summaryrefslogtreecommitdiff
path: root/arch/arm/mach-omap2
AgeCommit message (Collapse)AuthorFilesLines
2010-02-15omap2/3/4: Clean up entry-macro.s for adding support for omap4 multibootTony Lindgren1-4/+34
Move defines around and set up handlers based on MULTI_OMAP2. Note that this will only allow compiling in omap4 with omap2 and omap3. It will not yet make omap4 boot with multi-omap. Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap4: Use get_irqnr_preambleTony Lindgren1-1/+1
Use get_irqnr_preamble Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2/3/4: Clean up defines for entry-macro.STony Lindgren1-8/+7
Define the irq base the same way as for omap2 and omap3, and start using get_irqnr_preamble. Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2/3: Fix initcalls for multi-omapTony Lindgren2-1/+9
Otherwise the wrong initcalls can run. Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2/3/4: Replace orred CONFIG_ARCH_OMAP2/3/4 with CONFIG_ARCH_OMAP2PLUSTony Lindgren1-1/+1
omap: Replace orred CONFIG_ARCH_OMAP2/3/4 with CONFIG_ARCH_OMAP2PLUS Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap3: Replace ARCH_OMAP34XX with ARCH_OMAP3Tony Lindgren6-28/+23
Replace ARCH_OMAP34XX with ARCH_OMAP3 Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2: Convert ARCH_OMAP24XX to ARCH_OMAP2Tony Lindgren7-17/+13
Convert ARCH_OMAP24XX to ARCH_OMAP2 Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2/3/4: Fix mbox init for multi-omapTony Lindgren1-6/+24
Fix mbox init for multi-omap Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2/3/4: Fix omap2_map_common_io for multi-omapTony Lindgren21-37/+54
Fix omap2_map_common_io for multi-omap Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2/3: Multiboot compile fixes to compile in omap2 and omap3Tony Lindgren3-0/+39
Allows compiling in omap2 and omap3. Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap2/3: Make get_irqnr_and_base common for mach-omap2 multibootTony Lindgren1-20/+57
Make get_irqnr_and_base common for mach-omap2 multiboot Thanks to a tip from Russell King <rmk+kernel@arm.linux.org.uk>, this also optimizes the code for non-multiboot configurations by using get_irqnr_preamble. Note that this will only work currently for 24xx and 34xx. Support for 44xx can be added later on for basic multiboot, and similar patch should be done for mach-omap1/entry-macro.S. Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15Merge branch 'debug-ll' into omap-for-linusTony Lindgren4-36/+115
2010-02-15omap: Make uncompress code and DEBUG_LL code genericTony Lindgren1-22/+95
Define arch_decomp_setup() the same way as some other architectures do. Use arch_id to configure the debug uart based on the machine_is by storing it into the uart scratchpad register for DEBUG_LL code to use. Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-15omap: Clean the serial port definesTony Lindgren4-14/+20
This way we don't have conflicts with the defines with compiling in multiple omaps. Set the addresses for uarts in struct omap_globals for the early serial init code. Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-12Merge branch 'for-tony' of git://gitorious.org/linux-omap-dss2/linux into ↵Tony Lindgren3-12/+618
omap-for-linus
2010-02-12ARM: 5910/1: ARM: Add tmp register for addruart and loadspTony Lindgren1-1/+1
Otherwise more complicated uart configuration won't be possible. We can use r1 for tmp register for both head.S and debug.S. NOTE: This patch depends on another patch to add the the tmp register into all debug-macro.S files. That can be done with: $ sed -i -e "s/addruart,rx|addruart, rx/addruart, rx, tmp/" arch/arm/*/include/*/debug-macro.S Signed-off-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-02-12omap3: cm-t35: add DSS2 display supportMike Rapoport1-1/+238
Signed-off-by: Mike Rapoport <mike@compulab.co.il> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@nokia.com>
2010-02-12OMAP: AM3517: Enable DSS2 for AM3517EVM boardVaibhav Hiremath1-0/+145
Signed-off-by: Vaibhav Hiremath <hvaibhav@ti.com> [tomi.valkeinen@nokia.com: removed defconfig changes] Signed-off-by: Tomi Valkeinen <tomi.valkeinen@nokia.com>
2010-02-12OMAP: Enable DSS2 for OMAP3EVM boardVaibhav Hiremath1-11/+235
Signed-off-by: Vaibhav Hiremath <hvaibhav@ti.com> [tomi.valkeinen@nokia.com: removed evm defconfig changes] Signed-off-by: Tomi Valkeinen <tomi.valkeinen@nokia.com>
2010-02-11Merge branch 'omap-fixes-for-linus' into omap-for-linusTony Lindgren6-6/+78
