Re: [PATCH v3 15/17] mm: pgtable: remove tlb_remove_page_ptdesc()
On Mon, Dec 23, 2024 at 05:41:01PM +0800, Qi Zheng wrote:
> Here we are explicitly dealing with struct page, and the following logic
> semms strange:
>
> tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));
>
> tlb_remove_page_ptdesc
> --> tlb_remove_page(tlb, ptdesc_page(pt));
>
> So remove tlb_remove_page_ptdesc() and make callers call tlb_remove_page()
> directly.
Please don't. The ptdesc wrappers are there as a part of reducing the size
of struct page project [1].
For now struct ptdesc overlaps struct page, but the goal is to have them
separate and always operate on struct ptdesc when working with page tables.
[1] https://kernelnewbies.org/MatthewWilcox/Memdescs
> Signed-off-by: Qi Zheng
> Originally-by: Peter Zijlstra (Intel)
> ---
> arch/csky/include/asm/pgalloc.h | 2 +-
> arch/hexagon/include/asm/pgalloc.h | 2 +-
> arch/loongarch/include/asm/pgalloc.h | 2 +-
> arch/m68k/include/asm/sun3_pgalloc.h | 2 +-
> arch/mips/include/asm/pgalloc.h | 2 +-
> arch/nios2/include/asm/pgalloc.h | 2 +-
> arch/openrisc/include/asm/pgalloc.h | 2 +-
> arch/riscv/include/asm/pgalloc.h | 2 +-
> arch/sh/include/asm/pgalloc.h| 2 +-
> arch/um/include/asm/pgalloc.h| 8
> include/asm-generic/tlb.h| 6 --
> 11 files changed, 13 insertions(+), 19 deletions(-)
>
> diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
> index f1ce5b7b28f22..936a43a49e704 100644
> --- a/arch/csky/include/asm/pgalloc.h
> +++ b/arch/csky/include/asm/pgalloc.h
> @@ -64,7 +64,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
> #define __pte_free_tlb(tlb, pte, address)\
> do { \
> pagetable_dtor(page_ptdesc(pte)); \
> - tlb_remove_page_ptdesc(tlb, page_ptdesc(pte)); \
> + tlb_remove_page(tlb, (pte));\
> } while (0)
>
> extern void pagetable_init(void);
> diff --git a/arch/hexagon/include/asm/pgalloc.h
> b/arch/hexagon/include/asm/pgalloc.h
> index 40e42a0e71673..8b1550498f1bf 100644
> --- a/arch/hexagon/include/asm/pgalloc.h
> +++ b/arch/hexagon/include/asm/pgalloc.h
> @@ -90,7 +90,7 @@ static inline void pmd_populate_kernel(struct mm_struct
> *mm, pmd_t *pmd,
> #define __pte_free_tlb(tlb, pte, addr) \
> do { \
> pagetable_dtor((page_ptdesc(pte))); \
> - tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \
> + tlb_remove_page((tlb), (pte)); \
> } while (0)
>
> #endif
> diff --git a/arch/loongarch/include/asm/pgalloc.h
> b/arch/loongarch/include/asm/pgalloc.h
> index 7211dff8c969e..5a4f22aeb6189 100644
> --- a/arch/loongarch/include/asm/pgalloc.h
> +++ b/arch/loongarch/include/asm/pgalloc.h
> @@ -58,7 +58,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct
> *mm)
> #define __pte_free_tlb(tlb, pte, address)\
> do { \
> pagetable_dtor(page_ptdesc(pte)); \
> - tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));\
> + tlb_remove_page((tlb), (pte)); \
> } while (0)
>
> #ifndef __PAGETABLE_PMD_FOLDED
> diff --git a/arch/m68k/include/asm/sun3_pgalloc.h
> b/arch/m68k/include/asm/sun3_pgalloc.h
> index 2b626cb3ad0ae..63d9f95f5e3dd 100644
> --- a/arch/m68k/include/asm/sun3_pgalloc.h
> +++ b/arch/m68k/include/asm/sun3_pgalloc.h
> @@ -20,7 +20,7 @@ extern const char bad_pmd_string[];
> #define __pte_free_tlb(tlb, pte, addr) \
