parport netmos 9845 & 9855 1P4S fixes
Subsystems (2)
PATCH 1/1 parport netmos 9845 & 9855 1P4S fixes
Hello list,
--
netmos serial/parallel adapters come in different flavour differing only by the number of parallel and serial ports, which are encoded in the subdevice ID.
Last fix of Christian Pellegrin for 9855 2P2S broke support for 9855 1P4S, and works only by side-effect for the first parallel port of a 2P2S, as it is found by reading the second addr entry of
(struct parport_pc_pci) cards[netmos_9855], which is not initialized.
netmos_9xx5_combo entry in (struct parport_pc_pci) cards[], which is used for a 9845 1P4S should also be fixed when there are 4 serial ports because it currently gives 2 as BAR index for the parallel port, while, in this case, BAR 2 is the 3rd serial port and the parallel port is at BAR 4.
I fixed 9845 1P4S and 9855 1P4S support, while preserving 9855 2P2S support, by creating and using a netmos_9855_2p entry for 9855 boards with 2 parallel ports for 9855 2P2S and 9855 2P0S boards,
and by allowing netmos_parallel_init to change not only the number of parallel ports (0 or 1), but also the BAR index of the parallel port when the serial ports are before the parallel port.
PS: the netmos_9855_2p entry in
(struct pciserial_board) pci_parport_serial_boards[] is needed because netmos_parallel_init has no clean way to replace FL_BASE2 by FL_BASE4 based on the number of parallel ports in the card.
Tested with a 9845 1P4S and a 9855 1P4S board.
drivers/parport/parport_serial.c +25 -5
@@ -30,6 +30,7 @@ enum parport_pc_pci_cards { titan_210l, netmos_9xx5_combo, netmos_9855, + netmos_9855_2p, avlab_1s1p, avlab_1s2p, avlab_2s1p,
@@ -62,7 +63,7 @@ struct parport_pc_pci { struct parport_pc_pci *card, int failed); }; -static int __devinit netmos_parallel_init (struct pci_dev *dev,struct parport_pc_pci *card,int autoirq,int autodma) +static int __devinit netmos_parallel_init (struct pci_dev *dev,struct parport_pc_pci *par,int autoirq,int autodma) {/* the rule described below doesn't hold for this device */ if (dev->device == PCI_DEVICE_ID_NETMOS_9835 &&
@@ -74,9 +75,17 @@ static int __devinit netmos_parallel_ini* and serial ports. The form is 0x00PS, where <P> is the number of * parallel ports and <S> is the number of serial ports. */ - card->numports = (dev->subsystem_device &0xf0 ) >>4 ; -if (card->numports >ARRAY_SIZE (card->addr)) - card->numports =ARRAY_SIZE (card->addr); + par->numports = (dev->subsystem_device &0xf0 ) >>4 ; +if (par->numports >ARRAY_SIZE (par->addr)) + par->numports =ARRAY_SIZE (par->addr); +/* +* This function is currently only called for cards with up to +* one parallel port. +* Parallel port BAR is either before or after serial ports BARS; +* hence, lo should be either 0 or equal to the number of serial ports. +*/ +if (par->addr[0 ].lo !=0 ) + par->addr[0 ].lo = dev->subsystem_device &0xf ;return 0 ; }
@@ -84,7 +93,8 @@ static struct parport_pc_pci cards[] __d /* titan_110l */ { 1, { { 3, -1 }, } }, /* titan_210l */ { 1, { { 3, -1 }, } }, /* netmos_9xx5_combo */ { 1, { { 2, -1 }, }, netmos_parallel_init }, - /* netmos_9855 */ { 1, { { 2, -1 }, }, netmos_parallel_init }, + /* netmos_9855 */ { 1, { { 0, -1 }, }, netmos_parallel_init }, + /* netmos_9855_2p */ { 2, { { 0, -1 }, { 2, -1 }, } }, /* avlab_1s1p */ { 1, { { 1, 2}, } }, /* avlab_1s2p */ { 2, { { 1, 2}, { 3, 4 },} }, /* avlab_2s1p */ { 1, { { 2, 3}, } },
@@ -109,6 +119,10 @@ static struct pci_device_id parport_seri PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9xx5_combo }, { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9845, PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9xx5_combo }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, + 0x1000, 0x0020, 0, 0, netmos_9855_2p }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, + 0x1000, 0x0022, 0, 0, netmos_9855_2p }, { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9855 }, /* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
@@ -192,6 +206,12 @@ static struct pciserial_board pci_parpor .uart_offset = 8, }, [netmos_9855] = { + .flags = FL_BASE2 | FL_BASE_BARS, + .num_ports = 1, + .base_baud = 115200, + .uart_offset = 8, + }, + [netmos_9855_2p] = { .flags = FL_BASE4 | FL_BASE_BARS, .num_ports = 1, .base_baud = 115200,
Hello list,
Sorry for the resend. I had forgotten to cc Christian Pellegrin, and have rephrased somewhat the comment.
