x86/pci: Add a break condition when enabling BAR
PATCH 1/1 x86/pci: Add a break condition when enabling BAR
On an old flaky system with AMD Opteron 6320, boot hangs with the following trace since commit fa564ad9:
[ 28.181012] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 09/03/2014 [ 28.184022] RIP: 0010:lock_acquire+0xd5/0x1e0 [ 28.185010] RSP: 0018:ffffb7ad818c39a8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff11 [ 28.187010] RAX: ffffa074fb39b140 RBX: 0000000000000246 RCX: 0000000000000000 [ 28.189014] RDX: ffffffffb20a55a9 RSI: 0000000000040009 RDI: 0000000000000246 [ 28.191012] RBP: 0000000000000000 R08: 0000000000000006 R09: 0000000000000000 [ 28.193020] R10: 0000000000000001 R11: 00000000dac664b5 R12: 0000000000000000 [ 28.196013] R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000000 [ 28.197011] FS: 0000000000000000(0000) GS:ffffa074fbd00000(0000) knlGS:0000000000000000 [ 28.201014] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 28.201014] CR2: 0000000000000000 CR3: 00000003b6e10000 CR4: 00000000000406e0 [ 28.205008] Call Trace: [ 28.205013] ? request_resource_conflict+0x19/0x40 [ 28.207013] _raw_write_lock+0x2e/0x40 [ 28.209008] ? request_resource_conflict+0x19/0x40 [ 28.209010] request_resource_conflict+0x19/0x40 [ 28.212013] pci_amd_enable_64bit_bar+0x103/0x1a0 [ 28.213025] pci_fixup_device+0xd4/0x210 [ 28.213025] pci_setup_device+0x193/0x570 [ 28.215010] ? get_device+0x13/0x20 [ 28.217008] pci_scan_single_device+0x98/0xd0 [ 28.217011] pci_scan_slot+0x90/0x130 [ 28.219010] pci_scanild_bus_extend+0x3a/0x270 [ 28.321008] acpi_pci_root_create+0x1a9/0x210 [ 28.321014] ? pci_acpi_scan_root+0x135/0x1b0 [ 28.324013] pci_acpi_scan_root+0x15f/0x1b0 [ 28.325008] acpi_pci_root_add+0x283/0x560 [ 28.325014] ? acpi_match_device_ids+0xc/0x20 [ 28.327013] acpi_bus_attach+0xf9/0x1c0 [ 28.329008] acpi_bus_attach+0x82/0x1c0 [ 28.329044] acpi_bus_attach+0x82/0x1c0 [ 28.331010] acpi_bus_scan+0x47/0xa0 [ 28.333008] acpi_scan_init+0x12d/0x28d [ 28.333013] ? bus_register+0x208/0x280 [ 28.333013] acpi_init+0x30f/0x36f [ 28.335010] ? acpi_sleep_proc_init+0x24/0x24 [ 28.337013] do_one_initcall+0x4d/0x19c [ 28.337013] ? do_early_param+0x29/0x86 [ 28.340013] kernel_init_freeable+0x209/0x2a4 [ 28.341008] ? set_debug_rodata+0x11/0x11 [ 28.341011] ? rest_init+0xc0/0xc0 [ 28.343013] kernel_init+0xa/0x104 [ 28.345008] ret_from_fork+0x24/0x30 [ 28.345010] Code: 24 08 49 c1 e9 09 49 83 f1 01 41 83 e1 01 e8 73
e4 ff ff 65 48 8b 04 25 c0 d4 00 00 48 89 df c7 80 fc 0c 00 00 00 00 00 00 57 9d <0f> 1f 44 00 00 48 83 c4 30 5b 5d 41 5c 41 5d 41 5e 41 5f c3 65
Since request_resource() will unconditionally return a conflict for invalid regions, there will be no way to break out of the loop when enabling 64bit BAR. Add checks and exit the loop in these cases without attempting to enable BAR.
--- arch/x86/pci/fixup.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
arch/x86/pci/fixup.c +6 -1
@@ -696,8 +696,13 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) res->end =0xfd00000000ull -1 ;/* Just grab the free area behind system memory for this */ -while ((conflict =request_resource_conflict (&iomem_resource, res))) +while ((conflict =request_resource_conflict (&iomem_resource, res))) { +if ((res->start > res->end) || + (res->start < iomem_resource.start) || + (res->end > iomem_resource.end)) +break ; res->start = conflict->end +1 ; + }dev_info (&dev->dev,"adding root bus resource %pR\n" , res);
Signature · 1 line
2.9.4
Hi Bandas,
thanks for the patch, but this is a known issue with a fix already on the way into the next -rc.
Regards,
Christian.