> do { \
> pagetable_dtor(page_ptdesc(pte)); \
> - tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));\
> + tlb_remove_page((tlb), (pte)); \
> } while (0)
>
> static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
> pte_t *pte)
> diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
> index 36d9805033c4b..bbee21345154b 100644
> --- a/arch/mips/include/asm/pgalloc.h
> +++ b/arch/mips/include/asm/pgalloc.h
> @@ -57,7 +57,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t
> *pgd)
> #define __pte_free_tlb(tlb, pte, address)\
> do { \
> pagetable_dtor(page_ptdesc(pte)); \
> - tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));\
> + tlb_remove_page((tlb), (pte)); \
> } while (0)
>
> #ifndef __PAGETABLE_PMD_FOLDED
> diff --git a/arch/nios2/include/asm/pgalloc.h
> b/arch/nios2/include/asm/pgalloc.h
> index 12a536b7bfbd4..641cec8fb2a22 100644
> --- a/arch/nios2/include/asm/pgalloc.h
> +++ b/arch/nios2/include/asm/pgalloc.h
> @@ -31,7 +31,7 @@ extern pgd_t *pg
KVM: PPC: Book3E: KVM HV host module doesn't work anymore
Hi All, I found out which area is responsible for the KVM HV issue while reducing the revert patch. If I replace the following line in the file 'a/arch/powerpc/kvm/e500_mmu_host.c' then KVM HV works again. - pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, NULL, &page); + pfn = gfn_to_pfn_memslot(slot, gfn); On 28/12/24 15:55, Paolo Bonzini wrote: > The fix is already found, I will send it out shortly but everybody is on > vacation now Thanks a lot! Could you please post the patch on this list? I would like to patch the RC5 of kernel 6.13 next week. Thanks, Christian -- Sent with BrassMonkey 33.4.0 (https://github.com/wicknix/brass-monkey/releases/tag/33.4.0)
Re: [PATCH v11 2/5] modpost: Produce extended MODVERSIONS information
On Tue, Dec 24, 2024 at 5:13 AM Matthew Maurer wrote:
>
> Generate both the existing modversions format and the new extended one
> when running modpost. Presence of this metadata in the final .ko is
> guarded by CONFIG_EXTENDED_MODVERSIONS.
>
> We no longer generate an error on long symbols in modpost if
> CONFIG_EXTENDED_MODVERSIONS is set, as they can now be appropriately
> encoded in the extended section. These symbols will be skipped in the
> previous encoding. An error will still be generated if
> CONFIG_EXTENDED_MODVERSIONS is not set.
>
> Reviewed-by: Sami Tolvanen
> Signed-off-by: Matthew Maurer
> ---
> kernel/module/Kconfig| 10
> scripts/Makefile.modpost | 1 +
> scripts/mod/modpost.c| 65
> +---
> 3 files changed, 72 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
> index
> d443fc504ffca0d1001f880ec496ab1f21fe979e..9568b629a03ce8289d3f3597eefc66fc96445720
> 100644
> --- a/kernel/module/Kconfig
> +++ b/kernel/module/Kconfig
> @@ -207,6 +207,16 @@ config ASM_MODVERSIONS
> assembly. This can be enabled only when the target architecture
> supports it.
>
> +config EXTENDED_MODVERSIONS
> + bool "Extended Module Versioning Support"
> + depends on MODVERSIONS
> + help
> + This enables extended MODVERSIONs support, allowing long symbol
> + names to be versioned.
> +
> + The most likely reason you would enable this is to enable Rust
> + support. If unsure, say N.
