mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 20:53:00 +07:00
7e1c4e2792
When a memblock allocation APIs are called with align = 0, the alignment is implicitly set to SMP_CACHE_BYTES. Implicit alignment is done deep in the memblock allocator and it can come as a surprise. Not that such an alignment would be wrong even when used incorrectly but it is better to be explicit for the sake of clarity and the prinicple of the least surprise. Replace all such uses of memblock APIs with the 'align' parameter explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment in the memblock internal allocation functions. For the case when memblock APIs are used via helper functions, e.g. like iommu_arena_new_node() in Alpha, the helper functions were detected with Coccinelle's help and then manually examined and updated where appropriate. The direct memblock APIs users were updated using the semantic patch below: @@ expression size, min_addr, max_addr, nid; @@ ( | - memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc(size, 0) + memblock_alloc(size, SMP_CACHE_BYTES) | - memblock_alloc_raw(size, 0) + memblock_alloc_raw(size, SMP_CACHE_BYTES) | - memblock_alloc_from(size, 0, min_addr) + memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_nopanic(size, 0) + memblock_alloc_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_low(size, 0) + memblock_alloc_low(size, SMP_CACHE_BYTES) | - memblock_alloc_low_nopanic(size, 0) + memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_from_nopanic(size, 0, min_addr) + memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_node(size, 0, nid) + memblock_alloc_node(size, SMP_CACHE_BYTES, nid) ) [mhocko@suse.com: changelog update] [akpm@linux-foundation.org: coding-style fixes] [rppt@linux.ibm.com: fix missed uses of implicit alignment] Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Suggested-by: Michal Hocko <mhocko@suse.com> Acked-by: Paul Burton <paul.burton@mips.com> [MIPS] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michal Simek <monstr@monstr.eu> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
231 lines
5.8 KiB
C
231 lines
5.8 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/slab.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/export.h>
|
|
#include <linux/memblock.h>
|
|
|
|
/**
|
|
* cpumask_next - get the next cpu in a cpumask
|
|
* @n: the cpu prior to the place to search (ie. return will be > @n)
|
|
* @srcp: the cpumask pointer
|
|
*
|
|
* Returns >= nr_cpu_ids if no further cpus set.
|
|
*/
|
|
unsigned int cpumask_next(int n, const struct cpumask *srcp)
|
|
{
|
|
/* -1 is a legal arg here. */
|
|
if (n != -1)
|
|
cpumask_check(n);
|
|
return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
|
|
}
|
|
EXPORT_SYMBOL(cpumask_next);
|
|
|
|
/**
|
|
* cpumask_next_and - get the next cpu in *src1p & *src2p
|
|
* @n: the cpu prior to the place to search (ie. return will be > @n)
|
|
* @src1p: the first cpumask pointer
|
|
* @src2p: the second cpumask pointer
|
|
*
|
|
* Returns >= nr_cpu_ids if no further cpus set in both.
|
|
*/
|
|
int cpumask_next_and(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(cpumask_bits(src1p), cpumask_bits(src2p),
|
|
nr_cpumask_bits, n + 1);
|
|
}
|
|
EXPORT_SYMBOL(cpumask_next_and);
|
|
|
|
/**
|
|
* cpumask_any_but - return a "random" in a cpumask, but not this one.
|
|
* @mask: the cpumask to search
|
|
* @cpu: the cpu to ignore.
|
|
*
|
|
* Often used to find any cpu but smp_processor_id() in a mask.
|
|
* Returns >= nr_cpu_ids if no cpus set.
|
|
*/
|
|
int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
|
|
{
|
|
unsigned int i;
|
|
|
|
cpumask_check(cpu);
|
|
for_each_cpu(i, mask)
|
|
if (i != cpu)
|
|
break;
|
|
return i;
|
|
}
|
|
EXPORT_SYMBOL(cpumask_any_but);
|
|
|
|
/**
|
|
* cpumask_next_wrap - helper to implement for_each_cpu_wrap
|
|
* @n: the cpu prior to the place to search
|
|
* @mask: the cpumask pointer
|
|
* @start: the start point of the iteration
|
|
* @wrap: assume @n crossing @start terminates the iteration
|
|
*
|
|
* Returns >= nr_cpu_ids on completion
|
|
*
|
|
* Note: the @wrap argument is required for the start condition when
|
|
* we cannot assume @start is set in @mask.
