linux/arch/arm64/kernel/cacheinfo.c

118 lines
2.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* ARM64 cacheinfo support
*
* Copyright (C) 2015 ARM Ltd.
* All Rights Reserved
*/
#include <linux/acpi.h>
#include <linux/cacheinfo.h>
#include <linux/of.h>
#define MAX_CACHE_LEVEL 7 /* Max 7 level supported */
int cache_line_size(void)
{
if (coherency_max_size != 0)
return coherency_max_size;
return cache_line_size_of_cpu();
}
EXPORT_SYMBOL_GPL(cache_line_size);
static inline enum cache_type get_cache_type(int level)
{
u64 clidr;
if (level > MAX_CACHE_LEVEL)
return CACHE_TYPE_NOCACHE;
clidr = read_sysreg(clidr_el1);
return CLIDR_CTYPE(clidr, level);
}
static void ci_leaf_init(struct cacheinfo *this_leaf,
enum cache_type type, unsigned int level)
{
this_leaf->level = level;
this_leaf->type = type;
}
cacheinfo: Add arm64 early level initializer implementation This patch adds an architecture specific early cache level detection handler for arm64. This is basically the CLIDR_EL1 based detection that was previously done (only) in init_cache_level(). This is part of a patch series that attempts to further the work in commit 5944ce092b97 ("arch_topology: Build cacheinfo from primary CPU"). Previously, in the absence of any DT/ACPI cache info, architecture specific cache detection and info allocation for secondary CPUs would happen in non-preemptible context during early CPU initialization and trigger a "BUG: sleeping function called from invalid context" splat on an RT kernel. This patch does not solve the problem completely for RT kernels. It relies on the assumption that on most systems, the CPUs are symmetrical and therefore have the same number of cache leaves. The cacheinfo memory is allocated early (on the primary CPU), relying on the new handler. If later (when CLIDR_EL1 based detection runs again on the secondary CPU) the initial assumption proves to be wrong and the CPU has in fact more leaves, the cacheinfo memory is reallocated, and that still triggers a splat on an RT kernel. In other words, asymmetrical CPU systems *must* still provide cacheinfo data in DT/ACPI to avoid the splat on RT kernels (unless secondary CPUs happen to have less leaves than the primary CPU). But symmetrical CPU systems (the majority) can now get away without the additional DT/ACPI data and rely on CLIDR_EL1 based detection. Signed-off-by: Radu Rendec <rrendec@redhat.com> Reviewed-by: Pierre Gondois <pierre.gondois@arm.com> Link: https://lore.kernel.org/r/20230412185759.755408-3-rrendec@redhat.com Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
2023-04-12 14:57:58 -04:00
static void detect_cache_level(unsigned int *level_p, unsigned int *leaves_p)
{
arm64: cacheinfo: Fix incorrect assignment of signed error value to unsigned fw_level Though acpi_find_last_cache_level() always returned signed value and the document states it will return any errors caused by lack of a PPTT table, it never returned negative values before. Commit 0c80f9e165f8 ("ACPI: PPTT: Leave the table mapped for the runtime usage") however changed it by returning -ENOENT if no PPTT was found. The value returned from acpi_find_last_cache_level() is then assigned to unsigned fw_level. It will result in the number of cache leaves calculated incorrectly as a huge value which will then cause the following warning from __alloc_pages as the order would be great than MAX_ORDER because of incorrect and huge cache leaves value. | WARNING: CPU: 0 PID: 1 at mm/page_alloc.c:5407 __alloc_pages+0x74/0x314 | Modules linked in: | CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.19.0-10393-g7c2a8d3ac4c0 #73 | pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : __alloc_pages+0x74/0x314 | lr : alloc_pages+0xe8/0x318 | Call trace: | __alloc_pages+0x74/0x314 | alloc_pages+0xe8/0x318 | kmalloc_order_trace+0x68/0x1dc | __kmalloc+0x240/0x338 | detect_cache_attributes+0xe0/0x56c | update_siblings_masks+0x38/0x284 | store_cpu_topology+0x78/0x84 | smp_prepare_cpus+0x48/0x134 | kernel_init_freeable+0xc4/0x14c | kernel_init+0x2c/0x1b4 | ret_from_fork+0x10/0x20 Fix the same by changing fw_level to be signed integer and return the error from init_cache_level() early in case of error. Reported-and-Tested-by: Bruno Goncalves <bgoncalv@redhat.com> Signed-off-by: Sudeep Holla <sudeep.holla@arm.com> Link: https://lore.kernel.org/r/20220808084640.3165368-1-sudeep.holla@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2022-08-08 09:46:40 +01:00
