Parallel port fixes for 2.6.31
cover Parallel port fixes for 2.6.31
---
FUJITA Tomonori (1):
parport_pc: set properly the dma_mask for parport_pc device
Jens Rottmann (1):
parport_pc: after superio probing restore original register values
drivers/parport/parport_pc.c | 34 +
PATCH 1/2 parport_pc: after superio probing restore original register values
From: Jens Rottmann <[email protected]>
CONFIG_PARPORT_PC_SUPERIO probes for various superio chips by writing byte sequences to a set of different potential I/O ranges. But the probed ranges are not exclusive to parallel ports. Some of our boards just happen to have a watchdog in one of them. Took us almost a week to figure out why some distros reboot without warning after running flawlessly for 3 hours. For exactly 170 = 0xAA minutes, that is ...
Fixed by restoring original values after probing. Also fixed too small request_region() in detect_and_report_it87().
---
drivers/parport/parport_pc.c | 31 +++++++++++++++++++++++++------ 1 files changed, 25 insertions(+), 6 deletions(-)
drivers/parport/parport_pc.c +25 -6
@@ -1471,11 +1471,13 @@ static void __devinit decode_smsc(int efer, int key, int devid, int devrev)static void __devinit winbond_check (int io,int key) { -int devid, devrev, oldid, x_devid, x_devrev, x_oldid; +int origval, devid, devrev, oldid, x_devid, x_devrev, x_oldid;if (!request_region (io,3 , __func__))return ; + origval =inb (io);/* Save original value */ +/* First probe without key */ outb (0x20 , io); x_devid =inb (io +1 );
@@ -1495,6 +1497,8 @@ static void __devinit winbond_check(int io, int key) oldid =inb (io +1 );outb (0xaa , io);/* Magic Seal */ +outb (origval, io);/* in case we poked some entirely different hardware */ +if ((x_devid == devid) && (x_devrev == devrev) && (x_oldid == oldid)) goto out;/* protection against false positives */
@@ -1505,11 +1509,15 @@ out:static void __devinit winbond_check2 (int io,int key) { -int devid, devrev, oldid, x_devid, x_devrev, x_oldid; +int origval[3 ], devid, devrev, oldid, x_devid, x_devrev, x_oldid;if (!request_region (io,3 , __func__))return ; + origval[0 ] =inb (io);/* Save original values */ + origval[1 ] =inb (io +1 ); + origval[2 ] =inb (io +2 ); +/* First probe without the key */ outb (0x20 , io +2 ); x_devid =inb (io +2 );
@@ -1528,6 +1536,10 @@ static void __devinit winbond_check2(int io, int key) oldid =inb (io +2 );outb (0xaa , io);/* Magic Seal */ +outb (origval[0 ], io);/* in case we poked some entirely different hardware */ +outb (origval[1 ], io +1 ); +outb (origval[2 ], io +2 ); +if (x_devid == devid && x_devrev == devrev && x_oldid == oldid) goto out;/* protection against false positives */
@@ -1538,11 +1550,13 @@ out:static void __devinit smsc_check (int io,int key) { -int id, rev, oldid, oldrev, x_id, x_rev, x_oldid, x_oldrev; +int origval, id, rev, oldid, oldrev, x_id, x_rev, x_oldid, x_oldrev;if (!request_region (io,3 , __func__))return ; + origval =inb (io);/* Save original value */ +/* First probe without the key */ outb (0x0d , io); x_oldid =inb (io +1 );
@@ -1566,6 +1580,8 @@ static void __devinit smsc_check(int io, int key) rev =inb (io +1 );outb (0xaa , io);/* Magic Seal */ +outb (origval, io);/* in case we poked some entirely different hardware */ +if (x_id == id && x_oldrev == oldrev && x_oldid == oldid && x_rev == rev) goto out;/* protection against false positives */
@@ -1602,11 +1618,12 @@ static void __devinit detect_and_report_smsc(void)static void __devinit detect_and_report_it87 (void ) {u16 dev; -u8 r; +u8 origval, r;if (verbose_probing)printk (KERN_DEBUG "IT8705 Super-IO detection, now testing port 2E ...\n" ); -if (!request_region (0x2e ,1 , __func__)) +if (!request_region (0x2e ,2 , __func__))return ; + origval =inb (0x2e );/* Save original value */ outb (0x87 ,0x2e );outb (0x01 ,0x2e );outb (0x55 ,0x2e );
@@ -1626,8 +1643,10 @@ static void __devinit detect_and_report_it87(void)outb (r |8 ,0x2F );outb (0x02 ,0x2E );/* Lock */ outb(0x02, 0x2F); + }else { +outb (origval,0x2e );/* Oops, sorry to disturb */ } -release_region (0x2e ,1 ); +release_region (0x2e ,2 ); }#endif /* CONFIG_PARPORT_PC_SUPERIO */
Re: [PATCH 1/2] parport_pc: after superio probing restore original register values
Quoted 12 lines · Alan Cox
From: Jens Rottmann <[email protected]>
CONFIG_PARPORT_PC_SUPERIOprobes for various superio chips by writing byte sequences to a set of different potential I/O ranges. But the probed ranges are not exclusive to parallel ports. Some of our boards just happen to have a watchdog in one of them. Took us almost a week to figure out why some distros reboot without warning after running flawlessly for 3 hours. For exactly 170 =0xAAminutes, that is ...Fixed by restoring original values after probing. Also fixed too small
request_region()indetect_and_report_it87().
