The function now is safe to use while expecting a 64bit value. Use it
where relevant.
Signed-off-by: Nicolas Saenz Julienne <[email protected]>
---
drivers/acpi/arm64/iort.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_clock.c | 3 ++-
drivers/of/device.c | 3 ++-
drivers/pci/controller/cadence/pcie-cadence-ep.c | 3 ++-
drivers/pci/controller/cadence/pcie-cadence.c | 3 ++-
drivers/pci/controller/pcie-brcmstb.c | 3 ++-
drivers/pci/controller/pcie-rockchip-ep.c | 5 +++--
kernel/dma/direct.c | 2 +-
8 files changed, 15 insertions(+), 9 deletions(-)
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 33f71983e001..9950c9757092 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1090,7 +1090,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
* firmware.
*/
end = dmaaddr + size - 1;
- mask = DMA_BIT_MASK(ilog2(end) + 1);
+ mask = roundup_pow_of_two(end) - 1;
dev->bus_dma_limit = end;
dev->coherent_dma_mask = mask;
*dev->dma_mask = mask;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 024788549c25..23dcb18224d4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -33,6 +33,7 @@
#include <linux/mlx4/device.h>
#include <linux/clocksource.h>
+#include <linux/log2.h>
#include "mlx4_en.h"
@@ -252,7 +253,7 @@ static u32 freq_to_shift(u16 freq)
{
u32 freq_khz = freq * 1000;
u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
- u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1);
+ u64 max_val_cycles_rounded = roundup_pow_of_two(max_val_cycles);
/* calculate max possible multiplier in order to fit in 64bit */
u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index e9127db7b067..7259922d2078 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -11,6 +11,7 @@
#include <linux/mod_devicetable.h>
#include <linux/slab.h>
#include <linux/platform_device.h>
+#include <linux/log2.h>
#include <asm/errno.h>
#include "of_private.h"
@@ -149,7 +150,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
* set by the driver.
*/
end = dma_addr + size - 1;
- mask = DMA_BIT_MASK(ilog2(end) + 1);
+ mask = roundup_pow_of_two(end) - 1;
dev->coherent_dma_mask &= mask;
*dev->dma_mask &= mask;
/* ...but only set bus limit if we found valid dma-ranges earlier */
diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 1c173dad67d1..72eda0b2f939 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -10,6 +10,7 @@
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/sizes.h>
+#include <linux/log2.h>
#include "pcie-cadence.h"
@@ -65,7 +66,7 @@ static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn,
* roundup_pow_of_two() returns an unsigned long, which is not suited
* for 64bit values.
*/
- sz = 1ULL << fls64(sz - 1);
+ sz = roundup_pow_of_two(sz);
aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */
if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
diff --git a/drivers/pci/controller/cadence/pcie-cadence.c b/drivers/pci/controller/cadence/pcie-cadence.c
index cd795f6fc1e2..b1689f725b41 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.c
+++ b/drivers/pci/controller/cadence/pcie-cadence.c
@@ -4,6 +4,7 @@
// Author: Cyrille Pitchen <[email protected]>
#include <linux/kernel.h>
+#include <linux/log2.h>
#include "pcie-cadence.h"
@@ -15,7 +16,7 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 fn,
* roundup_pow_of_two() returns an unsigned long, which is not suited
* for 64bit values.
*/
- u64 sz = 1ULL << fls64(size - 1);
+ u64 sz = roundup_pow_of_two(size);
int nbits = ilog2(sz);
u32 addr0, addr1, desc0, desc1;
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index 7ba06a0e1a71..e705d9d73030 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -627,7 +627,8 @@ static inline int brcm_pcie_get_rc_bar2_size_and_offset(struct brcm_pcie *pcie,
return -ENODEV;
*rc_bar2_offset = -entry->offset;
- *rc_bar2_size = 1ULL << fls64(entry->res->end - entry->res->start);
+ *rc_bar2_size = roundup_pow_of_two(entry->res->end -
+ entry->res->start + 1);
/*
* We validate the inbound memory view even though we should trust
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index d743b0a48988..83665f5f804a 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -16,6 +16,7 @@
#include <linux/platform_device.h>
#include <linux/pci-epf.h>
#include <linux/sizes.h>
+#include <linux/log2.h>
#include "pcie-rockchip.h"
@@ -70,7 +71,7 @@ static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn,
u32 r, u32 type, u64 cpu_addr,
u64 pci_addr, size_t size)
{
- u64 sz = 1ULL << fls64(size - 1);
+ u64 sz = roundup_pow_of_two(size);
int num_pass_bits = ilog2(sz);
u32 addr0, addr1, desc0, desc1;
bool is_nor_msg = (type == AXI_WRAPPER_NOR_MSG);
@@ -176,7 +177,7 @@ static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn,
* roundup_pow_of_two() returns an unsigned long, which is not suited
* for 64bit values.