Am 07.12.2017 um 09:00 schrieb Bandan Das:
Quoted 80 lines
On an old flaky system with AMD Opteron 6320, boot hangs with the following trace since commit
fa564ad9:[ 28.181012] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 09/03/2014 [ 28.184022] RIP: 0010:lock_acquire+0xd5/0x1e0 [ 28.185010] RSP: 0018:ffffb7ad818c39a8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff11 [ 28.187010] RAX: ffffa074fb39b140 RBX: 0000000000000246 RCX: 0000000000000000 [ 28.189014] RDX: ffffffffb20a55a9 RSI: 0000000000040009 RDI: 0000000000000246 [ 28.191012] RBP: 0000000000000000 R08: 0000000000000006 R09: 0000000000000000 [ 28.193020] R10: 0000000000000001 R11: 00000000dac664b5 R12: 0000000000000000 [ 28.196013] R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000000 [ 28.197011] FS: 0000000000000000(0000) GS:ffffa074fbd00000(0000) knlGS:0000000000000000 [ 28.201014] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 28.201014] CR2: 0000000000000000 CR3: 00000003b6e10000 CR4: 00000000000406e0 [ 28.205008] Call Trace: [ 28.205013] ? request_resource_conflict+0x19/0x40 [ 28.207013] _raw_write_lock+0x2e/0x40 [ 28.209008] ? request_resource_conflict+0x19/0x40 [ 28.209010] request_resource_conflict+0x19/0x40 [ 28.212013] pci_amd_enable_64bit_bar+0x103/0x1a0 [ 28.213025] pci_fixup_device+0xd4/0x210 [ 28.213025] pci_setup_device+0x193/0x570 [ 28.215010] ? get_device+0x13/0x20 [ 28.217008] pci_scan_single_device+0x98/0xd0 [ 28.217011] pci_scan_slot+0x90/0x130 [ 28.219010] pci_scanild_bus_extend+0x3a/0x270 [ 28.321008] acpi_pci_root_create+0x1a9/0x210 [ 28.321014] ? pci_acpi_scan_root+0x135/0x1b0 [ 28.324013] pci_acpi_scan_root+0x15f/0x1b0 [ 28.325008] acpi_pci_root_add+0x283/0x560 [ 28.325014] ? acpi_match_device_ids+0xc/0x20 [ 28.327013] acpi_bus_attach+0xf9/0x1c0 [ 28.329008] acpi_bus_attach+0x82/0x1c0 [ 28.329044] acpi_bus_attach+0x82/0x1c0 [ 28.331010] acpi_bus_scan+0x47/0xa0 [ 28.333008] acpi_scan_init+0x12d/0x28d [ 28.333013] ? bus_register+0x208/0x280 [ 28.333013] acpi_init+0x30f/0x36f [ 28.335010] ? acpi_sleep_proc_init+0x24/0x24 [ 28.337013] do_one_initcall+0x4d/0x19c [ 28.337013] ? do_early_param+0x29/0x86 [ 28.340013] kernel_init_freeable+0x209/0x2a4 [ 28.341008] ? set_debug_rodata+0x11/0x11 [ 28.341011] ? rest_init+0xc0/0xc0 [ 28.343013] kernel_init+0xa/0x104 [ 28.345008] ret_from_fork+0x24/0x30 [ 28.345010] Code: 24 08 49 c1 e9 09 49 83 f1 01 41 83 e1 01 e8 73e4 ff ff 65 48 8b 04 25 c0 d4 00 00 48 89 df c7 80 fc 0c 00 00 00 00 00 00 57 9d <0f> 1f 44 00 00 48 83 c4 30 5b 5d 41 5c 41 5d 41 5e 41 5f c3 65
Since
request_resource()will unconditionally return a conflict for invalid regions, there will be no way to break out of the loop when enabling 64bit BAR. Add checks and exit the loop in these cases without attempting to enable BAR.Signed-off-by Bandan Das <[email protected]>--- arch/x86/pci/fixup.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)arch/x86/pci/fixup.c +6
-1@@ -696,8 +696,13 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) res->end =0xfd00000000ull -1 ;/* Just grab the free area behind system memory for this */ -while ((conflict =request_resource_conflict (&iomem_resource, res))) +while ((conflict =request_resource_conflict (&iomem_resource, res))) { +if ((res->start > res->end) || + (res->start < iomem_resource.start) || + (res->end > iomem_resource.end)) +break ; res->start = conflict->end +1 ; + }dev_info (&dev->dev,"adding root bus resource %pR\n" , res);
Quoted 4 lines · Christian König
Hi Bandas,
thanks for the patch, but this is a known issue with a fix already on the way into the next -rc.
Oh great! Thank you, have a pointer to the patch so that I can test ?
