From fb5a4315591dae307a65fc246ca80b5159d296e1 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Wed, 16 Aug 2023 11:32:21 +0900 Subject: dma-debug: don't call __dma_entry_alloc_check_leak() under free_entries_lock __dma_entry_alloc_check_leak() calls into printk -> serial console output (qcom geni) and grabs port->lock under free_entries_lock spin lock, which is a reverse locking dependency chain as qcom_geni IRQ handler can call into dma-debug code and grab free_entries_lock under port->lock. Move __dma_entry_alloc_check_leak() call out of free_entries_lock scope so that we don't acquire serial console's port->lock under it. Trimmed-down lockdep splat: The existing dependency chain (in reverse order) is: -> #2 (free_entries_lock){-.-.}-{2:2}: _raw_spin_lock_irqsave+0x60/0x80 dma_entry_alloc+0x38/0x110 debug_dma_map_page+0x60/0xf8 dma_map_page_attrs+0x1e0/0x230 dma_map_single_attrs.constprop.0+0x6c/0xc8 geni_se_rx_dma_prep+0x40/0xcc qcom_geni_serial_isr+0x310/0x510 __handle_irq_event_percpu+0x110/0x244 handle_irq_event_percpu+0x20/0x54 handle_irq_event+0x50/0x88 handle_fasteoi_irq+0xa4/0xcc handle_irq_desc+0x28/0x40 generic_handle_domain_irq+0x24/0x30 gic_handle_irq+0xc4/0x148 do_interrupt_handler+0xa4/0xb0 el1_interrupt+0x34/0x64 el1h_64_irq_handler+0x18/0x24 el1h_64_irq+0x64/0x68 arch_local_irq_enable+0x4/0x8 ____do_softirq+0x18/0x24 ... -> #1 (&port_lock_key){-.-.}-{2:2}: _raw_spin_lock_irqsave+0x60/0x80 qcom_geni_serial_console_write+0x184/0x1dc console_flush_all+0x344/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 register_console+0x230/0x38c uart_add_one_port+0x338/0x494 qcom_geni_serial_probe+0x390/0x424 platform_probe+0x70/0xc0 really_probe+0x148/0x280 __driver_probe_device+0xfc/0x114 driver_probe_device+0x44/0x100 __device_attach_driver+0x64/0xdc bus_for_each_drv+0xb0/0xd8 __device_attach+0xe4/0x140 device_initial_probe+0x1c/0x28 bus_probe_device+0x44/0xb0 device_add+0x538/0x668 of_device_add+0x44/0x50 of_platform_device_create_pdata+0x94/0xc8 of_platform_bus_create+0x270/0x304 of_platform_populate+0xac/0xc4 devm_of_platform_populate+0x60/0xac geni_se_probe+0x154/0x160 platform_probe+0x70/0xc0 ... -> #0 (console_owner){-...}-{0:0}: __lock_acquire+0xdf8/0x109c lock_acquire+0x234/0x284 console_flush_all+0x330/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 dma_entry_alloc+0xb4/0x110 debug_dma_map_sg+0xdc/0x2f8 __dma_map_sg_attrs+0xac/0xe4 dma_map_sgtable+0x30/0x4c get_pages+0x1d4/0x1e4 [msm] msm_gem_pin_pages_locked+0x38/0xac [msm] msm_gem_pin_vma_locked+0x58/0x88 [msm] msm_ioctl_gem_submit+0xde4/0x13ac [msm] drm_ioctl_kernel+0xe0/0x15c drm_ioctl+0x2e8/0x3f4 vfs_ioctl+0x30/0x50 ... Chain exists of: console_owner --> &port_lock_key --> free_entries_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(free_entries_lock); lock(&port_lock_key); lock(free_entries_lock); lock(console_owner); *** DEADLOCK *** Call trace: dump_backtrace+0xb4/0xf0 show_stack+0x20/0x30 dump_stack_lvl+0x60/0x84 dump_stack+0x18/0x24 print_circular_bug+0x1cc/0x234 check_noncircular+0x78/0xac __lock_acquire+0xdf8/0x109c lock_acquire+0x234/0x284 console_flush_all+0x330/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 dma_entry_alloc+0xb4/0x110 debug_dma_map_sg+0xdc/0x2f8 __dma_map_sg_attrs+0xac/0xe4 dma_map_sgtable+0x30/0x4c get_pages+0x1d4/0x1e4 [msm] msm_gem_pin_pages_locked+0x38/0xac [msm] msm_gem_pin_vma_locked+0x58/0x88 [msm] msm_ioctl_gem_submit+0xde4/0x13ac [msm] drm_ioctl_kernel+0xe0/0x15c drm_ioctl+0x2e8/0x3f4 vfs_ioctl+0x30/0x50 ... Reported-by: Rob Clark Signed-off-by: Sergey Senozhatsky Acked-by: Robin Murphy Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index f190651bcadd..06366acd27b0 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -637,15 +637,19 @@ static struct dma_debug_entry *__dma_entry_alloc(void) return entry; } -static void __dma_entry_alloc_check_leak(void) +/* + * This should be called outside of free_entries_lock scope to avoid potential + * deadlocks with serial consoles that use DMA. + */ +static void __dma_entry_alloc_check_leak(u32 nr_entries) { - u32 tmp = nr_total_entries % nr_prealloc_entries; + u32 tmp = nr_entries % nr_prealloc_entries; /* Shout each time we tick over some multiple of the initial pool */ if (tmp < DMA_DEBUG_DYNAMIC_ENTRIES) { pr_info("dma_debug_entry pool grown to %u (%u00%%)\n", - nr_total_entries, - (nr_total_entries / nr_prealloc_entries)); + nr_entries, + (nr_entries / nr_prealloc_entries)); } } @@ -656,8 +660,10 @@ static