> +
> config MODULE_SRCVERSION_ALL
> bool "Source checksum for all modules"
> help
> diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
> index
> ab0e94ea62496e11dbaa3ffc289ce546862795ca..40426fc6350985780c0092beb49c6cc29b9eff62
> 100644
> --- a/scripts/Makefile.modpost
> +++ b/scripts/Makefile.modpost
> @@ -43,6 +43,7 @@ MODPOST = $(objtree)/scripts/mod/modpost
> modpost-args =
> \
> $(if $(CONFIG_MODULES),-M)
> \
> $(if $(CONFIG_MODVERSIONS),-m)
> \
> + $(if $(CONFIG_EXTENDED_MODVERSIONS),-x)
> \
> $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)
> \
> $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E)
> \
> $(if $(KBUILD_MODPOST_WARN),-w)
> \
> diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
> index
> fb787a5715f5e8b37713162979ca45355770dc73..c58f08681fc1e37929333ba3a3e0989c4db5a79d
> 100644
> --- a/scripts/mod/modpost.c
> +++ b/scripts/mod/modpost.c
> @@ -33,6 +33,8 @@ static bool module_enabled;
> static bool modversions;
> /* Is CONFIG_MODULE_SRCVERSION_ALL set? */
> static bool all_versions;
> +/* Is CONFIG_EXTENDED_MODVERSIONS set? */
> +static bool extended_modversions;
> /* If we are modposting external module set to 1 */
> static bool external_module;
> /* Only warn about unresolved symbols */
> @@ -1804,6 +1806,52 @@ static void add_exported_symbols(struct buffer *buf,
> struct module *mod)
> }
> }
>
> +/**
> + * Record CRCs for unresolved symbols, supporting long names
> + */
> +static void add_extended_versions(struct buffer *b, struct module *mod)
> +{
> + struct symbol *s;
> +
> + if (!extended_modversions)
> + return;
> +
> + buf_printf(b, "\n");
> + buf_printf(b, "static const s32 version_ext_crcs[]\n");
In general, 's32' (i.e. signed) and the '%x' printf-format (i.e. unsigned)
are an odd combination. I know why you are mixing up these.
Previously, we had a reason to use 's32' because the 'crc' field may
contain a negative address offset.
After commit 7b4537199a4a, there is no more reason
for keeping this weirdness.
I will apply the following first.
https://lore.kernel.org/linux-kbuild/20241228154603.2234284-2-masahi...@kernel.org/T/#u
Then, you can change 's32' to 'u32' in this series.
> + buf_printf(b, "__used __section(\"__version_ext_crcs\") = {\n");
> + list_for_each_entry(s, &mod->unresolved_symbols, list) {
> + if (!s->module)
> + continue;
> + if (!s->crc_valid) {
> + /*
> +* We already warned on this when producing the legacy
> +* modversions table.
> +*/
> + continue;
Personally, I tend to avoid a noise change because you will change this comment
to warn() in the next commit.
It is up to you.
> + }
> + buf_printf(b, "\t%#8x,\n", s->crc);
This is also a copy-paste of the existing code.
I like to have zero-padding for better alignment.
Please follow
[PATCH 05/14] cpumask: deprecate cpumask_next_wrap()
The next patche aligns implementation of cpumask_next_wrap() with the
generic version in find.h which changes function signature.
To make the transition smooth, this patch deprecates current
implementation by adding an _old suffix. The following patches switch
current users to the new implementation one by one.
No functional changes were intended.
