summaryrefslogtreecommitdiffstats
path: root/arch
Commit message (Collapse)AuthorAgeFilesLines
* [PATCH] ARM: OMAP: Check gpio_fck not gpio_ickKomal Shah2006-09-251-1/+1
| | | | | | | Check gpio_fck not gpio_ick. Signed-off-by: Komal Shah <komal_shah802003@yahoo.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Sync DMA with linux-omap treeTony Lindgren2006-09-251-21/+64
| | | | | | | | This patch syncs OMAP DMA code with linux-omap tree. Mostly allow changing DMA callback function and set OMAP2 specific transfer mode. Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP2: Make sure peripherals can be accessed after clk_enableJuha Yrjola2006-09-251-1/+47
| | | | | | | | Some peripherals seem to need additional delay until they can actually be accessed after enabling their FCLK and ICLK. Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP2: Keep both APLLs active during bootupJuha Yrjola2006-09-251-0/+15
| | | | | | | | | Enabling and disabling the 54 MHz and 96 MHz APLLs can happen unnecessarily often during bootup. Make sure they're kept enabled during init. Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Add sanity check to clk_disableJuha Yrjola2006-09-251-0/+1
| | | | | | | BUG() if the clock use count is already zero. Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: GPIO: IRQSTATUS2 workaround for retention stateHiroshi DOYU2006-09-251-0/+6
| | | | | | | | | | | | | In OMAP2420, an incoming GPIO interrupt always sets both GPIO_IRQSTATUS1 and GPIO_IRQSTATUS2, even if the relevant bit is disabled in GPIO_IRQENABLE1/2 and DSP doesn't use GPIO at all. GPIO_IRQSTATUS1 is for MPU and GPIO_IRQSTATUS2 is for DSP. If IRQSTATUS is set, this will prevent the system from going to idle state. This patch also clears IRQSTATUS2 to avoid the above situation. Signed-off-by: Hiroshi DOYU <Hiroshi.DOYU@nokia.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Fix typo for 24xx GPIO resumeTony Lindgren2006-09-251-2/+2
| | | | | | Fix typo for 24xx GPIO resume Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: OMAP2 dmtimer power management supportJuha Yrjola2006-09-251-1/+9
| | | | | | | | GPT1 will be set into non-posted mode, and the wakeup register is set for all timers. Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Add support for forcing osc_ck onJuha Yrjola2006-09-252-1/+19
| | | | | | | | | Some boards might use the oscillator clock for powering external peripherals. Add support for making sure osc_ck stays active even when trying to go to sleep. Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Add enable/disable functions for dmtimerTimo Teras2006-09-251-42/+31
| | | | | | | | Add enable/disable functions which effectively control the GPT iclk and fclk. Signed-off-by: Timo Teras <timo.teras@solidboot.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Remove Remove superfluous/recursive locking for GPIODavid Brownell2006-09-251-2/+0
| | | | | | | Remove Remove superfluous/recursive locking for GPIO Signed-off-by: David Brownell <dbrownell@users.sourceforge.net> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Fix spinlock recursion for dyntickTony Lindgren2006-09-251-6/+20
| | | | | | | Fix spinlock recursion for dyntick. Modified version based on Imre Deak's earlier patch. Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Remove IVA IRQ bankKomal Shah2006-09-251-12/+0
| | | | | | | | | | | | | | | ARM11 can't access the IVA interrupt controller from IVA slave port. From Richard Woodruff: "The 0x40000000 is an IVA-ARM7 local bus address. The IVA-INTC is NOT accessible through the IVA-L3-Slave Port. The current TRM does say this directly and indirectly in a few spots and in figures." Signed-off-by: Komal Shah <komal_shah802003@yahoo.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Reset GPIO irq state after free_irq()Tony Lindgren2006-09-251-4/+21
| | | | | | This is needed to reset GPIO after free_irq(). Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Add write memory barriers to OMAP2 clock codeJuha Yrjola2006-09-251-4/+10