2010-02-10OMAP: hsmmc: fix memory leakAaro Koskinen1-1/+6
The platform data allocated with kmalloc() will become unreachable once the init is complete, so it should be freed. The problem was discovered by kmemleak. Signed-off-by: Aaro Koskinen <aaro.koskinen@nokia.com> Acked-by: Adrian Hunter <adrian.hunter@nokia.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-03omap: Disable serial port autoidle by defaultTony Lindgren1-2/+9
Currently the omap serial clocks are autoidled after 5 seconds. However, this causes lost characters on the serial ports. As this is considered non-standard behaviour for Linux, disable the timeout. Note that this will also cause blocking of any deeper omap sleep states. To enable the autoidling of the serial ports, do something like this for each serial port: # echo 5 > /sys/devices/platform/serial8250.0/sleep_timeout # echo 5 > /sys/devices/platform/serial8250.1/sleep_timeout ... Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-03omap: Fix arch/arm/mach-omap2/mux.c: Off by one errorTony Lindgren1-1/+2
David Binderman ran the sourceforge tool cppcheck over the source code of the new Linux kernel 2.6.33-rc6: [./arm/mach-omap2/mux.c:492]: (error) Buffer access out-of-bounds 13 characters + 1 digit + 1 zero byte is more than 14 characters. Also add a comment on mode0 name length in case new omaps start using longer names. Reported-by: David Binderman <dcb314@hotmail.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-03omap: Fix 3630 mux errorsTony Lindgren2-0/+54
3630 has more mux signals than 34xx. The additional pins exist in omap36xx_cbp_subset, but are not initialized as the superset is missing these offsets. This causes the following errors during the boot: mux: Unknown entry offset 0x236 mux: Unknown entry offset 0x22e mux: Unknown entry offset 0x1ec mux: Unknown entry offset 0x1ee mux: Unknown entry offset 0x1f4 mux: Unknown entry offset 0x1f6 mux: Unknown entry offset 0x1f8 mux: Unknown entry offset 0x1fa mux: Unknown entry offset 0x1fc mux: Unknown entry offset 0x22a mux: Unknown entry offset 0x226 mux: Unknown entry offset 0x230 mux: Unknown entry offset 0x22c mux: Unknown entry offset 0x228 Fix this by adding the missing offsets to omap3 superset. Note that additionally the uninitialized pins need to be skipped on 34xx. Based on an earlier patch by Allen Pais <allen.pais@ti.com>. Reported-by: Allen Pais <allen.pais@ti.com> Signed-off-by: Allen Pais <allen.pais@ti.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-03OMAP2/3: GPMC: ensure valid clock pointerKevin Hilman1-1/+4
Ensure valid clock pointer during GPMC init. Fixes compiler warning about potential use of uninitialized variable. Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-02-03OMAP2/3: IRQ: ensure valid base addressKevin Hilman1-1/+3
Ensure valid base address during IRQ init. Fixes compiler warning about potential use of uninitialized variable. Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com> Signed-off-by: Tony Lindgren <tony@atomide.com>
2010-01-29OMAP2+ powerdomains/clockdomains: prepare for multi-OMAP configsPaul Walmsley3-40/+40
Convert CONFIG_ARCH_OMAP34XX to CONFIG_ARCH_OMAP3, and CONFIG_ARCH_OMAP24XX to CONFIG_ARCH_OMAP2, in preparation for Tony's multi-OMAP patches. While here, update some copyrights, convert instances of "34xx" to "3xxx" where applicable, and convert preprocessor directives of the form #if defined(CONFIG_ARCH_OMAP2) | defined(CONFIG_ARCH_OMAP3) to #if defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3) for standardization. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Tony Lindgren <tony@atomide.com>
2010-01-29OMAP4: PRCM: Define shift macros as n instead of 1 << nRajendra Nayak2-773/+773
The macros defining the shift bits in registers for various register bit fields are defined as 1 << n. Instead define them as n. They can then be used as val << n. The changes are generated by updating the script which autogenerates the files modifed in the patch. Signed-off-by: Rajendra Nayak <rnayak@ti.com> Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-29OMAP2/3/4 clock: rename and clean the omap2_clk_init() functionsPaul Walmsley9-26/+21
