From 819403c893551c5e93bf9087d334e01bcab5c6b9 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 4 Dec 2024 13:54:36 +0100 Subject: fs/proc/vmcore: move vmcore definitions out of kcore.h These vmcore defines are not related to /proc/kcore, move them out. We'll move "struct vmcoredd_node" to vmcore.c, because it is only used internally. While "struct vmcore" is only used internally for now, we're planning on using it from inline functions in crash_dump.h next, so move it to crash_dump.h. While at it, rename "struct vmcore" to "struct vmcore_range", which is a more suitable name and will make the usage of it outside of vmcore.c clearer. Signed-off-by: David Hildenbrand Message-Id: <20241204125444.1734652-6-david@redhat.com> Acked-by: Andrew Morton Signed-off-by: Michael S. Tsirkin --- include/linux/crash_dump.h | 7 +++++++ include/linux/kcore.h | 13 ------------- 2 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index acc55626afdc..788a45061f35 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -114,6 +114,13 @@ struct vmcore_cb { extern void register_vmcore_cb(struct vmcore_cb *cb); extern void unregister_vmcore_cb(struct vmcore_cb *cb); +struct vmcore_range { + struct list_head list; + unsigned long long paddr; + unsigned long long size; + loff_t offset; +}; + #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 86c0f1d18998..9a2fa013c91d 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -20,19 +20,6 @@ struct kcore_list { int type; }; -struct vmcore { - struct list_head list; - unsigned long long paddr; - unsigned long long size; - loff_t offset; -}; - -struct vmcoredd_node { - struct list_head list; /* List of dumps */ - void *buf; /* Buffer containing device's dump */ - unsigned int size; /* Size of the buffer */ -}; - #ifdef CONFIG_PROC_KCORE void __init kclist_add(struct kcore_list *, void *, size_t, int type); -- cgit v1.2.3 From e017b1f4aa4eb887ee85fe13862206c0d31344b4 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 4 Dec 2024 13:54:37 +0100 Subject: fs/proc/vmcore: factor out allocating a vmcore range and adding it to a list Let's factor it out into include/linux/crash_dump.h, from where we can use it also outside of vmcore.c later. Acked-by: Baoquan He Signed-off-by: David Hildenbrand Message-Id: <20241204125444.1734652-7-david@redhat.com> Acked-by: Andrew Morton Signed-off-by: Michael S. Tsirkin --- include/linux/crash_dump.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 788a45061f35..9717912ce4d1 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -121,6 +121,20 @@ struct vmcore_range { loff_t offset; }; +/* Allocate a vmcore range and add it to the list. */ +static inline int vmcore_alloc_add_range(struct list_head *list, + unsigned long long paddr, unsigned long long size) +{ + struct vmcore_range *m = kzalloc(sizeof(*m), GFP_KERNEL); + + if (!m) + return -ENOMEM; + m->paddr = paddr; + m->size = size; + list_add_tail(&m->list, list); + return 0; +} + #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ -- cgit v1.2.3 From e29e9acae06dc28ca8dbf3db976e09787e610dc8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 4 Dec 2024 13:54:38 +0100 Subject: fs/proc/vmcore: factor out freeing a list of vmcore ranges Let's factor it out into include/linux/crash_dump.h, from where we can use it also outside of vmcore.c later. Acked-by: Baoquan He Signed-off-by: David Hildenbrand Message-Id: <20241204125444.1734652-8-david@redhat.com> Acked-by: Andrew Morton Signed-off-by: Michael S. Tsirkin --- include/linux/crash_dump.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 9717912ce4d1..5d61c7454fd6 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -135,6 +135,17 @@ static inline int vmcore_alloc_add_range(struct list_head *list, return 0; } +/* Free a list of vmcore ranges. */ +static inline void vmcore_free_ranges(struct list_head *list) +{ + struct vmcore_range *m, *tmp; + + list_for_each_entry_safe(m, tmp, list, list) { + list_del(&m->list); + kfree(m); + } +} + #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ -- cgit v1.2.3 From 7ad4d1f6e6ef967cd24c6275d8d4056045c019c1 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 4 Dec 2024 13:54:39 +0100 Subject: fs/proc/vmcore: introduce PROC_VMCORE_DEVICE_RAM to detect device RAM ranges in 2nd kernel s390 allocates+prepares the elfcore hdr in the dump (2nd) kernel, not in the crashed kernel. RAM provided by memory devices such as virtio-mem can only be detected using the device driver; when vmcore_init() is called, these device drivers are usually not loaded yet, or the devices did not get probed yet. Consequently, on s390 these