Quoted 82 lines
Regards,
Christian.Am 07.12.2017 um 09:00 schrieb Bandan Das:
Quoted 78 lines
On an old flaky system with AMD Opteron 6320, boot hangs with the following trace since commit
fa564ad9:[ 28.181012] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 09/03/2014 [ 28.184022] RIP: 0010:lock_acquire+0xd5/0x1e0 [ 28.185010] RSP: 0018:ffffb7ad818c39a8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff11 [ 28.187010] RAX: ffffa074fb39b140 RBX: 0000000000000246 RCX: 0000000000000000 [ 28.189014] RDX: ffffffffb20a55a9 RSI: 0000000000040009 RDI: 0000000000000246 [ 28.191012] RBP: 0000000000000000 R08: 0000000000000006 R09: 0000000000000000 [ 28.193020] R10: 0000000000000001 R11: 00000000dac664b5 R12: 0000000000000000 [ 28.196013] R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000000 [ 28.197011] FS: 0000000000000000(0000) GS:ffffa074fbd00000(0000) knlGS:0000000000000000 [ 28.201014] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 28.201014] CR2: 0000000000000000 CR3: 00000003b6e10000 CR4: 00000000000406e0 [ 28.205008] Call Trace: [ 28.205013] ? request_resource_conflict+0x19/0x40 [ 28.207013] _raw_write_lock+0x2e/0x40 [ 28.209008] ? request_resource_conflict+0x19/0x40 [ 28.209010] request_resource_conflict+0x19/0x40 [ 28.212013] pci_amd_enable_64bit_bar+0x103/0x1a0 [ 28.213025] pci_fixup_device+0xd4/0x210 [ 28.213025] pci_setup_device+0x193/0x570 [ 28.215010] ? get_device+0x13/0x20 [ 28.217008] pci_scan_single_device+0x98/0xd0 [ 28.217011] pci_scan_slot+0x90/0x130 [ 28.219010] pci_scanild_bus_extend+0x3a/0x270 [ 28.321008] acpi_pci_root_create+0x1a9/0x210 [ 28.321014] ? pci_acpi_scan_root+0x135/0x1b0 [ 28.324013] pci_acpi_scan_root+0x15f/0x1b0 [ 28.325008] acpi_pci_root_add+0x283/0x560 [ 28.325014] ? acpi_match_device_ids+0xc/0x20 [ 28.327013] acpi_bus_attach+0xf9/0x1c0 [ 28.329008] acpi_bus_attach+0x82/0x1c0 [ 28.329044] acpi_bus_attach+0x82/0x1c0 [ 28.331010] acpi_bus_scan+0x47/0xa0 [ 28.333008] acpi_scan_init+0x12d/0x28d [ 28.333013] ? bus_register+0x208/0x280 [ 28.333013] acpi_init+0x30f/0x36f [ 28.335010] ? acpi_sleep_proc_init+0x24/0x24 [ 28.337013] do_one_initcall+0x4d/0x19c [ 28.337013] ? do_early_param+0x29/0x86 [ 28.340013] kernel_init_freeable+0x209/0x2a4 [ 28.341008] ? set_debug_rodata+0x11/0x11 [ 28.341011] ? rest_init+0xc0/0xc0 [ 28.343013] kernel_init+0xa/0x104 [ 28.345008] ret_from_fork+0x24/0x30 [ 28.345010] Code: 24 08 49 c1 e9 09 49 83 f1 01 41 83 e1 01 e8 73e4 ff ff 65 48 8b 04 25 c0 d4 00 00 48 89 df c7 80 fc 0c 00 00 00 00 00 00 57 9d <0f> 1f 44 00 00 48 83 c4 30 5b 5d 41 5c 41 5d 41 5e 41 5f c3 65
Since
request_resource()will unconditionally return a conflict for invalid regions, there will be no way to break out of the loop when enabling 64bit BAR. Add checks and exit the loop in these cases without attempting to enable BAR.Signed-off-by Bandan Das <[email protected]>--- arch/x86/pci/fixup.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)arch/x86/pci/fixup.c +6
-1@@ -696,8 +696,13 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) res->end =0xfd00000000ull -1 ;/* Just grab the free area behind system memory for this */ -while ((conflict =request_resource_conflict (&iomem_resource, res))) +while ((conflict =request_resource_conflict (&iomem_resource, res))) { +if ((res->start > res->end) || + (res->start < iomem_resource.start) || + (res->end > iomem_resource.end)) +break ; res->start = conflict->end +1 ; + }dev_info (&dev->dev,"adding root bus resource %pR\n" , res);
Quoted 8 lines · Bandan Das
Quoted 4 lines · Christian König
Hi Bandas,
thanks for the patch, but this is a known issue with a fix already on the way into the next -rc.
Oh great! Thank you, have a pointer to the patch so that I can test ?
It's in linux-next. If you want just the patch, see
https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git/log/?h=for-linus
(there are a couple patches there).
There's still one fix for a related issue that I haven't applied yet because it needs a little more detailed changelog.
Bjorn