Also, in the $SUBJECT, s/numa/NUMA because that's an acronym not
an English word.
Here:
"ACPI/IORT: Reject platform device creation on NUMA node mapping failure"
Thanks,
Lorenzo
On Fri, Mar 29, 2019 at 11:17:51AM +0800, Kefeng Wang wrote:
> If there is only node 0 in system, but smmuv3 device is set to offline
> node 1, parsed from proximity domain in SMMUv3 IORT table, it will lead
> to following crash,
>
> [ 47.492451] Unable to handle kernel paging request at virtual address 0000000000001388
> [ 47.500361] Mem abort info:
> [ 47.503143] ESR = 0x96000004
> [ 47.506189] Exception class = DABT (current EL), IL = 32 bits
> [ 47.512099] SET = 0, FnV = 0
> [ 47.515140] EA = 0, S1PTW = 0
> [ 47.518272] Data abort info:
> [ 47.521144] ISV = 0, ISS = 0x00000004
> [ 47.524970] CM = 0, WnR = 0
> [ 47.527929] [0000000000001388] user address but active_mm is swapper
> [ 47.534285] Internal error: Oops: 96000004 [#1] SMP
> [ 47.539151] Modules linked in:
> [ 47.542194] CPU: 5 PID: 1 Comm: swapper/0 Not tainted 5.0.0 #15
> [ 47.549490] pstate: 80c00009 (Nzcv daif +PAN +UAO)
> [ 47.554272] pc : __alloc_pages_nodemask+0x13c/0x1068
> [ 47.559224] lr : __alloc_pages_nodemask+0xdc/0x1068
> ...
> [ 47.646873] Process swapper/0 (pid: 1, stack limit = 0x(____ptrval____))
> [ 47.653560] Call trace:
> [ 47.655994] __alloc_pages_nodemask+0x13c/0x1068
> [ 47.660600] new_slab+0xec/0x570
> [ 47.663816] ___slab_alloc+0x3e0/0x4f8
> [ 47.667553] __slab_alloc+0x60/0x80
> [ 47.671029] __kmalloc_node_track_caller+0x10c/0x478
> [ 47.675984] devm_kmalloc+0x44/0xb0
> [ 47.679460] pinctrl_bind_pins+0x4c/0x188
> [ 47.683457] really_probe+0x78/0x2b8
> [ 47.687019] driver_probe_device+0x64/0x110
> [ 47.691189] device_driver_attach+0x74/0x98
> [ 47.695360] __driver_attach+0x9c/0xe8
> [ 47.699095] bus_for_each_dev+0x84/0xd8
> [ 47.702919] driver_attach+0x30/0x40
> [ 47.706481] bus_add_driver+0x170/0x218
> [ 47.710304] driver_register+0x64/0x118
> [ 47.714128] __platform_driver_register+0x54/0x60
> [ 47.718820] arm_smmu_driver_init+0x24/0x2c
> [ 47.722991] do_one_initcall+0xbc/0x328
> [ 47.726816] kernel_init_freeable+0x304/0x3ac
> [ 47.731162] kernel_init+0x18/0x110
> [ 47.734638] ret_from_fork+0x10/0x1c
> [ 47.738202] Code: f90013b5 b9410fa1 1a9f0694 b50014c2 (b9400804)
> [ 47.744307] ---[ end trace dfeaed4c373a32da ]--
>
> This could be triggered by firmware bug with bad IORT configuration,
> or a NUMA node has no memory attaching to it, also with NR_CPUS less
> than CPUs presented in MADT.
>
> Make dev_set_proximity() with a return value, terminating device creation
> if it return failure.
>
> Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
> ---
> drivers/acpi/arm64/iort.c | 18 +++++++++++++-----
> 1 file changed, 13 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
> index e48894e002ba..1fc1851b078e 100644
> --- a/drivers/acpi/arm64/iort.c
> +++ b/drivers/acpi/arm64/iort.c
> @@ -1232,18 +1232,23 @@ static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
> /*
> * set numa proximity domain for smmuv3 device
> */
> -static void __init arm_smmu_v3_set_proximity(struct device *dev,
> +static int __init arm_smmu_v3_set_proximity(struct device *dev,
> struct acpi_iort_node *node)
> {
> struct acpi_iort_smmu_v3 *smmu;
>
> smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
> if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) {
> - set_dev_node(dev, acpi_map_pxm_to_node(smmu->pxm));
> + int node = acpi_map_pxm_to_node(smmu->pxm);
> + if (node != NUMA_NO_NODE && !node_online(node))
> + return -EINVAL;
> +
> + set_dev_node(dev, node);
> pr_info("SMMU-v3[%llx] Mapped to Proximity domain %d\n",
> smmu->base_address,
> smmu->pxm);
> }
> + return 0;
> }
> #else
> #define arm_smmu_v3_set_proximity NULL
> @@ -1318,7 +1323,7 @@ struct iort_dev_config {
> int (*dev_count_resources)(struct acpi_iort_node *node);
> void (*dev_init_resources)(struct resource *res,
> struct acpi_iort_node *node);
> - void (*dev_set_proximity)(struct device *dev,
> + int (*dev_set_proximity)(struct device *dev,
> struct acpi_iort_node *node);
> };
>
> @@ -1369,8 +1374,11 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
> if (!pdev)
> return -ENOMEM;
>
> - if (ops->dev_set_proximity)
> - ops->dev_set_proximity(&pdev->dev, node);
> + if (ops->dev_set_proximity) {
> + ret = ops->dev_set_proximity(&pdev->dev, node);
> + if (ret)
> + goto dev_put;
> + }
>
> count = ops->dev_count_resources(node);
>
> --
> 2.20.1
>