RAM ranges will not be included in the crash dump, which makes the dump partially corrupt and is unfortunate. Instead of deferring the vmcore_init() call, to an (unclear?) later point, let's reuse the vmcore_cb infrastructure to obtain device RAM ranges as the device drivers probe the device and get access to this information. Then, we'll add these ranges to the vmcore, adding more PT_LOAD entries and updating the offsets+vmcore size. Use a separate Kconfig option to be set by an architecture to include this code only if the arch really needs it. Further, we'll make the config depend on the relevant drivers (i.e., virtio_mem) once they implement support (next). The alternative of having a PROVIDE_PROC_VMCORE_DEVICE_RAM config option was dropped for now for simplicity. The current target use case is s390, which only creates an elf64 elfcore, so focusing on elf64 is sufficient. Signed-off-by: David Hildenbrand Message-Id: <20241204125444.1734652-9-david@redhat.com> Acked-by: Andrew Morton Signed-off-by: Michael S. Tsirkin --- include/linux/crash_dump.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 5d61c7454fd6..2f2555e6407c 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -20,6 +20,8 @@ extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); extern void elfcorehdr_free(unsigned long long addr); extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr, + unsigned long long paddr, unsigned long long size); extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); @@ -99,6 +101,12 @@ static inline void vmcore_unusable(void) * indicated in the vmcore instead. For example, a ballooned page * contains no data and reading from such a page will cause high * load in the hypervisor. + * @get_device_ram: query RAM ranges that can only be detected by device + * drivers, such as the virtio-mem driver, so they can be included in + * the crash dump on architectures that allocate the elfcore hdr in the dump + * ("2nd") kernel. Indicated RAM ranges may contain holes to reduce the + * total number of ranges; such holes can be detected using the pfn_is_ram + * callback just like for other RAM. * @next: List head to manage registered callbacks internally; initialized by * register_vmcore_cb(). * @@ -109,6 +117,7 @@ static inline void vmcore_unusable(void) */ struct vmcore_cb { bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn); + int (*get_device_ram)(struct vmcore_cb *cb, struct list_head *list); struct list_head next; }; extern void register_vmcore_cb(struct vmcore_cb *cb); -- cgit v1.2.3 From a0ec4fb63f5ce15732f8dadc63c931bdf9ff98b5 Mon Sep 17 00:00:00 2001 From: Israel Rukshin Date: Wed, 27 Nov 2024 08:57:31 +0200 Subject: virtio_pci: Add support for PCIe Function Level Reset Implement support for Function Level Reset (FLR) in virtio_pci devices. This change adds reset_prepare and reset_done callbacks, allowing drivers to properly handle FLR operations. Without this patch, performing and recovering from an FLR is not possible for virtio_pci devices. This implementation ensures proper FLR handling and recovery for both physical and virtual functions. The device reset can be triggered in case of error or manually via sysfs: echo 1 > /sys/bus/pci/devices/$PCI_ADDR/reset Signed-off-by: Israel Rukshin Reviewed-by: Max Gurtovoy Message-Id: <1732690652-3065-2-git-send-email-israelr@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index dd88682e27e3..4d16c13d0df5 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -190,6 +190,8 @@ int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); +int virtio_device_reset_prepare(struct virtio_device *dev); +int virtio_device_reset_done(struct virtio_device *dev); size_t virtio_max_dma_size(const struct virtio_device *vdev); @@ -214,6 +216,10 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev); * changes; may be called in interrupt context. * @freeze: optional function to call during suspend/hibernation. * @restore: optional function to call on resume. + * @reset_prepare: optional function to call when a transport specific reset + * occurs. + * @reset_done: optional function to call after transport specific reset + * operation has finished. */ struct virtio_driver { struct device_driver driver; @@ -229,6 +235,8 @@ struct virtio_driver { void (*config_changed)(struct virtio_device *dev); int (*freeze)(struct virtio_device *dev); int (*restore)(struct virtio_device *dev); + int (*reset_prepare)(struct virtio_device *dev); + int (*reset_done)(struct virtio_device *dev); }; #define drv_to_virtio(__drv) container_of_const(__drv, struct virtio_driver, driver) -- cgit v1.2.3