Signed-off-by: Yury Norov
---
arch/s390/kernel/processor.c| 2 +-
drivers/nvme/host/tcp.c | 2 +-
drivers/pci/controller/pci-hyperv.c | 2 +-
drivers/scsi/lpfc/lpfc_init.c | 2 +-
include/linux/cpumask.h | 4 ++--
kernel/padata.c | 2 +-
lib/cpumask.c | 6 +++---
7 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 5ce9a795a0fe..42ca61909030 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -72,7 +72,7 @@ void notrace stop_machine_yield(const struct cpumask *cpumask)
this_cpu = smp_processor_id();
if (__this_cpu_inc_return(cpu_relax_retry) >= spin_retry) {
__this_cpu_write(cpu_relax_retry, 0);
- cpu = cpumask_next_wrap(this_cpu, cpumask, this_cpu, false);
+ cpu = cpumask_next_wrap_old(this_cpu, cpumask, this_cpu, false);
if (cpu >= nr_cpu_ids)
return;
if (arch_vcpu_is_preempted(cpu))
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 28c76a3e1bd2..054904376c3c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1578,7 +1578,7 @@ static void nvme_tcp_set_queue_io_cpu(struct
nvme_tcp_queue *queue)
if (wq_unbound)
queue->io_cpu = WORK_CPU_UNBOUND;
else
- queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1,
false);
+ queue->io_cpu = cpumask_next_wrap_old(n - 1, cpu_online_mask,
-1, false);
}
static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
diff --git a/drivers/pci/controller/pci-hyperv.c
b/drivers/pci/controller/pci-hyperv.c
index cdd5be16021d..86d1c2be8eb5 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1757,7 +1757,7 @@ static int hv_compose_multi_msi_req_get_cpu(void)
spin_lock_irqsave(&multi_msi_cpu_lock, flags);
- cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask, nr_cpu_ids,
+ cpu_next = cpumask_next_wrap_old(cpu_next, cpu_online_mask, nr_cpu_ids,
false);
cpu = cpu_next;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 7f57397d91a9..31622fb0614a 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -12876,7 +12876,7 @@ lpfc_irq_rebalance(struct lpfc_hba *phba, unsigned int
cpu, bool offline)
if (offline) {
/* Find next online CPU on original mask */
- cpu_next = cpumask_next_wrap(cpu, orig_mask, cpu, true);
+ cpu_next = cpumask_next_wrap_old(cpu, orig_mask, cpu, true);
cpu_select = lpfc_next_online_cpu(orig_mask, cpu_next);
/* Found a valid CPU */
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 30042351f15f..b267a4f6a917 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -296,7 +296,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask
*src1p,
#if NR_CPUS == 1
static __always_inline
-unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start,
bool wrap)
+unsigned int cpumask_next_wrap_old(int n, const struct cpumask *mask, int
start, bool wrap)
{
cpumask_check(start);
if (n != -1)
@@ -312,7 +312,7 @@ unsigned int cpumask_next_wrap(int n, const struct cpumask
*mask, int start, boo
return cpumask_first(mask);
}
#else
-unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int
start, bool wrap);
+unsigned int __pure cpumask_next_wrap_old(int n, const struct cpumask *mask,
int start, bool wrap);
#endif
/**
diff --git a/kernel/padata.c b/kernel/padata.c
index d51bbc76b227..454ff2fca40b 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -274,7 +274,7 @@ static struct padata_priv *padata_find_next(struct
parallel_data *pd,
if (remove_object) {
list_del_init(&padata->list);
++pd->processed;
- pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false);
+ pd->cpu = cpumask_next_wrap_old(cpu, pd->cpumask.pcpu, -1,
false);
}
spin_unlock(&reorder->lock);
diff --git a/lib/cpumask.c b/lib/cpumask.c
index e77ee9d46f71..c9a9b451772a 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -8,7 +8,7 @@
#include
/**
- * cpumask_next_wrap - helper to implement for_each_cpu_wrap
+ * cpumask_next_wrap_old - helper to implement for_each_cpu_wrap
* @n: the cpu pri
[PATCH 06/14] cpumask: re-introduce cpumask_next{,_and}_wrap()
cpumask_next_wrap_old() has two additional parameters, comparing to it's
analogue in linux/find.h find_next_bit_wrap(). The reason for that is
historical.
Before 4fe49b3b97c262 ("lib/bitmap: introduce for_each_set_bit_wrap()
macro"), cpumask_next_wrap() was used to implement for_each_cpu_wrap()
iterator. Now that the iterator is an alias to generic
for_each_set_bit_wrap(), the additional parameters aren't used and may
confuse readers.