Christian, can you verify that the patch below works for your netmos 9855 2P2S board ?
Philippe
--
netmos serial/parallel adapters come in different flavour differing only by the number of parallel and serial ports, which are encoded in the subdevice ID.
Last fix of Christian Pellegrin for 9855 2P2S broke support for 9855 1P4S, and works only by side-effect for the first parallel port of a 2P2S, as this first parallel port is found by reading the second addr entry of (struct parport_pc_pci) cards[netmos_9855], which is not initialized, and hence has value 0, which happens to be the BAR of the first parallel port.
netmos_9xx5_combo entry in (struct parport_pc_pci) cards[], which is used for a 9845 1P4S must also be fixed for the parallel port support when there are 4 serial ports because this entry currently gives 2 as BAR index for the parallel port. Actually, in this case, BAR 2 is the 3rd serial port while the parallel port is at BAR 4.
I fixed 9845 1P4S and 9855 1P4S support, while preserving 9855 2P2S support,
- by creating a netmos_9855_2p entry and using it for 9855 boards with 2 parallel ports : 9855 2P2S and 9855 2P0S boards,
- and by allowing netmos_parallel_init to change not only the number of parallel ports (0 or 1), but making it also change the BAR index of the parallel port when the serial ports are before the parallel port.
PS: the netmos_9855_2p entry in
(struct pciserial_board) pci_parport_serial_boards[] is needed because netmos_parallel_init has no clean way to replace FL_BASE2 by FL_BASE4 in the description of the serial ports in function of the number of parallel ports on the card.
Tested with a 9845 1P4S and a 9855 1P4S board.
drivers/parport/parport_serial.c +25 -5
@@ -30,6 +30,7 @@ enum parport_pc_pci_cards { titan_210l, netmos_9xx5_combo, netmos_9855, + netmos_9855_2p, avlab_1s1p, avlab_1s2p, avlab_2s1p,
@@ -62,7 +63,7 @@ struct parport_pc_pci { struct parport_pc_pci *card, int failed); }; -static int __devinit netmos_parallel_init (struct pci_dev *dev,struct parport_pc_pci *card,int autoirq,int autodma) +static int __devinit netmos_parallel_init (struct pci_dev *dev,struct parport_pc_pci *par,int autoirq,int autodma) {/* the rule described below doesn't hold for this device */ if (dev->device == PCI_DEVICE_ID_NETMOS_9835 &&
@@ -74,9 +75,17 @@ static int __devinit netmos_parallel_ini* and serial ports. The form is 0x00PS, where <P> is the number of * parallel ports and <S> is the number of serial ports. */ - card->numports = (dev->subsystem_device &0xf0 ) >>4 ; -if (card->numports >ARRAY_SIZE (card->addr)) - card->numports =ARRAY_SIZE (card->addr); + par->numports = (dev->subsystem_device &0xf0 ) >>4 ; +if (par->numports >ARRAY_SIZE (par->addr)) + par->numports =ARRAY_SIZE (par->addr); +/* +* This function is currently only called for cards with up to +* one parallel port. +* Parallel port BAR is either before or after serial ports BARS; +* hence, lo should be either 0 or equal to the number of serial ports. +*/ +if (par->addr[0 ].lo !=0 ) + par->addr[0 ].lo = dev->subsystem_device &0xf ;return 0 ; }
