Re: [PATCH v6 00/49] QUICC Engine support on ARM, ARM64, PPC64
On Thu, Nov 28, 2019 at 8:59 AM Rasmus Villemoes wrote: > > There have been several attempts in the past few years to allow > building the QUICC engine drivers for platforms other than PPC32. This > is yet another attempt. > > v5 can be found here: > https://lore.kernel.org/lkml/20191118112324.22725-1-li...@rasmusvillemoes.dk/ > > Changes in v6: > > - add various R-b, A-b tags > > - add a patch (48/49) fixing a build issue on ARM with CONFIG_SMP=y > > I added that patch last in the series, apart from the "allow to build > on ARM" Kconfig change, to preserve the enumeration of the other > patches from v5. > > 1-5 are about replacing in_be32 etc. in the core QE code (drivers/soc/fsl/qe). > > 6-8 handle miscellaneous other ppcisms. > > 9-21 deal with qe_ic: Simplifying the driver significantly by removing > unused code, and removing the platform-specific initialization from > arch/powerpc/. > > 22-25 deal with raw access to devicetree properties in native endianness. > > 26-34 makes drivers/tty/serial/ucc_uart.c (CONFIG_SERIAL_QE) ready to build > on non-ppc. > > 35-46 deal with IS_ERR_VALUE() and some other things found while > digging around that part of the code. > > 47 adds a PPC32 dependency to UCC_GETH - it has some of the same > issues that have been fixed in the ucc_uart and ucc_hdlc cases. Nobody > has requested that I allow that driver to be built for arm{,64} and > reportedly, the hardware has only ever shipped on PPC SOCs. So instead > of growing this series even bigger, I kept that addition. It's trivial > to remove if somebody cares enough to fix the build errors/warnings > and actually has a platform to test the result on. > > 48 fixes a build issue on ARM reported by the kbuild bot. > > Finally patch 49 lifts the PPC32 restriction from QUICC_ENGINE. At the > request of Li Yang, it doesn't remove the PPC32 dependency but instead > changes it to PPC|| ARM || ARM64 (or COMPILE_TEST), i.e. listing > the platforms that may have a QE. > > The series has been built and booted on both an mpc8309-based platform > (ppc) as well as an ls1021a-based platform (arm). The core QE code is > exercised on both, while I could only test the ucc_uart on arm, since > the uarts are not wired up on our mpc8309 board. Qiang Zhao reports > that the ucc_hdlc driver does indeed work on a ls1043ardb (arm64) > board. Series applied for next on my soc tree. Thanks! Regards, Leo > > Rasmus Villemoes (49): > soc: fsl: qe: remove space-before-tab > soc: fsl: qe: drop volatile qualifier of struct qe_ic::regs > soc: fsl: qe: rename qe_(clr/set/clrset)bit* helpers > soc: fsl: qe: introduce qe_io{read,write}* wrappers > soc: fsl: qe: avoid ppc-specific io accessors > soc: fsl: qe: replace spin_event_timeout by readx_poll_timeout_atomic > soc: fsl: qe: qe.c: guard use of pvr_version_is() with CONFIG_PPC32 > soc: fsl: qe: drop unneeded #includes > soc: fsl: qe: drop assign-only high_active in qe_ic_init > soc: fsl: qe: remove pointless sysfs registration in qe_ic.c > soc: fsl: qe: use qe_ic_cascade_{low,high}_mpic also on 83xx > soc: fsl: qe: move calls of qe_ic_init out of arch/powerpc/ > powerpc/83xx: remove mpc83xx_ipic_and_qe_init_IRQ > powerpc/85xx: remove mostly pointless mpc85xx_qe_init() > soc: fsl: qe: move qe_ic_cascade_* functions to qe_ic.c > soc: fsl: qe: rename qe_ic_cascade_low_mpic -> qe_ic_cascade_low > soc: fsl: qe: remove unused qe_ic_set_* functions > soc: fsl: qe: don't use NO_IRQ in qe_ic.c > soc: fsl: qe: make qe_ic_get_{low,high}_irq static > soc: fsl: qe: simplify qe_ic_init() > soc: fsl: qe: merge qe_ic.h headers into qe_ic.c > soc: fsl: qe: qe.c: use of_property_read_* helpers > soc: fsl: qe: qe_io.c: don't open-code of_parse_phandle() > soc: fsl: qe: qe_io.c: access device tree property using be32_to_cpu > soc: fsl: qe: qe_io.c: use of_property_read_u32() in par_io_init() > soc: fsl: move cpm.h from powerpc/include/asm to include/soc/fsl > soc/fsl/qe/qe.h: update include path for cpm.h > serial: ucc_uart: explicitly include soc/fsl/cpm.h > serial: ucc_uart: replace ppc-specific IO accessors > serial: ucc_uart: factor out soft_uart initialization > serial: ucc_uart: stub out soft_uart_init for !CONFIG_PPC32 > serial: ucc_uart: use of_property_read_u32() in ucc_uart_probe() > serial: ucc_uart: limit brg-frequency workaround to PPC32 > serial: ucc_uart: access __be32 field using be32_to_cpu > soc: fsl: qe: change return type of cpm_muram_alloc() to s32 > soc: fsl: qe: make cpm_muram_free() return void > soc: fsl: qe: make cpm_muram_free() ignore a negative offset > soc: fsl: qe: drop broken lazy call of cpm_muram_init() > soc: fsl: qe: refactor cpm_muram_alloc_common to prevent BUG on error > path > soc: fsl: qe: avoid IS_ERR_VALUE in ucc_slow.c > soc: fsl: qe: drop use of IS_ERR_VALUE in qe_sdma_init() > soc: fsl: qe: drop pointless check in qe_sdma_init() > soc: fsl: qe: avoid IS_ERR_VALUE in ucc_fast.c > net/
Re: [PATCH v6 00/49] QUICC Engine support on ARM, ARM64, PPC64
From: Li Yang Date: Mon, 2 Dec 2019 16:56:39 -0600 > On Mon, Dec 2, 2019 at 2:14 AM Rasmus Villemoes > wrote: >> >> On 01/12/2019 17.10, Timur Tabi wrote: >> > On 11/28/19 8:55 AM, Rasmus Villemoes wrote: >> >> There have been several attempts in the past few years to allow >> >> building the QUICC engine drivers for platforms other than PPC32. This >> >> is yet another attempt. >> >> >> >> v5 can be found >> >> here:https://lore.kernel.org/lkml/20191118112324.22725-1-li...@rasmusvillemoes.dk/ >> >> >> > >> > If it helps: >> > >> > Entire series: >> > Acked-by: Timur Tabi >> >> Thanks. I'll leave it to Li Yang whether to apply that - they already >> all (except for the last-minute build fix) have your R-b. >> >> Li Yang, any chance you could pick up these patches so they have plenty >> of time in -next until 5.6? > > Sure. I will. I'm waiting for the Ack from David on the networking side. Acked-by: David S. Miller
Re: [PATCH v6 00/49] QUICC Engine support on ARM, ARM64, PPC64
On Mon, Dec 2, 2019 at 2:14 AM Rasmus Villemoes wrote: > > On 01/12/2019 17.10, Timur Tabi wrote: > > On 11/28/19 8:55 AM, Rasmus Villemoes wrote: > >> There have been several attempts in the past few years to allow > >> building the QUICC engine drivers for platforms other than PPC32. This > >> is yet another attempt. > >> > >> v5 can be found > >> here:https://lore.kernel.org/lkml/20191118112324.22725-1-li...@rasmusvillemoes.dk/ > >> > > > > If it helps: > > > > Entire series: > > Acked-by: Timur Tabi > > Thanks. I'll leave it to Li Yang whether to apply that - they already > all (except for the last-minute build fix) have your R-b. > > Li Yang, any chance you could pick up these patches so they have plenty > of time in -next until 5.6? Sure. I will. I'm waiting for the Ack from David on the networking side. Regards, Leo
Re: [PATCH v6 00/49] QUICC Engine support on ARM, ARM64, PPC64
On 01/12/2019 17.10, Timur Tabi wrote: > On 11/28/19 8:55 AM, Rasmus Villemoes wrote: >> There have been several attempts in the past few years to allow >> building the QUICC engine drivers for platforms other than PPC32. This >> is yet another attempt. >> >> v5 can be found >> here:https://lore.kernel.org/lkml/20191118112324.22725-1-li...@rasmusvillemoes.dk/ >> > > If it helps: > > Entire series: > Acked-by: Timur Tabi Thanks. I'll leave it to Li Yang whether to apply that - they already all (except for the last-minute build fix) have your R-b. Li Yang, any chance you could pick up these patches so they have plenty of time in -next until 5.6? Thanks, Rasmus
Re: [PATCH v6 00/49] QUICC Engine support on ARM, ARM64, PPC64
On 11/28/19 8:55 AM, Rasmus Villemoes wrote: There have been several attempts in the past few years to allow building the QUICC engine drivers for platforms other than PPC32. This is yet another attempt. v5 can be found here:https://lore.kernel.org/lkml/20191118112324.22725-1-li...@rasmusvillemoes.dk/ If it helps: Entire series: Acked-by: Timur Tabi I've worked on all code covered by this patchset except for the hdlc driver. I don't know if my ACKs are acceptable to everyone, but you have them regardless.