All existing users call cpumask_next_wrap() in a way that makes it
possible to turn it to straight and simple alias to find_next_bit_wrap().
In a couple places kernel users opencode missing cpumask_next_and_wrap().
Add it as well.
Signed-off-by: Yury Norov
---
include/linux/cpumask.h | 37 +
1 file changed, 37 insertions(+)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index b267a4f6a917..18c9908d50c4 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -284,6 +284,43 @@ unsigned int cpumask_next_and(int n, const struct cpumask
*src1p,
small_cpumask_bits, n + 1);
}
+/**
+ * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from
+ *@n and wrapping around, if needed
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Return: >= nr_cpu_ids if no further cpus set in both.
+ */
+static __always_inline
+unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p,
+ const struct cpumask *src2p)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpumask_check(n);
+ return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p),
+ small_cpumask_bits, n + 1);
+}
+
+/*
+ * cpumask_next_wrap - get the next cpu in *src, starting from
+ *@n and wrapping around, if needed
+ * @n: the cpu prior to the place to search
+ * @src: cpumask pointer
+ *
+ * Return: >= nr_cpu_ids if no further cpus set in both.
+ */
+static __always_inline
+unsigned int cpumask_next_wrap(int n, const struct cpumask *src)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpumask_check(n);
+ return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1);
+}
+
/**
* for_each_cpu - iterate over every cpu in a mask
* @cpu: the (optionally unsigned) integer iterator
--
2.43.0
[PATCH 04/14] powerpc/xmon: simplify xmon_batch_next_cpu()
The function opencodes for_each_cpu_wrap() macro. As a loop termination
condition it uses cpumask_empty(), which is O(N), and it makes the whole
algorithm O(N^2). Switching to for_each_cpu_wrap() simplifies the logic,
and makes the algorithm linear.
Signed-off-by: Yury Norov
---
arch/powerpc/xmon/xmon.c | 6 +-
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index f4e841a36458..d7809f15dc68 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1271,11 +1271,7 @@ static int xmon_batch_next_cpu(void)
{
unsigned long cpu;
- while (!cpumask_empty(&xmon_batch_cpus)) {
- cpu = cpumask_next_wrap(smp_processor_id(), &xmon_batch_cpus,
- xmon_batch_start_cpu, true);
- if (cpu >= nr_cpu_ids)
- break;
+ for_each_cpu_wrap(cpu, &xmon_batch_cpus, xmon_batch_start_cpu) {
if (xmon_batch_start_cpu == -1)
xmon_batch_start_cpu = cpu;
if (xmon_switch_cpu(cpu))
--
2.43.0
[PATCH 00/14] cpumask: cleanup cpumask_next_wrap() implementation and usage
cpumask_next_wrap() is overly complicated, comparing to it's generic
version find_next_bit_wrap(), not mentioning it duplicates the above.
It roots to the times when the function was used in the implementation
of for_each_cpu_wrap() iterator. The function has 2 additional parameters
that were used to catch loop termination condition for the iterator.
(Although, only one is needed.)
Since 4fe49b3b97c262 ("lib/bitmap: introduce for_each_set_bit_wrap()
macro"), for_each_cpu_wrap() is wired to corresponding generic
wrapping bitmap iterator, and additional complexity of
cpumask_next_wrap() is not needed anymore.
All existing users call cpumask_next_wrap() in a manner that makes
it possible to turn it to a straight and simple alias to
find_next_bit_wrap().
This series replaces historical 4-parameter cpumask_next_wrap() with a
thin 2-parameter wrapper around find_next_bit_wrap().
Where it's possible to use for_each_cpu_wrap() iterator, the code is
switched to use it because it's always preferable to use iterators over
open loops.
This series touches various scattered subsystems and To-list for the
whole series is quite a long. To minimize noise, I send cover-letter and
key patches #5 and 6 to every person involved. All other patches are sent
individually to those pointed by scripts/get_maintainers.pl.