@@ -84,7 +93,8 @@ static struct parport_pc_pci cards[] __d /* titan_110l */ { 1, { { 3, -1 }, } }, /* titan_210l */ { 1, { { 3, -1 }, } }, /* netmos_9xx5_combo */ { 1, { { 2, -1 }, }, netmos_parallel_init }, - /* netmos_9855 */ { 1, { { 2, -1 }, }, netmos_parallel_init }, + /* netmos_9855 */ { 1, { { 0, -1 }, }, netmos_parallel_init }, + /* netmos_9855_2p */ { 2, { { 0, -1 }, { 2, -1 }, } }, /* avlab_1s1p */ { 1, { { 1, 2}, } }, /* avlab_1s2p */ { 2, { { 1, 2}, { 3, 4 },} }, /* avlab_2s1p */ { 1, { { 2, 3}, } },
@@ -109,6 +119,10 @@ static struct pci_device_id parport_seri PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9xx5_combo }, { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9845, PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9xx5_combo }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, + 0x1000, 0x0020, 0, 0, netmos_9855_2p }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, + 0x1000, 0x0022, 0, 0, netmos_9855_2p }, { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9855 }, /* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
@@ -192,6 +206,12 @@ static struct pciserial_board pci_parpor .uart_offset = 8, }, [netmos_9855] = { + .flags = FL_BASE2 | FL_BASE_BARS, + .num_ports = 1, + .base_baud = 115200, + .uart_offset = 8, + }, + [netmos_9855_2p] = { .flags = FL_BASE4 | FL_BASE_BARS, .num_ports = 1, .base_baud = 115200,
Quoted 2 lines · Philippe De Muyter
Hello list,
Hi,
Quoted 2 lines
Christian, can you verify that the patch below works for your netmos 9855 2P2S board ?
I compiled a kernel with this patch and I see both serial and both parallel ports in dmesg. I tested the serial ports and they work. Unfortunately I don't have any device around to test the parallel ports. You know, USB killed the pport stars.
Quoted 2 lines
Last fix of Christian Pellegrin for 9855 2P2S broke support for 9855 1P4S, and works only by side-effect for the first parallel port of a 2P2S,
sorry for that, I didn't know about the 1P4S version. This is the reason why I changed netmos9855 entry directyl.
Signature · 5 lines
Christian Pellegrin, see http://www.evolware.org/chri/ "Real Programmers don't play tennis, or any other sport which requires you to change clothes. Mountain climbing is OK, and Real Programmers wear their climbing boots to work in case a mountain should suddenly spring up in the middle of the computer room."
Quoted 11 lines · christian pellegrin
Quoted 2 lines · Philippe De Muyter
Hello list,
Hi,
Quoted 2 lines
Christian, can you verify that the patch below works for your netmos 9855 2P2S board ?
I compiled a kernel with this patch and I see both serial and both parallel ports in dmesg. I tested the serial ports and they work.
Thanks for your quick feedback.
Quoted 2 lines
Unfortunately I don't have any device around to test the parallel ports. You know, USB killed the pport stars.
I only use parallel ports for hardware debuggers.
Quoted 6 lines
Quoted 3 lines
Last fix of Christian Pellegrin for 9855 2P2S broke support for 9855 1P4S, and works only by side-effect for the first parallel port of a 2P2S,
sorry for that, I didn't know about the 1P4S version. This is the reason why I changed netmos9855 entry directyl.
No problem. I have not been affected. I needed to fix the 9845 1P4S support, but as I have also a computer with a 9855 1P4S, I did some code inspection there also and found your change.