[PATCH v6 00/49] QUICC Engine support on ARM, ARM64, PPC64
There have been several attempts in the past few years to allow building the QUICC engine drivers for platforms other than PPC32. This is yet another attempt. v5 can be found here: https://lore.kernel.org/lkml/20191118112324.22725-1-li...@rasmusvillemoes.dk/ Changes in v6: - add various R-b, A-b tags - add a patch (48/49) fixing a build issue on ARM with CONFIG_SMP=y I added that patch last in the series, apart from the "allow to build on ARM" Kconfig change, to preserve the enumeration of the other patches from v5. 1-5 are about replacing in_be32 etc. in the core QE code (drivers/soc/fsl/qe). 6-8 handle miscellaneous other ppcisms. 9-21 deal with qe_ic: Simplifying the driver significantly by removing unused code, and removing the platform-specific initialization from arch/powerpc/. 22-25 deal with raw access to devicetree properties in native endianness. 26-34 makes drivers/tty/serial/ucc_uart.c (CONFIG_SERIAL_QE) ready to build on non-ppc. 35-46 deal with IS_ERR_VALUE() and some other things found while digging around that part of the code. 47 adds a PPC32 dependency to UCC_GETH - it has some of the same issues that have been fixed in the ucc_uart and ucc_hdlc cases. Nobody has requested that I allow that driver to be built for arm{,64} and reportedly, the hardware has only ever shipped on PPC SOCs. So instead of growing this series even bigger, I kept that addition. It's trivial to remove if somebody cares enough to fix the build errors/warnings and actually has a platform to test the result on. 48 fixes a build issue on ARM reported by the kbuild bot. Finally patch 49 lifts the PPC32 restriction from QUICC_ENGINE. At the request of Li Yang, it doesn't remove the PPC32 dependency but instead changes it to PPC|| ARM || ARM64 (or COMPILE_TEST), i.e. listing the platforms that may have a QE. The series has been built and booted on both an mpc8309-based platform (ppc) as well as an ls1021a-based platform (arm). The core QE code is exercised on both, while I could only test the ucc_uart on arm, since the uarts are not wired up on our mpc8309 board. Qiang Zhao reports that the ucc_hdlc driver does indeed work on a ls1043ardb (arm64) board. Rasmus Villemoes (49): soc: fsl: qe: remove space-before-tab soc: fsl: qe: drop volatile qualifier of struct qe_ic::regs soc: fsl: qe: rename qe_(clr/set/clrset)bit* helpers soc: fsl: qe: introduce qe_io{read,write}* wrappers soc: fsl: qe: avoid ppc-specific io accessors soc: fsl: qe: replace spin_event_timeout by readx_poll_timeout_atomic soc: fsl: qe: qe.c: guard use of pvr_version_is() with CONFIG_PPC32 soc: fsl: qe: drop unneeded #includes soc: fsl: qe: drop assign-only high_active in qe_ic_init soc: fsl: qe: remove pointless sysfs registration in qe_ic.c soc: fsl: qe: use qe_ic_cascade_{low,high}_mpic also on 83xx soc: fsl: qe: move calls of qe_ic_init out of arch/powerpc/ powerpc/83xx: remove mpc83xx_ipic_and_qe_init_IRQ powerpc/85xx: remove mostly pointless mpc85xx_qe_init() soc: fsl: qe: move qe_ic_cascade_* functions to qe_ic.c soc: fsl: qe: rename qe_ic_cascade_low_mpic -> qe_ic_cascade_low soc: fsl: qe: remove unused qe_ic_set_* functions soc: fsl: qe: don't use NO_IRQ in qe_ic.c soc: fsl: qe: make qe_ic_get_{low,high}_irq static soc: fsl: qe: simplify qe_ic_init() soc: fsl: qe: merge qe_ic.h headers into qe_ic.c soc: fsl: qe: qe.c: use of_property_read_* helpers soc: fsl: qe: qe_io.c: don't open-code of_parse_phandle() soc: fsl: qe: qe_io.c: access device tree property using be32_to_cpu soc: fsl: qe: qe_io.c: use of_property_read_u32() in par_io_init() soc: fsl: move cpm.h from powerpc/include/asm to include/soc/fsl soc/fsl/qe/qe.h: update include path for cpm.h serial: ucc_uart: explicitly include soc/fsl/cpm.h serial: ucc_uart: replace ppc-specific IO accessors serial: ucc_uart: factor out soft_uart initialization serial: ucc_uart: stub out soft_uart_init for !CONFIG_PPC32 serial: ucc_uart: use of_property_read_u32() in ucc_uart_probe() serial: ucc_uart: limit brg-frequency workaround to PPC32 serial: ucc_uart: access __be32 field using be32_to_cpu soc: fsl: qe: change return type of cpm_muram_alloc() to s32 soc: fsl: qe: make cpm_muram_free() return void soc: fsl: qe: make cpm_muram_free() ignore a negative offset soc: fsl: qe: drop broken lazy call of cpm_muram_init() soc: fsl: qe: refactor cpm_muram_alloc_common to prevent BUG on error path soc: fsl: qe: avoid IS_ERR_VALUE in ucc_slow.c soc: fsl: qe: drop use of IS_ERR_VALUE in qe_sdma_init() soc: fsl: qe: drop pointless check in qe_sdma_init() soc: fsl: qe: avoid IS_ERR_VALUE in ucc_fast.c net/wan/fsl_ucc_hdlc: avoid use of IS_ERR_VALUE() net/wan/fsl_ucc_hdlc: fix reading of __be16 registers net/wan/fsl_ucc_hdlc: reject muram offsets above 64K net: ethernet: freescale: make UCC_GETH explicitly depend on PPC32 soc: fsl: qe: remove unused #include of asm/irq.h from ucc.c soc: fsl: qe: remo