I'd like to move the series with my bitmap-for-next branch as a whole.
Yury Norov (14):
objpool: rework objpool_pop()
virtio_net: simplify virtnet_set_affinity()
ibmvnic: simplify ibmvnic_set_queue_affinity()
powerpc/xmon: simplify xmon_batch_next_cpu()
cpumask: deprecate cpumask_next_wrap()
cpumask: re-introduce cpumask_next_wrap()
cpumask: use cpumask_next_wrap() where appropriate
padata: switch padata_find_next() to using cpumask_next_wrap()
s390: switch stop_machine_yield() to using cpumask_next_wrap()
nvme-tcp: switch nvme_tcp_set_queue_io_cpu() to using
cpumask_next_wrap()
scsi: lpfc: switch lpfc_irq_rebalance() to using cpumask_next_wrap()
scsi: lpfc: rework lpfc_next_{online,present}_cpu()
PCI: hv: switch hv_compose_multi_msi_req_get_cpu() to using
cpumask_next_wrap()
cpumask: drop cpumask_next_wrap_old()
arch/powerpc/xmon/xmon.c| 6 +---
arch/s390/kernel/processor.c| 2 +-
drivers/net/ethernet/ibm/ibmvnic.c | 17 +-
drivers/net/virtio_net.c| 12 +---
drivers/nvme/host/tcp.c | 2 +-
drivers/pci/controller/pci-hyperv.c | 3 +-
drivers/scsi/lpfc/lpfc.h| 23 +++---
drivers/scsi/lpfc/lpfc_init.c | 2 +-
include/linux/cpumask.h | 48 -
include/linux/objpool.h | 7 ++---
kernel/padata.c | 2 +-
lib/cpumask.c | 37 ++
12 files changed, 60 insertions(+), 101 deletions(-)
--
2.43.0
[PATCH 03/14] ibmvnic: simplify ibmvnic_set_queue_affinity()
A loop based on cpumask_next_wrap() opencodes the dedicated macro
for_each_online_cpu_wrap(). Using the macro allows to avoid setting
bits affinity mask more than once when stride >= num_online_cpus.
This also helps to drop cpumask handling code in the caller function.
Signed-off-by: Yury Norov
---
drivers/net/ethernet/ibm/ibmvnic.c | 17 ++---
1 file changed, 10 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c
b/drivers/net/ethernet/ibm/ibmvnic.c
index e95ae0d39948..4cfd90fb206b 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -234,11 +234,16 @@ static int ibmvnic_set_queue_affinity(struct
ibmvnic_sub_crq_queue *queue,
(*stragglers)--;
}
/* atomic write is safer than writing bit by bit directly */
- for (i = 0; i < stride; i++) {
- cpumask_set_cpu(*cpu, mask);
- *cpu = cpumask_next_wrap(*cpu, cpu_online_mask,
-nr_cpu_ids, false);
+ for_each_online_cpu_wrap(i, *cpu) {
+ if (!stride--)
+ break;
+ cpumask_set_cpu(i, mask);
}
+
+ /* For the next queue we start from the first unused CPU in this queue
*/
+ if (i < nr_cpu_ids)
+ *cpu = i + 1;
+
/* set queue affinity mask */
cpumask_copy(queue->affinity_mask, mask);
rc = irq_set_affinity_and_hint(queue->irq, queue->affinity_mask);
@@ -256,7 +261,7 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter
*adapter)
int num_rxqs = adapter->num_active_rx_scrqs, i_rxqs = 0;
int num_txqs = adapter->num_active_tx_scrqs, i_txqs = 0;
int total_queues, stride, stragglers, i;
- unsigned int num_cpu, cpu;
+ unsigned int num_cpu, cpu = 0;
bool is_rx_queue;
int rc = 0;
@@ -274,8 +279,6 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter
*adapter)
stride = max_t(int, num_cpu / total_queues, 1);
/* number of leftover cpu's */
stragglers = num_cpu >= total_queues ? num_cpu % total_queues : 0;
- /* next available cpu to assign irq to */