Quoted 7 lines
Signed-off-by Jens Rottmann <[email protected]>Signed-off-by Alan Cox <[email protected]>Cc <[email protected]>---
drivers/parport/parport_pc.c | 31 +++++++++++++++++++++++++------ 1 files changed, 25 insertions(+), 6 deletions(-)
PATCH 2/2 parport_pc: set properly the dma_mask for parport_pc device
In reply to Alan CoxFrom: FUJITA Tomonori <[email protected]>
parport_pc_probe_port() creates the own 'parport_pc' device if the device argument is NULL. Then parport_pc_probe_port() doesn't initialize the dma_mask and coherent_dma_mask of the device and calls dma_alloc_coherent with it. dma_alloc_coherent fails because dma_alloc_coherent() doesn't accept the uninitialized dma_mask:
http://lkml.org/lkml/2009/6/16/150
Long ago, X86_32 and X86_64 had the own dma_alloc_coherent implementations; X86_32 accepted a device having dma_mask that is not initialized however X86_64 didn't. When we merged them, we chose to prohibit a device having dma_mask that is not initialized. I think that it's good to require drivers to set up dma_mask (and coherent_dma_mask) properly if the drivers want DMA.
---
drivers/parport/parport_pc.c | 3 +++ 1 files changed, 3 insertions(+), 0 deletions(-)
drivers/parport/parport_pc.c +3 -0
@@ -2290,6 +2290,9 @@ struct parport *parport_pc_probe_port(unsigned long int base,if (IS_ERR (pdev))return NULL ; dev = &pdev->dev; + + dev->coherent_dma_mask =DMA_BIT_MASK (24 ); + dev->dma_mask = &dev->coherent_dma_mask; } ops =kmalloc (sizeof (struct parport_operations ),GFP_KERNEL );
Re: [PATCH 2/2] parport_pc: set properly the dma_mask for parport_pc device
Quoted 22 lines · Alan Cox
From: FUJITA Tomonori <[email protected]>
parport_pc_probe_port()creates the own 'parport_pc' device if the device argument is NULL. Thenparport_pc_probe_port()doesn't initialize thedma_maskandcoherent_dma_maskof the device and callsdma_alloc_coherentwith it.dma_alloc_coherentfails becausedma_alloc_coherent()doesn't accept the uninitializeddma_mask:http://lkml.org/lkml/2009/6/16/150
Long ago,
X86_32andX86_64had the owndma_alloc_coherentimplementations;X86_32accepted a device havingdma_maskthat is not initialized howeverX86_64didn't. When we merged them, we chose to prohibit a device havingdma_maskthat is not initialized. I think that it's good to require drivers to set updma_mask(andcoherent_dma_mask) properly if the drivers want DMA.Signed-off-by FUJITA Tomonori <[email protected]>Reported-by Malcom Blaney <[email protected]>Tested-by Malcom Blaney <[email protected]>Signed-off-by Alan Cox <[email protected]>
Quoted 4 lines
---
drivers/parport/parport_pc.c | 3 +++ 1 files changed, 3 insertions(+), 0 deletions(-)