Rename the omap2_clk_init() in the OMAP2, 3, and 4 clock code to be omap2xxx_clk_init(), omap3xxx_clk_init(), etc. Remove all traces of the (commented) old virt_prcm_set code from omap3xxx_clk_init() and omap4xxx_clk_init(), since this will be handled with the OPP code that is cooking in the PM branch. After this patch, there should be very little else in the clock code that blocks a multi-OMAP 2+3 kernel. (OMAP2420+OMAP2430 still has some outstanding issues that need to be resolved; this is pending on some additions to the hwmod data.) Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-29OMAP3 DPLL: reorganize static functionsPaul Walmsley1-55/+58
Move all static functions up to the top of the file to match the practice in other OMAP clock code. Make omap3_noncore_dpll_program() static (noted by sparse) and prepend an underscore to the function name to mark that it is file-local. Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-29OMAP2/3/4 clock: omap2_clk_prepare_for_reboot() is OMAP2xxx-onlyPaul Walmsley6-29/+9
omap2_clk_prepare_for_reboot() is only applicable to OMAP2xxx chips, so rename it to omap2xxx_clk_prepare_for_reboot() and only call it when running on OMAP2xxx chips. Remove the old stub in the OMAP3 clock code. Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-29OMAP2/3 clock: remove unnecessary includes and clean up headerPaul Walmsley2-38/+13
Now that almost all of the code has been removed from clock2xxx.c and clock34xx.c, many of the includes are now unnecessary and can be removed. While we're here, standardize the initial comment blocks. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Richard Woodruff <r-woodruff2@ti.com> Cc: Jouni Högander <jouni.hogander@nokia.com>
2010-01-29OMAP2/3 clock: clean up omap*_clk_arch_init()Paul Walmsley2-13/+10
In the OMAP3xxx clock code, remove the #ifdef CONFIG_ARCH_OMAP3 in clock34xx.c, since this file is only compiled for OMAP3xxx builds. Also, rename omap2_clk_arch_init in this file to omap3xxx_clk_arch_init() to pave the way for multi-OMAP kernels. Ensure that it is not executed on non-OMAP3xxx systems. In the OMAP2xxx clock code, rename omap2_clk_arch_init in this file to omap2xxx_clk_arch_init() to pave the way for multi-OMAP kernels. Ensure that it is not executed on non-OMAP2xxx systems. Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-29OMAP3 clock: split out DPLL3 M2 divider functions into ↵Paul Walmsley3-91/+122
mach-omap2/clkt34xx_dpll3m2.c Split the DPLL3 M2 divider clock functions out of clock34xx.c and move them into mach-omap2/clkt34xx_dpll3m2.c. This is intended to make the clock code easier to understand, since all of the functions needed to manage the OMAP3 DPLL3 M2 divider are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for the DPLL3 M2 clock alone. This should reduce unnecessary console noise when debugging DVFS. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap34xx/ directory, rather than shared with other chip types that don't use this clock type. This patch also lays the groundwork to skip compilation of this code on OMAP3 chips that don't support DVFS (e.g., AM35xx) via the Makefile, rather than via #ifdefs. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to improve the patch description. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Jouni Högander <jouni.hogander@nokia.com> Cc: Alexander Shishkin <virtuoso@slind.org>
2010-01-29OMAP2 clock: don't compile OMAP2430-only functions on non-2430 buildsPaul Walmsley1-0/+6
omap2430_clk_i2chs_find_idlest() doesn't need to be compiled in on non-2430 builds, so skip it in those cases to save memory. Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-29OMAP2xxx clock: move sys_clk code into mach-omap2/clkt2xxx_sys.cPaul Walmsley5-35/+55
Move the sys_clk clock functions from clock2xxx.c to mach-omap2/clkt2xxx_sys.c. This is intended to make the clock code easier to understand, since all of the functions needed to manage the sys_clk are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for the sys_clk clock alone. This should reduce unnecessary console noise when debugging. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/ directory, rather than shared with other chip types that don't use this clock type. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to improve the patch description. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Alexander Shishkin <virtuoso@slind.org>
2010-01-29OMAP2xxx clock: move osc_clk code into mach-omap2/clkt2xxx_osc.cPaul Walmsley4-33/+66