*/
- sz = 1ULL << fls64(sz - 1);
+ sz = roundup_pow_of_two(sz);
aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */
if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 6af7ae83c4ad..056886c4efec 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -53,7 +53,7 @@ u64 dma_direct_get_required_mask(struct device *dev)
{
u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
- return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
+ return rounddown_pow_of_two(max_dma) * 2 - 1;
}
static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
--
2.24.0
On Tue, Dec 3, 2019 at 5:48 AM Nicolas Saenz Julienne
<[email protected]> wrote:
>
> The function now is safe to use while expecting a 64bit value. Use it
> where relevant.
What was wrong with the existing code? This is missing some context.
> Signed-off-by: Nicolas Saenz Julienne <[email protected]>
> ---
> drivers/acpi/arm64/iort.c | 2 +-
> drivers/net/ethernet/mellanox/mlx4/en_clock.c | 3 ++-
> drivers/of/device.c | 3 ++-
In any case,
Acked-by: Rob Herring <[email protected]>
> drivers/pci/controller/cadence/pcie-cadence-ep.c | 3 ++-
> drivers/pci/controller/cadence/pcie-cadence.c | 3 ++-
> drivers/pci/controller/pcie-brcmstb.c | 3 ++-
> drivers/pci/controller/pcie-rockchip-ep.c | 5 +++--
> kernel/dma/direct.c | 2 +-
> 8 files changed, 15 insertions(+), 9 deletions(-)
Hi Rob,
On Tue, 2019-12-03 at 09:53 -0600, Rob Herring wrote:
> On Tue, Dec 3, 2019 at 5:48 AM Nicolas Saenz Julienne
> <[email protected]> wrote:
> > The function now is safe to use while expecting a 64bit value. Use it
> > where relevant.
>
> What was wrong with the existing code? This is missing some context.
You're right, I'll update it.
For most of files changed the benefit here is factoring out a common pattern
using the standard function roundup/down_pow_two() which now provides correct
64bit results.
As for of/device.c and arm64/iort.c it's more of a readability enhancement. I
consider it's easier to understand than the current calculation as it abstracts
the math.
> > Signed-off-by: Nicolas Saenz Julienne <[email protected]>
> > ---
> > drivers/acpi/arm64/iort.c | 2 +-
> > drivers/net/ethernet/mellanox/mlx4/en_clock.c | 3 ++-
> > drivers/of/device.c | 3 ++-
>
> In any case,
>
> Acked-by: Rob Herring <[email protected]>
>
Thanks!
Regards,
Nicolas
The subject contains a couple typos: it's missing "of" and it's
missing the "n" on "down".
On Tue, Dec 03, 2019 at 12:47:41PM +0100, Nicolas Saenz Julienne wrote:
> The function now is safe to use while expecting a 64bit value. Use it
> where relevant.
Please include the function names ("roundup_pow_of_two()",
"rounddown_pow_of_two()") in the changelog so it is self-contained and
doesn't depend on the subject.
> Signed-off-by: Nicolas Saenz Julienne <[email protected]>
With the nits above and below addressed,
Acked-by: Bjorn Helgaas <[email protected]> # drivers/pci
> ---
> drivers/acpi/arm64/iort.c | 2 +-
> drivers/net/ethernet/mellanox/mlx4/en_clock.c | 3 ++-
> drivers/of/device.c | 3 ++-
> drivers/pci/controller/cadence/pcie-cadence-ep.c | 3 ++-
> drivers/pci/controller/cadence/pcie-cadence.c | 3 ++-
> drivers/pci/controller/pcie-brcmstb.c | 3 ++-
> drivers/pci/controller/pcie-rockchip-ep.c | 5 +++--
> kernel/dma/direct.c | 2 +-
> 8 files changed, 15 insertions(+), 9 deletions(-)
> --- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
> +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
> @@ -10,6 +10,7 @@
> #include <linux/platform_device.h>
> #include <linux/pm_runtime.h>
> #include <linux/sizes.h>
> +#include <linux/log2.h>
>
> #include "pcie-cadence.h"
>
> @@ -65,7 +66,7 @@ static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn,
> * roundup_pow_of_two() returns an unsigned long, which is not suited
> * for 64bit values.
> */
Please remove the comment above since it no longer applies.
> - sz = 1ULL << fls64(sz - 1);
> + sz = roundup_pow_of_two(sz);
> aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */
>
> if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
> diff --git a/drivers/pci/controller/cadence/pcie-cadence.c b/drivers/pci/controller/cadence/pcie-cadence.c
> index cd795f6fc1e2..b1689f725b41 100644
> --- a/drivers/pci/controller/cadence/pcie-cadence.c
> +++ b/drivers/pci/controller/cadence/pcie-cadence.c
> @@ -4,6 +4,7 @@
> // Author: Cyrille Pitchen <[email protected]>
>
> #include <linux/kernel.h>
> +#include <linux/log2.h>
>
> #include "pcie-cadence.h"
>
> @@ -15,7 +16,7 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 fn,
> * roundup_pow_of_two() returns an unsigned long, which is not suited
> * for 64bit values.