unsigned int ctype, level, leaves;
for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) {
ctype = get_cache_type(level);
if (ctype == CACHE_TYPE_NOCACHE) {
level--;
break;
}
/* Separate instruction and data caches */
leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1;
}
cacheinfo: Add arm64 early level initializer implementation This patch adds an architecture specific early cache level detection handler for arm64. This is basically the CLIDR_EL1 based detection that was previously done (only) in init_cache_level(). This is part of a patch series that attempts to further the work in commit 5944ce092b97 ("arch_topology: Build cacheinfo from primary CPU"). Previously, in the absence of any DT/ACPI cache info, architecture specific cache detection and info allocation for secondary CPUs would happen in non-preemptible context during early CPU initialization and trigger a "BUG: sleeping function called from invalid context" splat on an RT kernel. This patch does not solve the problem completely for RT kernels. It relies on the assumption that on most systems, the CPUs are symmetrical and therefore have the same number of cache leaves. The cacheinfo memory is allocated early (on the primary CPU), relying on the new handler. If later (when CLIDR_EL1 based detection runs again on the secondary CPU) the initial assumption proves to be wrong and the CPU has in fact more leaves, the cacheinfo memory is reallocated, and that still triggers a splat on an RT kernel. In other words, asymmetrical CPU systems *must* still provide cacheinfo data in DT/ACPI to avoid the splat on RT kernels (unless secondary CPUs happen to have less leaves than the primary CPU). But symmetrical CPU systems (the majority) can now get away without the additional DT/ACPI data and rely on CLIDR_EL1 based detection. Signed-off-by: Radu Rendec <rrendec@redhat.com> Reviewed-by: Pierre Gondois <pierre.gondois@arm.com> Link: https://lore.kernel.org/r/20230412185759.755408-3-rrendec@redhat.com Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
2023-04-12 14:57:58 -04:00
*level_p = level;
*leaves_p = leaves;
}
int early_cache_level(unsigned int cpu)
{
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
detect_cache_level(&this_cpu_ci->num_levels, &this_cpu_ci->num_leaves);
return 0;
}
int init_cache_level(unsigned int cpu)
{
unsigned int level, leaves;
int fw_level, ret;
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
detect_cache_level(&level, &leaves);
if (acpi_disabled) {
fw_level = of_find_last_cache_level(cpu);
} else {
ret = acpi_get_cache_info(cpu, &fw_level, NULL);
if (ret < 0)
fw_level = 0;
}
if (level < fw_level) {
/*
* some external caches not specified in CLIDR_EL1
* the information may be available in the device tree
* only unified external caches are considered here
*/
leaves += (fw_level - level);
level = fw_level;
}
this_cpu_ci->num_levels = level;
this_cpu_ci->num_leaves = leaves;
return 0;
}
int populate_cache_leaves(unsigned int cpu)
{
unsigned int level, idx;
enum cache_type type;
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
struct cacheinfo *this_leaf = this_cpu_ci->info_list;
for (idx = 0, level = 1; level <= this_cpu_ci->num_levels &&
idx < this_cpu_ci->num_leaves; idx++, level++) {
type = get_cache_type(level);
if (type == CACHE_TYPE_SEPARATE) {
ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
} else {
ci_leaf_init(this_leaf++, type, level);
}
}
return 0;
}