| | | | | | | | | | After adjusting clock parameters, OMAP2 CPUs need a memory barrier to make sure the changes go into effect immediately. Otherwise bad things will happen if we try to access the peripheral whose clock is just being enabled. Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Fix OMAP2 clock.c typoSamuel Ortiz2006-09-251-1/+1
| | | | | | | | | A forgotten parenthesis in clock.c caused the PLL stabilization loop to not be executed correctly. Signed-off-by: Samuel Ortiz <samuel.ortiz@solidboot.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Use GPT iclk only when neededTimo Teras2006-09-251-13/+62
| | | | | | | | | | This patch makes the OMAP2 dmtimers module using the interface clocks only while the registers are accessed (except GPT1 which has iclk enabled all the time). Signed-off-by: Timo Teras <timo.teras@solidboot.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: DMA source and destination addresses are unsignedTony Lindgren2006-09-251-0/+2
| | | | | | Also export some omap24xx specific DMA functions. Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP2: Dynamic allocator for GPMC memory spaceImre Deak2006-09-251-2/+178
| | | | | | | | | | | | | Add support for assigning memory regions dynamically to peripherals attached to GPMC interface. Platform specific code should now call gpmc_cs_request to get a free GPMC memory region instead of using a fixed address. Make the H4 and Apollon platform initialization use the new API. Signed-off-by: Imre Deak <imre.deak@solidboot.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Fix OMAP1 compilation after MPUIO check changeJonathan McDowell2006-09-251-1/+1
| | | | | | | | | The recent MPUIO range change fix breaks compilation if CONFIG_ARCH_OMAP24XX isn't defined; it should be OMAP_MAX_GPIO_LINES not MAX_GPIO_LINES I believe. This one liner fixes it. Signed-off-by: Jonathan McDowell <noodles@earth.li> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: mux: add config for 16xx SPI pinsMark Howell2006-09-251-0/+11
| | | | | | | | | This patch adds pin mux info for the SPI master/slave interface on OMAP16xx. Data from OMAP 1611/1612 TRM and errata. Works for me on my 1611/H2 with current git kernel. Signed-off-by: Mark Howell <mhowell@northlink.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Sleep is prevented when no LCD is attachedImre Deak2006-09-251-0/+8
| | | | | | | | | We have to make sure that the LCD DMA external destination bit is cleared by default, otherwise OMAP won't sleep. Signed-off-by: Imre Deak <imre.deak@solidboot.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: GPIO: fix MPUIO checkImre Deak2006-09-251-3/+3
| | | | | | | | | - MPUIO doesn't exist on OMAP2 - no error was returned for too big MPUIO numbers Signed-off-by: Imre Deak <imre.deak@solidboot.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Remove sys_ck and sys_clkout from McBSP for 24xxTony Lindgren2006-09-251-9/+0
| | | | | | | McBSP does not need sys_ck or sys_clkout. If the devices connected to McBSP need sys_clkout, they need to request it. Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Apollon MMC supportKyungmin Park2006-09-253-5/+36
| | | | | | | | | | Apollon board MMC supports on OMAP2 TODO: We have to check MMC on H4 Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: 2420 boot BUG(): failure to map SRAMKevin Hilman2006-09-251-4/+1
| | | | | | | | | ARM: OMAP: Fix SRAM static mapping for EMU devices. Fix SRAM static mapping for EMU devices. Signed-off-by: Kevin Hilman <khilman@deeprooted.net> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: timer32k: fix tick count calculation when reprogrammingImre Deak2006-09-251-1/+11
