From 497a92308af8e9385fa3d135f7f416a997e4b93b Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 15 May 2014 16:59:34 +0200 Subject: [PATCH] ARM: mvebu: implement L2/PCIe deadlock workaround The Marvell Armada 375 and Armada 38x SOCs, which use the Cortex-A9 CPU core, the PL310 cache and the Marvell PCIe hardware block are affected a L2/PCIe deadlock caused by a system erratum when hardware I/O coherency is used. This deadlock can be avoided by mapping the PCIe memory areas as strongly-ordered (note: MT_UNCACHED is strongly-ordered), and by removing the outer cache sync done in software. This is implemented in this patch by: * Registering a custom arch_ioremap_caller function that allows to make sure PCI memory regions are mapped MT_UNCACHED. * Adding at runtime the 'arm,io-coherent' property to the PL310 cache controller. This cannot be done permanently in the DT, because the hardware I/O coherency can only be enabled when CONFIG_SMP is enabled, in the current kernel situation. Signed-off-by: Thomas Petazzoni Link: https://lkml.kernel.org/r/1400165974-9059-4-git-send-email-thomas.petazzoni@free-electrons.com Signed-off-by: Jason Cooper --- arch/arm/mach-mvebu/coherency.c | 39 +++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 5723178f6589..a2225070ac3d 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "armada-370-xp.h" #include "coherency.h" #include "mvebu-soc-id.h" @@ -309,9 +310,47 @@ static void __init armada_370_coherency_init(struct device_node *np) set_cpu_coherent(); } +/* + * This ioremap hook is used on Armada 375/38x to ensure that PCIe + * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This + * is needed as a workaround for a deadlock issue between the PCIe + * interface and the cache controller. + */ +static void __iomem * +armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, + unsigned int mtype, void *caller) +{ + struct resource pcie_mem; + + mvebu_mbus_get_pcie_mem_aperture(&pcie_mem); + + if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end) + mtype = MT_UNCACHED; + + return __arm_ioremap_caller(phys_addr, size, mtype, caller); +} + static void __init armada_375_380_coherency_init(struct device_node *np) { + struct device_node *cache_dn; + coherency_cpu_base = of_iomap(np, 0); + arch_ioremap_caller = armada_pcie_wa_ioremap_caller; + + /* + * Add the PL310 property "arm,io-coherent". This makes sure the + * outer sync operation is not used, which allows to + * workaround the system erratum that causes deadlocks when + * doing PCIe in an SMP situation on Armada 375 and Armada + * 38x. + */ + for_each_compatible_node(cache_dn, NULL, "arm,pl310-cache") { + struct property *p; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + p->name = kstrdup("arm,io-coherent", GFP_KERNEL); + of_add_property(cache_dn, p); + } } static int coherency_type(void) -- 2.20.1