Have a nice day
Philippe
PATCH 1/1 parport netmos 9845 & 9855 1P4S fixes
In reply to Philippe De MuyterHello list,
The same patch, with an additional Tested-by, after the positive feedback of Christian Pellegrin.
Philippe
--
netmos serial/parallel adapters come in different flavour differing only by the number of parallel and serial ports, which are encoded in the subdevice ID.
Last fix of Christian Pellegrin for 9855 2P2S broke support for 9855 1P4S, and works only by side-effect for the first parallel port of a 2P2S, as this first parallel port is found by reading the second addr entry of (struct parport_pc_pci) cards[netmos_9855], which is not initialized, and hence has value 0, which happens to be the BAR of the first parallel port.
netmos_9xx5_combo entry in (struct parport_pc_pci) cards[], which is used for a 9845 1P4S must also be fixed for the parallel port support when there are 4 serial ports because this entry currently gives 2 as BAR index for the parallel port. Actually, in this case, BAR 2 is the 3rd serial port while the parallel port is at BAR 4.
I fixed 9845 1P4S and 9855 1P4S support, while preserving 9855 2P2S support,
- by creating a netmos_9855_2p entry and using it for 9855 boards with 2 parallel ports : 9855 2P2S and 9855 2P0S boards,
- and by allowing netmos_parallel_init to change not only the number of parallel ports (0 or 1), but making it also change the BAR index of the parallel port when the serial ports are before the parallel port.
PS: the netmos_9855_2p entry in
(struct pciserial_board) pci_parport_serial_boards[] is needed because netmos_parallel_init has no clean way to replace FL_BASE2 by FL_BASE4 in the description of the serial ports in function of the number of parallel ports on the card.
Tested with 9845 1P4S, 9855 1P4S and 9855 2P2S boards.
drivers/parport/parport_serial.c +25 -5
@@ -30,6 +30,7 @@ enum parport_pc_pci_cards { titan_210l, netmos_9xx5_combo, netmos_9855, + netmos_9855_2p, avlab_1s1p, avlab_1s2p, avlab_2s1p,
@@ -62,7 +63,7 @@ struct parport_pc_pci { struct parport_pc_pci *card, int failed); }; -static int __devinit netmos_parallel_init (struct pci_dev *dev,struct parport_pc_pci *card,int autoirq,int autodma) +static int __devinit netmos_parallel_init (struct pci_dev *dev,struct parport_pc_pci *par,int autoirq,int autodma) {/* the rule described below doesn't hold for this device */ if (dev->device == PCI_DEVICE_ID_NETMOS_9835 &&
@@ -74,9 +75,17 @@ static int __devinit netmos_parallel_ini* and serial ports. The form is 0x00PS, where <P> is the number of * parallel ports and <S> is the number of serial ports. */ - card->numports = (dev->subsystem_device &0xf0 ) >>4 ; -if (card->numports >ARRAY_SIZE (card->addr)) - card->numports =ARRAY_SIZE (card->addr); + par->numports = (dev->subsystem_device &0xf0 ) >>4 ; +if (par->numports >ARRAY_SIZE (par->addr)) + par->numports =ARRAY_SIZE (par->addr); +/* +* This function is currently only called for cards with up to +* one parallel port. +* Parallel port BAR is either before or after serial ports BARS; +* hence, lo should be either 0 or equal to the number of serial ports. +*/ +if (par->addr[0 ].lo !=0 ) + par->addr[0 ].lo = dev->subsystem_device &0xf ;return 0 ; }
@@ -84,7 +93,8 @@ static struct parport_pc_pci cards[] __d /* titan_110l */ { 1, { { 3, -1 }, } }, /* titan_210l */ { 1, { { 3, -1 }, } }, /* netmos_9xx5_combo */ { 1, { { 2, -1 }, }, netmos_parallel_init }, - /* netmos_9855 */ { 1, { { 2, -1 }, }, netmos_parallel_init }, + /* netmos_9855 */ { 1, { { 0, -1 }, }, netmos_parallel_init }, + /* netmos_9855_2p */ { 2, { { 0, -1 }, { 2, -1 }, } }, /* avlab_1s1p */ { 1, { { 1, 2}, } }, /* avlab_1s2p */ { 2, { { 1, 2}, { 3, 4 },} }, /* avlab_2s1p */ { 1, { { 2, 3}, } },