| | | | | | | | | | | | | | | Reprogramming takes places before putting the CPU into idle mode if the dynamic tick option is enabled. The timer is then set to expire at the next pending timer event. Because some time has already passed since the last reported jiffy we have to wait less than the time specified in jiffies. Also make sure we don't set a load value of 0 whose outcome is unspecified according to the TRM. Signed-off-by: Imre Deak <imre.deak@solidboot.com> Signed-off-by: Juha Yrjola <juha.yrjola@solidboot.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
* ARM: OMAP: Avoid sleeping during arch_resetTony Lindgren2006-09-252-7/+23
| | | | | | | If we call clk_get() from arch_reset we get ugly messages before reboot. Signed-off-by: Tony Lindgren <tony@atomide.com>
* Merge branch 'master' of ↵David Woodhouse2006-09-24196-3223/+7250
|\ | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6
| * [SPARC64]: Update defconfig.David S. Miller2006-09-231-6/+19
| | | | | | | | Signed-off-by: David S. Miller <davem@davemloft.net>
| * [SPARC64]: Fix sched_clock() wrapping every ~17 seconds.David S. Miller2006-09-231-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Unfortunately, sparc64 doesn't have an easy way to do a "64 X 64 --> 128" bit multiply like PowerPC and IA64 do. We were doing a "64 X 64 --> 64" bit multiple which causes overflow very quickly with a 30-bit quotient shift. So use a quotientshift count of 10 instead of 30, just like x86 and ARM do. This also fixes the wrapping of printk timestamp values every ~17 seconds. Signed-off-by: David S. Miller <davem@davemloft.net>
| * [PATCH] more fallout from get_property returning pointer to constAl Viro2006-09-232-3/+3
| | | | | | | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
| * Merge master.kernel.org:/pub/scm/linux/kernel/git/davej/cpufreqLinus Torvalds2006-09-224-75/+240
| |\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * master.kernel.org:/pub/scm/linux/kernel/git/davej/cpufreq: [CPUFREQ] sw_any_bug_dmi_table can be used on resume, so it isn't initdata [CPUFREQ] Fix some more CPU hotplug locking. [CPUFREQ] Workaround for BIOS bug in software coordination of frequency [CPUFREQ] Longhaul - Add voltage scaling to driver [CPUFREQ] Fix sparse warning in ondemand [CPUFREQ] make drivers/cpufreq/cpufreq_ondemand.c:powersave_bias_target() static [CPUFREQ] Longhaul - Add ignore_latency option [CPUFREQ] Longhaul - Disable arbiter [CPUFREQ][2/2] ondemand: updated add powersave_bias tunable [CPUFREQ][1/2] ondemand: updated tune for hardware coordination [CPUFREQ] Fix typo.
| | * [CPUFREQ] sw_any_bug_dmi_table can be used on resume, so it isn't initdataJeremy Fitzhardinge2006-09-221-1/+1
| | | | | | | | | | | | | | | | | | | | | sw_any_bug_dmi_table can be used on resume, so it isn't initdata. Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Dave Jones <davej@redhat.com>
| | * [CPUFREQ] Workaround for BIOS bug in software coordination of frequencyVenkatesh Pallipadi2006-09-052-2/+79
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Some buggy BIOSes do a "software any" kind of coordination without telling about it to OS. So, when OS sets frequency on one CPU on these platforms, it will also impact all the other logical CPUs that are in the same power domain. Attached patch is a workaround for those buggy BIOSes. Patch should be a noop on the normal non-buggy platforms. Applies over previously sent acpi-cpufreq and software coordination bug fix patch Signed-off-by: Denis Sadykov <denis.m.sadykov@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Alexey Starikovskiy <alexey.y.starikovskiy@intel.com> Signed-off-by: Dave Jones <davej@redhat.com>
| | * [CPUFREQ] Longhaul - Add voltage scaling to driverRafał Bilski2006-09-052-51/+94
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Rename option "dont_scale_voltage" to "scale_voltage" because don't will be default. Use "pos" for calculating voltage. In this way driver don't need to know mV value or low level value. Simply min U is one pos and max U is second pos. All pos between these two are used. Assume that min U is for min f and max U for max f. For frequency between min and max calculate pos based on difference between current frequency and min f. Values in mobile VRM table changed to values from C3-M datasheet. Signed-off-by: Rafał Bilski <rafalbilski@interia.pl> Signed-off-by: Dave Jones <davej@redhat.com>