|
|
*/
|
|
int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
|
|
{
|
|
int next;
|
|
|
|
again:
|
|
next = cpumask_next(n, mask);
|
|
|
|
if (wrap && n < start && next >= start) {
|
|
return nr_cpumask_bits;
|
|
|
|
} else if (next >= nr_cpumask_bits) {
|
|
wrap = true;
|
|
n = -1;
|
|
goto again;
|
|
}
|
|
|
|
return next;
|
|
}
|
|
EXPORT_SYMBOL(cpumask_next_wrap);
|
|
|
|
/* These are not inline because of header tangles. */
|
|
#ifdef CONFIG_CPUMASK_OFFSTACK
|
|
/**
|
|
* alloc_cpumask_var_node - allocate a struct cpumask on a given node
|
|
* @mask: pointer to cpumask_var_t where the cpumask is returned
|
|
* @flags: GFP_ flags
|
|
*
|
|
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
|
|
* a nop returning a constant 1 (in <linux/cpumask.h>)
|
|
* Returns TRUE if memory allocation succeeded, FALSE otherwise.
|
|
*
|
|
* In addition, mask will be NULL if this fails. Note that gcc is
|
|
* usually smart enough to know that mask can never be NULL if
|
|
* CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case
|
|
* too.
|
|
*/
|
|
bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
|
|
{
|
|
*mask = kmalloc_node(cpumask_size(), flags, node);
|
|
|
|
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
|
|
if (!*mask) {
|
|
printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");
|
|
dump_stack();
|
|
}
|
|
#endif
|
|
|
|
return *mask != NULL;
|
|
}
|
|
EXPORT_SYMBOL(alloc_cpumask_var_node);
|
|
|
|
bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
|
|
{
|
|
return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
|
|
}
|
|
EXPORT_SYMBOL(zalloc_cpumask_var_node);
|
|
|
|
/**
|
|
* alloc_cpumask_var - allocate a struct cpumask
|
|
* @mask: pointer to cpumask_var_t where the cpumask is returned
|
|
* @flags: GFP_ flags
|
|
*
|
|
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
|
|
* a nop returning a constant 1 (in <linux/cpumask.h>).
|
|
*
|
|
* See alloc_cpumask_var_node.
|
|
*/
|
|
bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
|
|
{
|
|
return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
|
|
}
|
|
EXPORT_SYMBOL(alloc_cpumask_var);
|
|
|
|
bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
|
|
{
|
|
return alloc_cpumask_var(mask, flags | __GFP_ZERO);
|
|
}
|
|
EXPORT_SYMBOL(zalloc_cpumask_var);
|
|
|
|
/**
|
|
* alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
|
|
* @mask: pointer to cpumask_var_t where the cpumask is returned
|
|
*
|
|
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
|
|
* a nop (in <linux/cpumask.h>).
|
|
* Either returns an allocated (zero-filled) cpumask, or causes the
|
|
* system to panic.
|
|
*/
|
|
void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask)
|
|
{
|
|
*mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES);
|
|
}
|
|
|
|
/**
|
|
* free_cpumask_var - frees memory allocated for a struct cpumask.
|
|
* @mask: cpumask to free
|
|
*
|
|
* This is safe on a NULL mask.
|
|
*/
|
|
void free_cpumask_var(cpumask_var_t mask)
|
|
{
|
|
kfree(mask);
|
|
}
|
|
EXPORT_SYMBOL(free_cpumask_var);
|
|
|
|
/**
|
|
* free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var
|
|
* @mask: cpumask to free
|
|
*/
|
|
void __init free_bootmem_cpumask_var(cpumask_var_t mask)
|
|
{
|
|
memblock_free_early(__pa(mask), cpumask_size());
|
|
}
|
|
#endif
|
|
|
|
/**
|
|
* cpumask_local_spread - select the i'th cpu with local numa cpu's first
|
|
* @i: index number
|
|
* @node: local numa_node
|
|
*
|
|
* This function selects an online CPU according to a numa aware policy;
|
|
* local cpus are returned first, followed by non-local ones, then it
|
|
* wraps around.
|
|
*
|
|
* It's not very efficient, but useful for setup.
|
|
*/
|
|
unsigned int cpumask_local_spread(unsigned int i, int node)
|
|
{
|
|
int cpu;
|
|
|
|
/* Wrap: we always want a cpu. */
|
|
i %= num_online_cpus();
|
|
|
|
if (node == -1) {
|
|
for_each_cpu(cpu, cpu_online_mask)
|
|
if (i-- == 0)
|
|
return cpu;
|
|
} else {
|
|
/* NUMA first. */
|
|
for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
|
|
if (i-- == 0)
|
|
return cpu;
|
|
|
|
for_each_cpu(cpu, cpu_online_mask) {
|
|
/* Skip NUMA nodes, done above. */
|
|
if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
|
|
continue;
|
|
|
|
if (i-- == 0)
|
|
return cpu;
|
|
}
|
|
}
|
|
BUG();
|
|
}
|
|
EXPORT_SYMBOL(cpumask_local_spread);
|