@@ -109,6 +119,10 @@ static struct pci_device_id parport_seri PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9xx5_combo }, { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9845, PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9xx5_combo }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, + 0x1000, 0x0020, 0, 0, netmos_9855_2p }, + { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, + 0x1000, 0x0022, 0, 0, netmos_9855_2p }, { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855, PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9855 }, /* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
@@ -192,6 +206,12 @@ static struct pciserial_board pci_parpor .uart_offset = 8, }, [netmos_9855] = { + .flags = FL_BASE2 | FL_BASE_BARS, + .num_ports = 1, + .base_baud = 115200, + .uart_offset = 8, + }, + [netmos_9855_2p] = { .flags = FL_BASE4 | FL_BASE_BARS, .num_ports = 1, .base_baud = 115200,
Signature · 2 lines
Philippe De Muyter phdm at macqel dot be Tel +32 27029044 Macq Electronique SA rue de l'Aeronef 2 B-1140 Bruxelles Fax +32 27029077
RFC PATCH 1/1 vfat and Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
Hello vfat guru's
I have an IOMEGA home network hard disk that I can connect either by ethernet (ftp or cifs) or by USB. because of the ftp server mode firmware, I must keep it formatted as a vfat filesystem.
I have copied my music files on it using the ftp mode. Using the same ftp mode, I can also retrieve my music files without problem, and when I list them, they have the exact names that they had on my linux ext3 partition.
When I connected this disk via USB, now relying on the vfat module of linux, there were some directories that I could not reread. The common factor of these directories names is that they end with one or more dots, e.g.
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
If I issue the ls' or find' command, I get this strange message :
find: ./Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.: No such file or directory
Adding printk's in `fat_search_long' revealed that on this disk, the file/directory NAMES ENDING WITH DOTS ARE STORED WITH THEIR TRAILING DOTS.
Here is a patch squetch that make accessing my
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m. directory possible, but I
don't know if storing long filenames ending with dot's should not also be fixed.
fs/fat/namei_vfat.c +1 -4
@@ -702,10 +702,7 @@static int vfat_find (struct inode *dir,struct qstr *qname,struct fat_slot_info *sinfo) { -unsigned int len =vfat_striptail_len (qname); -if (len ==0 ) -return -ENOENT ; -return fat_search_long (dir, qname->name, len, sinfo); +return fat_search_long (dir, qname->name, qname->len, sinfo); } static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
OGAWA Hirofumi
maintainerRe: [PATCH RFC] vfat and Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
Quoted 20 lines · Philippe De Muyter
I have an IOMEGA home network hard disk that I can connect either by ethernet (ftp or cifs) or by USB. because of the ftp server mode firmware, I must keep it formatted as a vfat filesystem.
I have copied my music files on it using the ftp mode. Using the same ftp mode, I can also retrieve my music files without problem, and when I list them, they have the exact names that they had on my linux ext3 partition.
When I connected this disk via USB, now relying on the vfat module of linux, there were some directories that I could not reread. The common factor of these directories names is that they end with one or more dots, e.g.
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.If I issue the
ls' orfind' command, I get this strange message :find: ./Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.: No such file or directory
Quoted 7 lines
Adding printk's in `fat_search_long' revealed that on this disk, the file/directory NAMES ENDING WITH DOTS ARE STORED WITH THEIR TRAILING DOTS.
Here is a patch squetch that make accessing my
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m. directory possible, but I
don't know if storing long filenames ending with dot's should not also be fixed.
IIRC, Windows stripped the trailing ".". That filename can be read/used on Windows?
If it can be read, I think we should consider to remove vfat_striptail_len() (at least for lookup path), more investigation would be needed though.