| | * Merge ../linusDave Jones2006-09-05140-1838/+5149
| | |\
| | * | [CPUFREQ] Longhaul - Add ignore_latency optionRafał Bilski2006-08-141-3/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Some laptops with VIA C3 processor, CLE266 chipset and AMI BIOS have incorrect latency values in FADT table. These laptops seems to be C3 capable, but latency values are to big: 101 for C2 and 1017 for C3. This option will allow user to skip C3 latency test but not C3 address test. AMI BIOS is setting C3 address to correct value in DSDT table. Signed-off-by: Rafał Bilski <rafalbilski@interia.pl> Signed-off-by: Dave Jones <davej@redhat.com>
| | * | [CPUFREQ] Longhaul - Disable arbiterRafał Bilski2006-08-111-22/+64
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ACPI C3 works for "Powersaver" processors, so use it only for them. Older CPU will change frequency on "halt" only. But we can protect transition in two ways: - by ACPI PM2 register, there is "bus master arbiter disable" bit. This isn't tested because VIA mainboards don't have PM2 register, - by PLE133 PCI/AGP arbiter disable register. There are two bits in this register. First is "PCI arbiter disable", second "AGP arbiter disable". This is working on VIA Epia 800 mainboards. Test on bm_control is more proper because this is true when PM2 register exist. Signed-off-by: Rafał Bilski <rafalbilski@interia.pl> Signed-off-by: Dave Jones <davej@redhat.com>
| * | | [PATCH] sun4: fix sbus_setup_iommu()Al Viro2006-09-221-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | iommu_init() and iounit_init() are never called for sun4, but that's not enough - these calls should be ifdefed out since the functions in question simply do not exist for CONFIG_SUN4 kernel. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
| * | | [PATCH] sanitize frv archcleanAl Viro2006-09-222-5/+3
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
| * | | [PATCH] fix ancient breakage in ebus_init()Al Viro2006-09-221-4/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Back when pci_dev had base_address[], loop of form base = &...->base_address[0]; for (.....) { ... *base++ = addr; } was fine, but when that array got spread in ->resource[...].start replacing the initialization with base = &...->resource[0].start; was not a sufficient modification. IOW this code got broken for cases when there had been more than one resource to fill. All way back in 2.3.41-pre3... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
| * | | Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6Linus Torvalds2006-09-2213-289/+1429
| |\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (64 commits) [BLOCK] dm-crypt: trivial comment improvements [CRYPTO] api: Deprecate crypto_digest_* and crypto_alg_available [CRYPTO] padlock: Convert padlock-sha to use crypto_hash [CRYPTO] users: Use crypto_comp and crypto_has_* [CRYPTO] api: Add crypto_comp and crypto_has_* [CRYPTO] users: Use crypto_hash interface instead of crypto_digest [SCSI] iscsi: Use crypto_hash interface instead of crypto_digest [CRYPTO] digest: Remove old HMAC implementation [CRYPTO] doc: Update documentation for hash and me [SCTP]: Use HMAC template and hash interface [IPSEC]: Use HMAC template and hash interface [CRYPTO] tcrypt: Use HMAC template and hash interface [CRYPTO] hmac: Add crypto template implementation [CRYPTO] digest: Added user API for new hash type [CRYPTO] api: Mark parts of cipher interface as deprecated [PATCH] scatterlist: Add const to sg_set_buf/sg_init_one pointer argument [CRYPTO] drivers: Remove obsolete block cipher operations [CRYPTO] users: Use block ciphers where applicable [SUNRPC] GSS: Use block ciphers where applicable [IPSEC] ESP: Use block ciphers where applicable ...