Move the osc_clk clock functions from clock2xxx.c to mach-omap2/clkt2xxx_osc. This is intended to make the clock code easier to understand, since all of the functions needed to manage the osc_clk are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for osc_clk clocks alone. This should reduce unnecessary console noise when debugging. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/ directory, rather than shared with other chip types that don't use this clock type. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to improve the patch description. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Alexander Shishkin <virtuoso@slind.org>
2010-01-29OMAP2xxx clock: move the APLL clock code into mach-omap2/clkt2xxx_apll.cPaul Walmsley4-86/+124
Move the APLL-related clock functions from clock2xxx.c to mach-omap2/clkt2xxx_apll.c. This is intended to make the clock code easier to understand, since all of the functions needed to manage APLLs are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for APLL clocks alone. This should reduce unnecessary console noise when debugging. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/ directory, rather than shared with other chip types that don't use this clock type. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to improve the patch description. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Richard Woodruff <r-woodruff2@ti.com> Cc: Alexander Shishkin <virtuoso@slind.org>
2010-01-27OMAP2xxx clock: move the DVFS virtual clock code into ↵Paul Walmsley3-212/+256
mach-omap2/clkt2xxx_virt_prcm_set.c Move the DVFS virtual clock functions from clock2xxx.c to mach-omap2/clkt2xxx_virt_prcm_set.c. This is intended to make the clock code easier to understand, since all of the functions needed to manage the virt_prcm_set clock are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for the virt_prcm_set clock alone. This should reduce unnecessary console noise when debugging. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/ directory, rather than shared with other chip types that don't use this clock type. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments. Thanks also to Kevin Hilman <khilman@deeprootsystems.com> for finding and fixing a bug with the CONFIG_CPU_FREQ portion of this patch. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Richard Woodruff <r-woodruff2@ti.com> Cc: Alexander Shishkin <virtuoso@slind.org> Cc: Kevin Hilman <khilman@deeprootsystems.com>
2010-01-27OMAP2xxx clock: move the DPLL+CORE composite clock code into ↵Paul Walmsley3-137/+176
mach-omap2/clkt2xxx_dpllcore.c Move the DPLL+CORE composite clock functions from clock2xxx.c to mach-omap2/clkt2xxx_dpllcore.c. This is intended to make the clock code easier to understand, since all of the functions needed to manage the OMAP2 DPLL+CORE clock are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for the DPLL+CORE clock alone. This should reduce unnecessary console noise when debugging. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/ directory, rather than shared with other chip types that don't use this clock type. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to improve the patch description. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Richard Woodruff <r-woodruff2@ti.com> Cc: Alexander Shishkin <virtuoso@slind.org>
2010-01-27OMAP2/3/4 clock: combine all omap2_clk_functionsPaul Walmsley5-33/+32
The struct clk_functions for OMAP2, 3, and 4 are all essentially the same, so combine them. This removes one multi-OMAP kernel impediment and saves memory on multi-OMAP builds. The stubs for omap2_clk_{init,exit}_cpufreq() code will removed once the OPP layer code that's currently in Kevin's PM branch is merged. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Kevin Hilman <khilman@deeprootsystems.com>
2010-01-27OMAP2 clock: move all static functions to the top of the filePaul Walmsley1-42/+46
Move static functions to the top of the file and ensure that their names are prefixed with an underscore to conform with the practice in the newer OMAP clock code files. Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-27OMAP2/3/4 clock: move clksel clock functions into mach-omap2/clkt_clksel.cPaul Walmsley4-375/+424
Move all clksel-related clock functions from mach-omap2/clock.c to mach-omap2/clkt_clksel.c. This is intended to make the clock code easier to understand, since all of the functions needed to manage clksel clocks are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for clksel clocks alon. This should reduce unnecessary console noise when debugging. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be moved to the plat-omap/ directory to be shared. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to improve the patch description. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Alexander Shishkin <virtuoso@slind.org>
