @@ void pmac_pci_irq_fixup(struct pci_dev *dev)
>   #endif /* CONFIG_PPC32 */
>   }
>
> +#ifdef CONFIG_PPC64
> +static int pmac_pci_root_bridge_prepare(struct pci_hot_bridge *bridge)
> +{
> +	struct pci_controller *hose = pci_bus_to_host(bridge->bus);
> +	struct device_node *np, *child;
> +
> +	if (hose != u3_agp)
> +		return 0;
> +
> +	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
> +	 * assume there is no P2P bridge on the AGP bus, which should be a
> +	 * safe assumptions for now. We should do something better in the
> +	 * future though
> +	 */
> +	np = hose->dn;
> +	PCI_DN(np)->busno = 0xf0;
> +	for_each_child_of_node(np, child)
> +		PCI_DN(child)->busno = 0xf0;
> +
> +	return 0;
> +}
> +#endif /* CONFIG_PPC64 */
> +
>   void __init pmac_pci_init(void)
>   {
>   	struct device_node *np, *root;
> @@ -914,22 +937,8 @@ void __init pmac_pci_init(void)
>   	if (ht && pmac_add_bridge(ht) != 0)
>   		of_node_put(ht);
>
> -	/* Setup the linkage between OF nodes and PHBs */
> -	pci_devs_phb_init();
> -
> -	/* Fixup the PCI<->OF mapping for U3 AGP due to bus renumbering. We
> -	 * assume there is no P2P bridge on the AGP bus, which should be a
> -	 * safe assumptions for now. We should do something better in the
> -	 * future though
> -	 */
> -	if (u3_agp) {
> -		struct device_node *np = u3_agp->dn;
> -		PCI_DN(np)->busno = 0xf0;
> -		for (np = np->child; np; np = np->sibling)
> -			PCI_DN(np)->busno = 0xf0;
> -	}
>   	/* pmac_check_ht_link(); */
> -
> +	ppc_md.pcibios_root_bridge_prepare = pmac_pci_root_bridge_prepare;
>   #else /* CONFIG_PPC64 */
>   	init_p2pbridge();
>   	init_second_ohare();
> diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
> index 60e6d65..21a4eb3 100644
> --- a/arch/powerpc/platforms/powernv/pci.c
> +++ b/arch/powerpc/platforms/powernv/pci.c
> @@ -819,9 +819,6 @@ void __init pnv_pci_init(void)
>   	for_each_compatible_node(np, NULL, "ibm,ioda2-phb")
>   		pnv_pci_init_ioda2_phb(np);
>
> -	/* Setup the linkage between OF nodes and PHBs */
> -	pci_devs_phb_init();
> -
>   	/* Configure IOMMU DMA hooks */
>   	ppc_md.tce_build = pnv_tce_build_vm;
>   	ppc_md.tce_free = pnv_tce_free_vm;
> diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
> index df6a704..5f80758 100644
> --- a/arch/powerpc/platforms/pseries/setup.c
> +++ b/arch/powerpc/platforms/pseries/setup.c
> @@ -482,7 +482,6 @@ static void __init find_and_init_phbs(void)
>   	}
>
>   	of_node_put(root);
> -	pci_devs_phb_init();
>
>   	/*
>   	 * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties
>

-- 
Alexey