Thanks.
Signature · 1 line
OGAWA Hirofumi <[email protected]>
Re: [PATCH RFC] vfat and Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
Hi Ogawa,
Quoted 25 lines · OGAWA Hirofumi
Quoted 23 lines · Philippe De Muyter
I have an IOMEGA home network hard disk that I can connect either by ethernet (ftp or cifs) or by USB. Because of the ftp server mode firmware, I must keep it formatted as a vfat filesystem.
I have copied my music files on it using the ftp mode. Using the same ftp mode, I can also retrieve my music files without problem, and when I list them, they have the exact names that they had on my linux ext3 partition.
When I connected this disk via USB, now relying on the vfat module of linux, there were some directories that I could not reread. The common factor of these directories names is that they end with one or more dots, e.g.
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.If I issue the
ls' orfind' command, I get this strange message :find: ./Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.: No such file or directory
Adding printk's in `fat_search_long' revealed that on this disk, the file/directory NAMES ENDING WITH DOTS ARE STORED WITH THEIR TRAILING DOTS.
Quoted 7 lines
Quoted 4 lines
Here is a patch sketch that makes accessing my
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m. directory possible, but I
don't know if storing long filenames ending with dot's should not also be fixed.IIRC, Windows stripped the trailing ".". That filename can be read/used on Windows?
Sorry I don't use MS-Windows. I'll try to find someone who does.
But, risking repeating myself, the firmware of the IOMEGA disk (via the ftp interface) presents the filenames with the trailing dots.
Quoted 3 lines
If it can be read, I think we should consider to remove
vfat_striptail_len()(at least for lookup path), more investigation would be needed though.
That's what my patch does actually. Maybe it should depend of the length of the filename, though.
Thanks
Philippe
Re: [PATCH RFC] vfat and Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
Hi Ogawa,
Quoted 33 lines · On Tue, Sep 29, 2009 at 12:25:59PM +0200, I wrote:
Hi Ogawa,
Quoted 30 lines · OGAWA Hirofumi
Quoted 27 lines · Philippe De Muyter
I have an IOMEGA home network hard disk that I can connect either by ethernet (ftp or cifs) or by USB. Because of the ftp server mode firmware, I must keep it formatted as a vfat filesystem.
I have copied my music files on it using the ftp mode. Using the same ftp mode, I can also retrieve my music files without problem, and when I list them, they have the exact names that they had on my linux ext3 partition.
When I connected this disk via USB, now relying on the vfat module of linux, there were some directories that I could not reread. The common factor of these directories names is that they end with one or more dots, e.g.
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.If I issue the
ls' orfind' command, I get this strange message :find: ./Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.: No such file or directory
Adding printk's in `fat_search_long' revealed that on this disk, the file/directory NAMES ENDING WITH DOTS ARE STORED WITH THEIR TRAILING DOTS.
Here is a patch sketch that makes accessing my
Simon_&_Garfunkel-Wednesday_Morning,_3_a.m. directory possible, but I
don't know if storing long filenames ending with dot's should not also be fixed.
Quoted 4 lines
Quoted 2 lines
IIRC, Windows stripped the trailing ".". That filename can be read/used on Windows?
Sorry I don't use MS-Windows. I'll try to find someone who does.
MS-Windows (XP SP3) lists correctly the names with their trailing dots.
Philippe
OGAWA Hirofumi
maintainerRe: [PATCH RFC] vfat and Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
Quoted 6 lines · Philippe De Muyter
Quoted 4 lines
Quoted 2 lines
IIRC, Windows stripped the trailing ".". That filename can be read/used on Windows?
Sorry I don't use MS-Windows. I'll try to find someone who does.
MS-Windows (XP SP3) lists correctly the names with their trailing dots.
Ok. Is it meaning you could read the file correctly? I guess so, and I'll review deeply about dcache issues for it.
Thanks.