> */
Same here.
> - u64 sz = 1ULL << fls64(size - 1);
> + u64 sz = roundup_pow_of_two(size);
> int nbits = ilog2(sz);
> u32 addr0, addr1, desc0, desc1;
>
> --- a/drivers/pci/controller/pcie-rockchip-ep.c
> +++ b/drivers/pci/controller/pcie-rockchip-ep.c
> @@ -16,6 +16,7 @@
> #include <linux/platform_device.h>
> #include <linux/pci-epf.h>
> #include <linux/sizes.h>
> +#include <linux/log2.h>
>
> #include "pcie-rockchip.h"
>
> @@ -70,7 +71,7 @@ static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn,
> u32 r, u32 type, u64 cpu_addr,
> u64 pci_addr, size_t size)
> {
> - u64 sz = 1ULL << fls64(size - 1);
> + u64 sz = roundup_pow_of_two(size);
> int num_pass_bits = ilog2(sz);
> u32 addr0, addr1, desc0, desc1;
> bool is_nor_msg = (type == AXI_WRAPPER_NOR_MSG);
> @@ -176,7 +177,7 @@ static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn,
> * roundup_pow_of_two() returns an unsigned long, which is not suited
> * for 64bit values.
> */
And here.
> - sz = 1ULL << fls64(sz - 1);
> + sz = roundup_pow_of_two(sz);
> aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */
>
> if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> index 6af7ae83c4ad..056886c4efec 100644
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -53,7 +53,7 @@ u64 dma_direct_get_required_mask(struct device *dev)
> {
> u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
>
> - return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
> + return rounddown_pow_of_two(max_dma) * 2 - 1;
Personally I would probably make this one a separate patch since it's
qualitatively different than the others and it would avoid the slight
awkwardness of the non-greppable "roundup/down_pow_of_two()"
construction in the commit subject.
But it's fine either way.
> }
>
> static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
> --
> 2.24.0
>
On Thu, 2019-12-05 at 14:38 -0600, Bjorn Helgaas wrote:
> The subject contains a couple typos: it's missing "of" and it's
> missing the "n" on "down".
Noted >
> On Tue, Dec 03, 2019 at 12:47:41PM +0100, Nicolas Saenz Julienne wrote:
> > The function now is safe to use while expecting a 64bit value. Use it
> > where relevant.
>
> Please include the function names ("roundup_pow_of_two()",
> "rounddown_pow_of_two()") in the changelog so it is self-contained and
> doesn't depend on the subject.
Noted
> > Signed-off-by: Nicolas Saenz Julienne <[email protected]>
>
> With the nits above and below addressed,
>
> Acked-by: Bjorn Helgaas <[email protected]> # drivers/pci
Thanks!
> > ---
> > drivers/acpi/arm64/iort.c | 2 +-
> > drivers/net/ethernet/mellanox/mlx4/en_clock.c | 3 ++-
> > drivers/of/device.c | 3 ++-
> > drivers/pci/controller/cadence/pcie-cadence-ep.c | 3 ++-
> > drivers/pci/controller/cadence/pcie-cadence.c | 3 ++-
> > drivers/pci/controller/pcie-brcmstb.c | 3 ++-
> > drivers/pci/controller/pcie-rockchip-ep.c | 5 +++--
> > kernel/dma/direct.c | 2 +-
> > 8 files changed, 15 insertions(+), 9 deletions(-)
> > --- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
> > +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
> > @@ -10,6 +10,7 @@
> > #include <linux/platform_device.h>
> > #include <linux/pm_runtime.h>
> > #include <linux/sizes.h>
> > +#include <linux/log2.h>
> >
> > #include "pcie-cadence.h"
> >
> > @@ -65,7 +66,7 @@ static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8
> > fn,
> > * roundup_pow_of_two() returns an unsigned long, which is not suited
> > * for 64bit values.
> > */
>
> Please remove the comment above since it no longer applies.
Noted
[...]
> > diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
> > index 6af7ae83c4ad..056886c4efec 100644
> > --- a/kernel/dma/direct.c
> > +++ b/kernel/dma/direct.c
> > @@ -53,7 +53,7 @@ u64 dma_direct_get_required_mask(struct device *dev)
> > {
> > u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
> >
> > - return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
> > + return rounddown_pow_of_two(max_dma) * 2 - 1;
>
> Personally I would probably make this one a separate patch since it's
> qualitatively different than the others and it would avoid the slight
> awkwardness of the non-greppable "roundup/down_pow_of_two()"
> construction in the commit subject.
>
> But it's fine either way.
I'll split it into two parts, as RobH made a similar complaint.
Regards,
Nicolas