2010-01-27OMAP2/3/4 clock: move DPLL clock functions into mach-omap2/clkt_dpll.cPaul Walmsley3-356/+388
Move all DPLL-related clock functions from mach-omap2/clock.c to mach-omap2/clkt_dpll.c. This is intended to make the clock code easier to understand, since all of the functions needed to manage DPLLs are now located in their own file, rather than being mixed with other, unrelated functions. Clock debugging is also now more finely-grained, since the DEBUG macro can now be defined for DPLLs alone. This should reduce unnecessary console noise when debugging. Also, if at some future point the mach-omap2/ directory is split into OMAP2/3/4 variants, this clkt file can be moved to the plat-omap/ directory to be shared. Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to improve the patch description. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Alexander Shishkin <virtuoso@slind.org>
2010-01-27OMAP3 clock: move OMAP3-specific DPLL functions to dpll3xxx.cPaul Walmsley2-1/+1
Mark the OMAP3-specific DPLL functions as being OMAP3-specific by moving them from mach-omap2/dpll.c to mach-omap2/dpll3xxx.c. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Rajendra Nayak <rnayak@ti.com>
2010-01-27OMAP: hwmod: add API for slave idlemode settingKevin Hilman1-0/+17
Some HW blocks have errata which requires specific slave idle mode under certain conditions. This patch adds an hwmod API to allow setting slave idlemode ensuring that any SYSCONFIG register updates go through hwmod. Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com> Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-27OMAP clockdomain/powerdomain: improve documentationPaul Walmsley2-104/+110
This patch only affects documentation; no functional changes are included. Clean up comments in the current clockdomain, powerdomain code and header files. This mostly involves conversion to kerneldoc format, although some clarifications are also included. Signed-off-by: Paul Walmsley <paul@pwsan.com>
2010-01-27OMAP powerdomain: remove pwrdm_clk_state_switchPaul Walmsley1-6/+0
Nothing calls pwrdm_clk_state_switch(), and the function that seems to be its ideal use case calls pwrdm_clkdm_state_switch(clk->clkdm), so remove it. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Tero Kristo <tero.kristo@nokia.com> Cc: Kevin Hilman <khilman@deeprootsystems.com>
2010-01-27OMAP powerdomain/PM: use symbolic constants for the max number of power statesPaul Walmsley1-1/+1
Replace some bare constants with symbolic constants. Signed-off-by: Paul Walmsley <paul@pwsan.com> Cc: Kevin Hilman <khilman@deeprootsystems.com>
2010-01-27OMAP clockdomains: add usecounting for wakeup and sleep dependenciesPaul Walmsley3-39/+229
Add usecounting for wakeup and sleep dependencies. In the current situation, if several functions add dependencies on the same clockdomains, when the first dependency removal function is called, the dependency will be incorrectly removed from the hardware. Add clkdm_clear_all_wkdeps() and clkdm_clear_all_sleepdeps(), which provide a fast and usecounting-consistent way to clear all hardware clockdomain dependencies, since accesses to these registers can be quite slow. pm{2,3}4xx.c has been updated to use these new functions. The original version of this patch did not touch these files, which previously wrote directly to the wkdep registers, and thus confused the usecounting code. This problem was found by Kevin Hilman <khilman@deeprootsystems.com>. N.B.: This patch introduces one significant functional difference over the previous pm34xx.c code: sleepdeps are now cleared during clockdomain initialization, whereas previously they were left untouched. This has been tested by Kevin and confirmed to work. The original version of this patch also did not take into consideration that some clockdomains do not have sleep or wakeup dependency sources, which caused NULL pointer dereferences. This problem was debugged and fixed by Kevin Hilman <khilman@deeprootsystems.com>. Signed-off-by: Paul Walmsley <paul@pwsan.com> Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com> Cc: Jouni Högander <jouni.hogander@nokia.com>
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-23 14:56:51 +0300