From e0d59733f6b1796b8d6692642c87d7dd862c3e3a Mon Sep 17 00:00:00 2001 From: Seiji Aguchi Date: Wed, 30 Oct 2013 15:27:26 -0400 Subject: efivars, efi-pstore: Hold off deletion of sysfs entry until the scan is completed Currently, when mounting pstore file system, a read callback of efi_pstore driver runs mutiple times as below. - In the first read callback, scan efivar_sysfs_list from head and pass a kmsg buffer of a entry to an upper pstore layer. - In the second read callback, rescan efivar_sysfs_list from the entry and pass another kmsg buffer to it. - Repeat the scan and pass until the end of efivar_sysfs_list. In this process, an entry is read across the multiple read function calls. To avoid race between the read and erasion, the whole process above is protected by a spinlock, holding in open() and releasing in close(). At the same time, kmemdup() is called to pass the buffer to pstore filesystem during it. And then, it causes a following lockdep warning. To make the dynamic memory allocation runnable without taking spinlock, holding off a deletion of sysfs entry if it happens while scanning it via efi_pstore, and deleting it after the scan is completed. To implement it, this patch introduces two flags, scanning and deleting, to efivar_entry. On the code basis, it seems that all the scanning and deleting logic is not needed because __efivars->lock are not dropped when reading from the EFI variable store. But, the scanning and deleting logic is still needed because an efi-pstore and a pstore filesystem works as follows. In case an entry(A) is found, the pointer is saved to psi->data. And efi_pstore_read() passes the entry(A) to a pstore filesystem by releasing __efivars->lock. And then, the pstore filesystem calls efi_pstore_read() again and the same entry(A), which is saved to psi->data, is used for resuming to scan a sysfs-list. So, to protect the entry(A), the logic is needed. [ 1.143710] ------------[ cut here ]------------ [ 1.144058] WARNING: CPU: 1 PID: 1 at kernel/lockdep.c:2740 lockdep_trace_alloc+0x104/0x110() [ 1.144058] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags)) [ 1.144058] Modules linked in: [ 1.144058] CPU: 1 PID: 1 Comm: systemd Not tainted 3.11.0-rc5 #2 [ 1.144058] 0000000000000009 ffff8800797e9ae0 ffffffff816614a5 ffff8800797e9b28 [ 1.144058] ffff8800797e9b18 ffffffff8105510d 0000000000000080 0000000000000046 [ 1.144058] 00000000000000d0 00000000000003af ffffffff81ccd0c0 ffff8800797e9b78 [ 1.144058] Call Trace: [ 1.144058] [] dump_stack+0x54/0x74 [ 1.144058] [] warn_slowpath_common+0x7d/0xa0 [ 1.144058] [] warn_slowpath_fmt+0x4c/0x50 [ 1.144058] [] ? vsscanf+0x57f/0x7b0 [ 1.144058] [] lockdep_trace_alloc+0x104/0x110 [ 1.144058] [] __kmalloc_track_caller+0x50/0x280 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] kmemdup+0x20/0x50 [ 1.144058] [] efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x170/0x170 [ 1.144058] [] efi_pstore_read_func+0xb4/0xe0 [ 1.144058] [] __efivar_entry_iter+0xfb/0x120 [ 1.144058] [] efi_pstore_read+0x3f/0x50 [ 1.144058] [] pstore_get_records+0x9a/0x150 [ 1.158207] [] ? selinux_d_instantiate+0x1c/0x20 [ 1.158207] [] ? parse_options+0x80/0x80 [ 1.158207] [] pstore_fill_super+0xa5/0xc0 [ 1.158207] [] mount_single+0xa2/0xd0 [ 1.158207] [] pstore_mount+0x18/0x20 [ 1.158207] [] mount_fs+0x39/0x1b0 [ 1.158207] [] ? __alloc_percpu+0x10/0x20 [ 1.158207] [] vfs_kern_mount+0x63/0xf0 [ 1.158207] [] do_mount+0x23e/0xa20 [ 1.158207] [] ? strndup_user+0x4b/0xf0 [ 1.158207] [] SyS_mount+0x83/0xc0 [ 1.158207] [] system_call_fastpath+0x16/0x1b [ 1.158207] ---[ end trace 61981bc62de9f6f4 ]--- Signed-off-by: Seiji Aguchi Tested-by: Madper Xie Cc: stable@kernel.org Signed-off-by: Matt Fleming --- drivers/firmware/efi/vars.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/firmware/efi/vars.c') diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 391c67b182d..b22659cccca 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -683,8 +683,16 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, if (!found) return NULL; - if (remove) - list_del(&entry->list); + if (remove) { + if (entry->scanning) { + /* + * The entry will be deleted + * after scanning is completed. + */ + entry->deleting = true; + } else + list_del(&entry->list); + } return entry; } -- cgit v1.2.3-70-g09d2