- cpu = cpumask_next(-1, cpu_online_mask);
for (i = 0; i < total_queues; i++) {
is_rx_queue = false;
--
2.43.0
[PATCH v2 0/3] sysfs: constify bin_attribute argument of sysfs_bin_attr_simple_read()
Most users use this function through the BIN_ATTR_SIMPLE* macros, they can handle the switch transparently. This series is meant to be merged through the driver core tree. Signed-off-by: Thomas Weißschuh --- Changes in v2: - Rebase on torvalds/master - Drop wmi-bmof patch - Pick up Acks from Andrii - Link to v1: https://lore.kernel.org/r/20241205-sysfs-const-bin_attr-simple-v1-0-4a4e4ced7...@weissschuh.net --- Thomas Weißschuh (3): sysfs: constify bin_attribute argument of sysfs_bin_attr_simple_read() btf: Switch vmlinux BTF attribute to sysfs_bin_attr_simple_read() btf: Switch module BTF attribute to sysfs_bin_attr_simple_read() arch/powerpc/platforms/powernv/opal.c | 2 +- fs/sysfs/file.c | 2 +- include/linux/sysfs.h | 4 ++-- kernel/bpf/btf.c | 15 ++- kernel/bpf/sysfs_btf.c| 12 ++-- kernel/module/sysfs.c | 2 +- 6 files changed, 9 insertions(+), 28 deletions(-) --- base-commit: d6ef8b40d075c425f548002d2f35ae3f06e9cf96 change-id: 20241122-sysfs-const-bin_attr-simple-7c0ddb2fcf12 Best regards, -- Thomas Weißschuh
[PATCH v2 1/3] sysfs: constify bin_attribute argument of sysfs_bin_attr_simple_read()
Most users use this function through the BIN_ATTR_SIMPLE* macros,
they can handle the switch transparently.
Also adapt the two non-macro users in the same change.
Signed-off-by: Thomas Weißschuh
---
arch/powerpc/platforms/powernv/opal.c | 2 +-
fs/sysfs/file.c | 2 +-
include/linux/sysfs.h | 4 ++--
kernel/module/sysfs.c | 2 +-
4 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/opal.c
b/arch/powerpc/platforms/powernv/opal.c
index
5d0f35bb917ebced8c741cd3af2c511949a1d2ef..013637e2b2a8e6a4ec6b93a520f8d5d9d3245467
100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -818,7 +818,7 @@ static int opal_add_one_export(struct kobject *parent,
const char *export_name,
sysfs_bin_attr_init(attr);
attr->attr.name = name;
attr->attr.mode = 0400;
- attr->read = sysfs_bin_attr_simple_read;
+ attr->read_new = sysfs_bin_attr_simple_read;
attr->private = __va(vals[0]);
attr->size = vals[1];
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index
785408861c01c89fc84c787848243a13c1338367..6931308876c4ac3b4c19878d5e1158ad8fe4f16f
100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -817,7 +817,7 @@ EXPORT_SYMBOL_GPL(sysfs_emit_at);
* Returns number of bytes written to @buf.
*/
ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
+ const struct bin_attribute *attr, char *buf,
loff_t off, size_t count)
{
memcpy(buf, attr->private + off, count);
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index
0f2fcd244523f050c5286f19d4fe1846506f9214..2205561159afdb57d0a250bb0439b28c01d9010e
100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -511,7 +511,7 @@ __printf(3, 4)
int sysfs_emit_at(char *buf, int at, const char *fmt, ...);
ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
+ const struct bin_attribute *attr, char *buf,
loff_t off, size_t count);
#else /* CONFIG_SYSFS */
@@ -774,7 +774,7 @@ static inline int sysfs_emit_at(char *buf, int at, const
char *fmt, ...)