void __dma_entry_alloc_check_leak(void) */ static struct dma_debug_entry *dma_entry_alloc(void) { + bool alloc_check_leak = false; struct dma_debug_entry *entry; unsigned long flags; + u32 nr_entries; spin_lock_irqsave(&free_entries_lock, flags); if (num_free_entries == 0) { @@ -667,13 +673,17 @@ static struct dma_debug_entry *dma_entry_alloc(void) pr_err("debugging out of memory - disabling\n"); return NULL; } - __dma_entry_alloc_check_leak(); + alloc_check_leak = true; + nr_entries = nr_total_entries; } entry = __dma_entry_alloc(); spin_unlock_irqrestore(&free_entries_lock, flags); + if (alloc_check_leak) + __dma_entry_alloc_check_leak(nr_entries); + #ifdef CONFIG_STACKTRACE entry->stack_len = stack_trace_save(entry->stack_entries, ARRAY_SIZE(entry->stack_entries), -- cgit v1.2.3 From 2dcdf8c18d5c1835571bfa40f40ac134c8a1f0f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Aug 2023 11:25:25 +0200 Subject: dma-contiguous: fix the Kconfig entry for CONFIG_DMA_NUMA_CMA It makes no sense to expose CONFIG_DMA_NUMA_CMA if CONFIG_NUMA is not enabled, and random config options shouldn't be default unless there is a good reason. Replace the default NUMA with a depends on to fix both issues. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- kernel/dma/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 4c1e9a3c0ab6..f488997b0717 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -160,7 +160,7 @@ if DMA_CMA config DMA_NUMA_CMA bool "Enable separate DMA Contiguous Memory Area for NUMA Node" - default NUMA + depends on NUMA help Enable this option to get numa CMA areas so that NUMA devices can get local memory by DMA coherent APIs. -- cgit v1.2.3 From 765aa6b3a462ed69ddcb1c41a6f7f93b8abb7d43 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Aug 2023 11:22:59 +0200 Subject: dma-pool: remove a __maybe_unused label in atomic_pool_expand Move the #endif a line so that free_page label is only seen by the compile pass when actually used. Signed-off-by: Christoph Hellwig Reviewed-by: Chunhui He Reviewed-by: Robin Murphy --- kernel/dma/pool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 1acec2e22827..b481c48a31a6 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -135,9 +135,9 @@ encrypt_mapping: remove_mapping: #ifdef CONFIG_DMA_DIRECT_REMAP dma_common_free_remap(addr, pool_size); -#endif -free_page: __maybe_unused +free_page: __free_pages(page, order); +#endif out: return ret; } -- cgit v1.2.3 From f875db4f20f4ec2e4fa3b3be0e5081976e0b5dad Mon Sep 17 00:00:00 2001 From: Zhenhua Huang Date: Thu, 7 Sep 2023 16:03:56 +0800 Subject: Revert "dma-contiguous: check for memory region overlap" This reverts commit 3fa6456ebe13adab3ba1817c8e515a5b88f95dce. The Commit broke the CMA region creation through DT on arm64, as showed below logs with "memblock=debug": [ 0.000000] memblock_phys_alloc_range: 41943040 bytes align=0x200000 from=0x0000000000000000 max_addr=0x00000000ffffffff early_init_dt_alloc_reserved_memory_arch+0x34/0xa0 [ 0.000000] memblock_reserve: [0x00000000fd600000-0x00000000ffdfffff] memblock_alloc_range_nid+0xc0/0x19c [ 0.000000] Reserved memory: overlap with other memblock reserved region >From call flow, region we defined in DT was always reserved before entering into rmem_cma_setup. Also, rmem_cma_setup has one routine cma_init_reserved_mem to ensure the region was reserved. Checking the region not reserved here seems not correct. early_init_fdt_scan_reserved_mem: fdt_scan_reserved_mem __reserved_mem_reserve_reg early_init_dt_reserve_memory memblock_reserve(using “reg” prop case) fdt_init_reserved_mem __reserved_mem_alloc_size *early_init_dt_alloc_reserved_memory_arch* memblock_reserve(dynamic alloc case) __reserved_mem_init_node rmem_cma_setup(region overlap check here should always fail) Example DT can be used to reproduce issue: dump_mem: mem_dump_region { compatible = "shared-dma-pool"; alloc-ranges = <0x0 0x00000000 0x0 0xffffffff>; reusable; size = <0 0x2800000>; }; Signed-off-by: Zhenhua Huang --- kernel/dma/contiguous.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index 88c595e49e34..f005c66f378c 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -473,11 +473,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) return -EBUSY; } - if (memblock_is_region_reserved(rmem->base, rmem->size)) { - pr_info("Reserved memory: overlap with other memblock reserved region\n"); - return -EBUSY; - } - if (!of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; -- cgit v1.2.3