| | * | | [CRYPTO] drivers: Remove obsolete block cipher operationsHerbert Xu2006-09-212-315/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch removes obsolete block operations of the simple cipher type from drivers. These were preserved so that existing users can make a smooth transition. Now that the transition is complete, they are no longer needed. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| | * | | [CRYPTO] s390: Added block cipher versions of CBC/ECBHerbert Xu2006-09-213-14/+590
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds block cipher algorithms for S390. Once all users of the old cipher type have been converted the existing CBC/ECB non-block cipher operations will be removed. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| | * | | [CRYPTO] s390: Added missing driver name and priorityHerbert Xu2006-09-215-0/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Accelerated versions of crypto algorithms must carry a distinct driver name and priority in order to distinguish themselves from their generic counter- part. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| | * | | [CRYPTO] api: Get rid of flags argument to setkeyHerbert Xu2006-09-214-9/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Now that the tfm is passed directly to setkey instead of the ctx, we no longer need to pass the &tfm->crt_flags pointer. This patch also gets rid of a few unnecessary checks on the key length for ciphers as the cipher layer guarantees that the key length is within the bounds specified by the algorithm. Rather than testing dia_setkey every time, this patch does it only once during crypto_alloc_tfm. The redundant check from crypto_digest_setkey is also removed. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| | * | | [CRYPTO] twofish: x86-64 assembly versionJoachim Fritschi2006-09-213-0/+424
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The patch passed the trycpt tests and automated filesystem tests. This rewrite resulted in some nice perfomance increase over my last patch. Short summary of the tcrypt benchmarks: Twofish Assembler vs. Twofish C (256bit 8kb block CBC) encrypt: -27% Cycles decrypt: -23% Cycles Twofish Assembler vs. AES Assembler (128bit 8kb block CBC) encrypt: +18% Cycles decrypt: +15% Cycles Twofish Assembler vs. AES Assembler (256bit 8kb block CBC) encrypt: -9% Cycles decrypt: -8% Cycles Full Output: http://homepages.tu-darmstadt.de/~fritschi/twofish/tcrypt-speed-twofish-c-x86_64.txt http://homepages.tu-darmstadt.de/~fritschi/twofish/tcrypt-speed-twofish-asm-x86_64.txt http://homepages.tu-darmstadt.de/~fritschi/twofish/tcrypt-speed-aes-asm-x86_64.txt Here is another bonnie++ benchmark with encrypted filesystems. Most runs maxed out the hd. It should give some idea what the module can do for encrypted filesystem performance even though you can't see the full numbers. http://homepages.tu-darmstadt.de/~fritschi/twofish/output_20060610_130806_x86_64.html Signed-off-by: Joachim Fritschi <jfritschi@freenet.de> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| | * | | [CRYPTO] twofish: i586 assembly versionJoachim Fritschi2006-09-213-0/+435
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The patch passed the trycpt tests and automated filesystem tests. This rewrite resulted in some nice perfomance increase over my last patch. Short summary of the tcrypt benchmarks: Twofish Assembler vs. Twofish C (256bit 8kb block CBC) encrypt: -33% Cycles decrypt: -45% Cycles Twofish Assembler vs. AES Assembler (128bit 8kb block CBC) encrypt: +3% Cycles decrypt: -22% Cycles Twofish Assembler vs. AES Assembler (256bit 8kb block CBC) encrypt: -20% Cycles decrypt: -36% Cycles Full Output: http://homepages.tu-darmstadt.de/~fritschi/twofish/tcrypt-speed-twofish-asm-i586.txt http://homepages.tu-darmstadt.de/~fritschi/twofish/tcrypt-speed-twofish-c-i586.txt http://homepages.tu-darmstadt.de/~fritschi/twofish/tcrypt-speed-aes-asm-i586.txt Here is another bonnie++ benchmark with encrypted filesystems. All runs with the twofish assembler modules max out the drivespeed. It should give some idea what the module can do for encrypted filesystem performance even though you can't see the full numbers. http://homepages.tu-darmstadt.de/~fritschi/twofish/output_20060611_205432_x86.html Signed-off-by: Joachim Fritschi <jfritschi@freenet.de> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | | Merge branch 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6Linus Torvalds2006-09-2234-980/+2466
| |\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6: (44 commits) [S390] hypfs crashes with invalid mount option. [S390] cio: subchannel evaluation function operates without lock [S390] cio: always query all paths on path verification. [S390] cio: update path groups on logical CHPID changes. [S390] cio: subchannels in no-path state. [S390] Replace nopav-message on VM. [S390] set modalias for ccw bus uevents. [S390] Get rid of DBG macro. [S390] Use alternative user-copy operations for new hardware. [S390] Make user-copy operations run-time configurable. [S390] Cleanup in signal handling code. [S390] Cleanup in page table related code. [S390] Linux API for writing z/VM APPLDATA Monitor records. [S390] xpram off by one error. [S390] Remove kexec experimental flag. [S390] cleanup appldata. [S390] fix typo in vmcp. [S390] Kernel stack overflow handling. [S390] qdio slsb processing state. [S390] Missing initialization in common i/o layer. ...
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-19 14:12:33 +0000