static inline ssize_t sysfs_bin_attr_simple_read(struct file *file,
struct kobject *kobj,
-struct bin_attribute *attr,
+const struct bin_attribute
*attr,
char *buf, loff_t off,
size_t count)
{
diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c
index
456358e1fdc43e6b5b24f383bbefa37812971174..254017b58b645d4afcf6876d29bcc2e2113a8dc4
100644
--- a/kernel/module/sysfs.c
+++ b/kernel/module/sysfs.c
@@ -196,7 +196,7 @@ static int add_notes_attrs(struct module *mod, const struct
load_info *info)
nattr->attr.mode = 0444;
nattr->size = info->sechdrs[i].sh_size;
nattr->private = (void *)info->sechdrs[i].sh_addr;
- nattr->read = sysfs_bin_attr_simple_read;
+ nattr->read_new = sysfs_bin_attr_simple_read;
++nattr;
}
++loaded;
--
2.47.1
[PATCH v2 3/3] btf: Switch module BTF attribute to sysfs_bin_attr_simple_read()
The generic function from the sysfs core can replace the custom one.
Signed-off-by: Thomas Weißschuh
Acked-by: Andrii Nakryiko
---
kernel/bpf/btf.c | 15 ++-
1 file changed, 2 insertions(+), 13 deletions(-)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index
e5a5f023cedd5c288c2774218862c69db469917f..76de36d2552002d1e25c826d701340d9cde07ba1
100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -8011,17 +8011,6 @@ struct btf_module {
static LIST_HEAD(btf_modules);
static DEFINE_MUTEX(btf_module_mutex);
-static ssize_t
-btf_module_read(struct file *file, struct kobject *kobj,
- struct bin_attribute *bin_attr,
- char *buf, loff_t off, size_t len)
-{
- const struct btf *btf = bin_attr->private;
-
- memcpy(buf, btf->data + off, len);
- return len;
-}
-
static void purge_cand_cache(struct btf *btf);
static int btf_module_notify(struct notifier_block *nb, unsigned long op,
@@ -8082,8 +8071,8 @@ static int btf_module_notify(struct notifier_block *nb,
unsigned long op,
attr->attr.name = btf->name;
attr->attr.mode = 0444;
attr->size = btf->data_size;
- attr->private = btf;
- attr->read = btf_module_read;
+ attr->private = btf->data;
+ attr->read_new = sysfs_bin_attr_simple_read;
err = sysfs_create_bin_file(btf_kobj, attr);
if (err) {
--
2.47.1
[PATCH v2 2/3] btf: Switch vmlinux BTF attribute to sysfs_bin_attr_simple_read()
The generic function from the sysfs core can replace the custom one.
Signed-off-by: Thomas Weißschuh
Acked-by: Andrii Nakryiko
---
This is a replacement for [0], as Alexei was not happy about
BIN_ATTR_SIMPLE_RO()
[0]
https://lore.kernel.org/lkml/20241122-sysfs-const-bin_attr-bpf-v1-1-823aea399...@weissschuh.net/
---
kernel/bpf/sysfs_btf.c | 12 ++--
1 file changed, 2 insertions(+), 10 deletions(-)
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index
fedb54c94cdb830a4890d33677dcc5a6e236c13f..81d6cf90584a7157929c50f62a5c6862e7a3d081
100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -12,24 +12,16 @@
extern char __start_BTF[];
extern char __stop_BTF[];
-static ssize_t
-btf_vmlinux_read(struct file *file, struct kobject *kobj,
-struct bin_attribute *bin_attr,
-char *buf, loff_t off, size_t len)
-{
- memcpy(buf, __start_BTF + off, len);
- return len;
-}
-
static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
.attr = { .name = "vmlinux", .mode = 0444, },
- .read = btf_vmlinux_read,
+ .read_new = sysfs_bin_attr_simple_read,
};
struct kobject *btf_kobj;
static int __init btf_vmlinux_init(void)
{
+ bin_attr_btf_vmlinux.private = __start_BTF;
bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
if (bin_attr_btf_vmlinux.size == 0)
--
2.47.1
