| Message ID | 20240511130349.23409-5-ansuelsmth@gmail.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | mips: bmips: improve handling of RAC and CBR addr | expand |
On Sat, May 11, 2024 at 03:03:48PM +0200, Christian Marangi wrote: > From: Daniel González Cabanelas <dgcbueu@gmail.com> > > The data RAC is left disabled by the bootloader in some SoCs, at least in > the core it boots from. > Enabling this feature increases the performance up to +30% depending on the > task. > > Signed-off-by: Daniel González Cabanelas <dgcbueu@gmail.com> > Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com> > [ rework code and reduce code duplication ] > Signed-off-by: Christian Marangi <ansuelsmth@gmail.com> > Acked-by: Florian Fainelli <florian.fainelli@broadcom.com> > --- > arch/mips/kernel/smp-bmips.c | 17 +++++++++++++++++ > 1 file changed, 17 insertions(+) > > diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c > index 20e2fb10022d..52324738cbb3 100644 > --- a/arch/mips/kernel/smp-bmips.c > +++ b/arch/mips/kernel/smp-bmips.c > @@ -626,6 +626,23 @@ void bmips_cpu_setup(void) > __raw_readl(cbr + BMIPS_RAC_ADDRESS_RANGE); > break; > > + case CPU_BMIPS4350: > + u32 rac_addr = BMIPS_RAC_CONFIG_1; my gcc 10.2.1 doesn't like the declaration here: /local/tbogendoerfer/korg/linux/arch/mips/kernel/smp-bmips.c:630:3: error: a label can only be part of a statement and a declaration is not a statement 630 | u32 rac_addr = BMIPS_RAC_CONFIG_1; Thomas.
On Tue, Jun 11, 2024 at 10:47:16AM +0200, Thomas Bogendoerfer wrote: > On Sat, May 11, 2024 at 03:03:48PM +0200, Christian Marangi wrote: > > From: Daniel González Cabanelas <dgcbueu@gmail.com> > > > > The data RAC is left disabled by the bootloader in some SoCs, at least in > > the core it boots from. > > Enabling this feature increases the performance up to +30% depending on the > > task. > > > > Signed-off-by: Daniel González Cabanelas <dgcbueu@gmail.com> > > Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com> > > [ rework code and reduce code duplication ] > > Signed-off-by: Christian Marangi <ansuelsmth@gmail.com> > > Acked-by: Florian Fainelli <florian.fainelli@broadcom.com> > > --- > > arch/mips/kernel/smp-bmips.c | 17 +++++++++++++++++ > > 1 file changed, 17 insertions(+) > > > > diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c > > index 20e2fb10022d..52324738cbb3 100644 > > --- a/arch/mips/kernel/smp-bmips.c > > +++ b/arch/mips/kernel/smp-bmips.c > > @@ -626,6 +626,23 @@ void bmips_cpu_setup(void) > > __raw_readl(cbr + BMIPS_RAC_ADDRESS_RANGE); > > break; > > > > + case CPU_BMIPS4350: > > + u32 rac_addr = BMIPS_RAC_CONFIG_1; > > my gcc 10.2.1 doesn't like the declaration here: > > /local/tbogendoerfer/korg/linux/arch/mips/kernel/smp-bmips.c:630:3: error: a label can only be part of a statement and a declaration is not a statement > 630 | u32 rac_addr = BMIPS_RAC_CONFIG_1; > Thanks I moved the declaration up before the switch.
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 20e2fb10022d..52324738cbb3 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -626,6 +626,23 @@ void bmips_cpu_setup(void) __raw_readl(cbr + BMIPS_RAC_ADDRESS_RANGE); break; + case CPU_BMIPS4350: + u32 rac_addr = BMIPS_RAC_CONFIG_1; + + if (!(read_c0_brcm_cmt_local() & (1 << 31))) + rac_addr = BMIPS_RAC_CONFIG; + + /* Enable data RAC */ + cfg = __raw_readl(cbr + rac_addr); + __raw_writel(cfg | 0xf, cbr + rac_addr); + __raw_readl(cbr + rac_addr); + + /* Flush stale data out of the readahead cache */ + cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG); + __raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG); + __raw_readl(cbr + BMIPS_RAC_CONFIG); + break; + case CPU_BMIPS4380: /* CBG workaround for early BMIPS4380 CPUs */ switch (read_c0_prid()) {