Signature · 1 line
OGAWA Hirofumi <[email protected]>
Re: [PATCH RFC] vfat and Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
Quoted 11 lines · OGAWA Hirofumi
Quoted 6 lines · Philippe De Muyter
Quoted 4 lines
Quoted 2 lines
IIRC, Windows stripped the trailing ".". That filename can be read/used on Windows?
Sorry I don't use MS-Windows. I'll try to find someone who does.
MS-Windows (XP SP3) lists correctly the names with their trailing dots.
Ok. Is it meaning you could read the file correctly? I guess so, and I'll review deeply about dcache issues for it.
Sorry. I did not test enough yesterday. It was late :/
on MS-Windows XP SP#, the files and directories are listed with their real name, including the trailing dots, but if one tries to open such a file or go into such a directory, that fails with an error message.
With a "123456789." file :
Cannot find the E:\PUBLIC\trailing_dots\123456789. file. Do you want to create a new file?
Yes No Cancel
With a "directoryname." directory :
E\PUBLIC\trailing_dots\directoryname. refers to a location that is unavailable. It could be on a hard drive on this computer, or on a network. Check to make sure that the disk is properly inserted, or that you are connected to the Internet or your network, and then try again. If it still cannot be located, the information might have been moved to a different location.
OK
I don't think we want linux to remain compatible with this bug. So perhaps not removing the trailing dots for a lookup is all what is needed.
Best regards
Philippe
OGAWA Hirofumi
maintainerRe: [PATCH RFC] vfat and Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.
Quoted 19 lines · Philippe De Muyter
Sorry. I did not test enough yesterday. It was late :/
on MS-Windows XP SP#, the files and directories are listed with their real name, including the trailing dots, but if one tries to open such a file or go into such a directory, that fails with an error message.
With a "123456789." file :
Cannot find the E:\PUBLIC\trailing_dots\123456789. file. Do you want to create a new file?Yes No CancelWith a "directoryname." directory :
E\PUBLIC\trailing_dots\directoryname. refers to a location that is unavailable. It could be on a hard drive on this computer, or on a network. Check to make sure that the disk is properly inserted, or that you are connected to the Internet or your network, and then try again. If it still cannot be located, the information might have been moved to a different location.
OK
Quoted 2 lines
I don't think we want linux to remain compatible with this bug. So perhaps not removing the trailing dots for a lookup is all what is needed.
I think to make that filename readable is not crazy, however it would be the part of design.
And I found one issue for now, fs has to check existant file to make new file. But if lookup and creation was using different name, the check can not be done with that patch correctly.
Thanks.
Signature · 1 line
OGAWA Hirofumi <[email protected]>
PATCH 1/1 allow retrieving entries with trailing dots
This fixes accessing vfat entries with trailing dots created by an external vfat driver (like the one in IOMEGA home network hard drives)
Philippe
--
Some vfat-formatted network disks that are also usb disk do not discard trailing dots when creating files or directories via ftp. When connected via usb to a linux machine, that leads to this problem :
if one issues the ls' or find' command, one gets this message :
find: ./Simon_&_Garfunkel-Wednesday_Morning,_3_a.m.: No such file or directory
Fix that by first trying to retrieve the entry with the full name, and only if that fails and there are trailing dots in the searched name, try then to find the truncated name.
fs/fat/namei_vfat.c +14 -1
@@ -702,9 +702,22 @@static int vfat_find (struct inode *dir,struct qstr *qname,struct fat_slot_info *sinfo) { -unsigned int len =vfat_striptail_len (qname); +int err; +unsigned int len; + +/* Some combined ethernet + usb external hard drive do not +* remove the trailing dots when creating entries in ethernet mode. +* (e.g. Iomega Home Network Hard Drive) +* Make accessing those entries possible. +*/ + err =fat_search_long (dir, qname->name, qname->len, sinfo); +if (!err) +return err; + len =vfat_striptail_len (qname);if (len ==0 )return -ENOENT ; +if (len == qname->len) +return err;return fat_search_long (dir, qname->name, len, sinfo); }