Commit 3d410094 authored by Thomas Gleixner's avatar Thomas Gleixner

x86/cpu: Provide a sane leaf 0xb/0x1f parser

detect_extended_topology() along with it's early() variant is a classic
example for duct tape engineering:

  - It evaluates an array of subleafs with a boatload of local variables
    for the relevant topology levels instead of using an array to save the
    enumerated information and propagate it to the right level

  - It has no boundary checks for subleafs

  - It prevents updating the die_id with a crude workaround instead of
    checking for leaf 0xb which does not provide die information.

  - It's broken vs. the number of dies evaluation as it uses:

      num_processors[DIE_LEVEL] / num_processors[CORE_LEVEL]

    which "works" only correctly if there is none of the intermediate
    topology levels (MODULE/TILE) enumerated.

There is zero value in trying to "fix" that code as the only proper fix is
to rewrite it from scratch.

Implement a sane parser with proper code documentation, which will be used
for the consolidated topology evaluation in the next step.
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Tested-by: default avatarJuergen Gross <jgross@suse.com>
Tested-by: default avatarSohil Mehta <sohil.mehta@intel.com>
Tested-by: default avatarMichael Kelley <mhklinux@outlook.com>
Tested-by: default avatarZhang Rui <rui.zhang@intel.com>
Tested-by: default avatarWang Wendy <wendy.wang@intel.com>
Tested-by: default avatarK Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20240212153624.830571770@linutronix.de
parent 92853a77
...@@ -18,7 +18,7 @@ KMSAN_SANITIZE_common.o := n ...@@ -18,7 +18,7 @@ KMSAN_SANITIZE_common.o := n
KCSAN_SANITIZE_common.o := n KCSAN_SANITIZE_common.o := n
obj-y := cacheinfo.o scattered.o obj-y := cacheinfo.o scattered.o
obj-y += topology_common.o topology.o obj-y += topology_common.o topology_ext.o topology.o
obj-y += common.o obj-y += common.o
obj-y += rdrand.o obj-y += rdrand.o
obj-y += match.o obj-y += match.o
......
...@@ -16,6 +16,7 @@ void cpu_init_topology(struct cpuinfo_x86 *c); ...@@ -16,6 +16,7 @@ void cpu_init_topology(struct cpuinfo_x86 *c);
void cpu_parse_topology(struct cpuinfo_x86 *c); void cpu_parse_topology(struct cpuinfo_x86 *c);
void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom, void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom,
unsigned int shift, unsigned int ncpus); unsigned int shift, unsigned int ncpus);
bool cpu_parse_topology_ext(struct topo_scan *tscan);
static inline u32 topo_shift_apicid(u32 apicid, enum x86_topology_domains dom) static inline u32 topo_shift_apicid(u32 apicid, enum x86_topology_domains dom)
{ {
...@@ -36,4 +37,15 @@ static inline u32 topo_domain_mask(enum x86_topology_domains dom) ...@@ -36,4 +37,15 @@ static inline u32 topo_domain_mask(enum x86_topology_domains dom)
return (1U << x86_topo_system.dom_shifts[dom]) - 1; return (1U << x86_topo_system.dom_shifts[dom]) - 1;
} }
/*
* Update a domain level after the fact without propagating. Used to fixup
* broken CPUID enumerations.
*/
static inline void topology_update_dom(struct topo_scan *tscan, enum x86_topology_domains dom,
unsigned int shift, unsigned int ncpus)
{
tscan->dom_shifts[dom] = shift;
tscan->dom_ncpus[dom] = ncpus;
}
#endif /* ARCH_X86_TOPOLOGY_H */ #endif /* ARCH_X86_TOPOLOGY_H */
// SPDX-License-Identifier: GPL-2.0
#include <linux/cpu.h>
#include <asm/apic.h>
#include <asm/memtype.h>
#include <asm/processor.h>
#include "cpu.h"
enum topo_types {
INVALID_TYPE = 0,
SMT_TYPE = 1,
CORE_TYPE = 2,
MAX_TYPE_0B = 3,
MODULE_TYPE = 3,
TILE_TYPE = 4,
DIE_TYPE = 5,
DIEGRP_TYPE = 6,
MAX_TYPE_1F = 7,
};
/*
* Use a lookup table for the case that there are future types > 6 which
* describe an intermediate domain level which does not exist today.
*/
static const unsigned int topo_domain_map_0b_1f[MAX_TYPE_1F] = {
[SMT_TYPE] = TOPO_SMT_DOMAIN,
[CORE_TYPE] = TOPO_CORE_DOMAIN,
[MODULE_TYPE] = TOPO_MODULE_DOMAIN,
[TILE_TYPE] = TOPO_TILE_DOMAIN,
[DIE_TYPE] = TOPO_DIE_DOMAIN,
[DIEGRP_TYPE] = TOPO_DIEGRP_DOMAIN,
};
static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf,
unsigned int *last_dom)
{
unsigned int dom, maxtype;
const unsigned int *map;
struct {
// eax
u32 x2apic_shift : 5, // Number of bits to shift APIC ID right
// for the topology ID at the next level
: 27; // Reserved
// ebx
u32 num_processors : 16, // Number of processors at current level
: 16; // Reserved
// ecx
u32 level : 8, // Current topology level. Same as sub leaf number
type : 8, // Level type. If 0, invalid
: 16; // Reserved
// edx
u32 x2apic_id : 32; // X2APIC ID of the current logical processor
} sl;
switch (leaf) {
case 0x0b: maxtype = MAX_TYPE_0B; map = topo_domain_map_0b_1f; break;
case 0x1f: maxtype = MAX_TYPE_1F; map = topo_domain_map_0b_1f; break;
default: return false;
}
cpuid_subleaf(leaf, subleaf, &sl);
if (!sl.num_processors || sl.type == INVALID_TYPE)
return false;
if (sl.type >= maxtype) {
pr_err_once("Topology: leaf 0x%x:%d Unknown domain type %u\n",
leaf, subleaf, sl.type);
/*
* It really would have been too obvious to make the domain
* type space sparse and leave a few reserved types between
* the points which might change instead of following the
* usual "this can be fixed in software" principle.
*/
dom = *last_dom + 1;
} else {
dom = map[sl.type];
*last_dom = dom;
}
if (!dom) {
tscan->c->topo.initial_apicid = sl.x2apic_id;
} else if (tscan->c->topo.initial_apicid != sl.x2apic_id) {
pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf %d APIC ID mismatch %x != %x\n",
leaf, subleaf, tscan->c->topo.initial_apicid, sl.x2apic_id);
}
topology_set_dom(tscan, dom, sl.x2apic_shift, sl.num_processors);
return true;
}
static bool parse_topology_leaf(struct topo_scan *tscan, u32 leaf)
{
unsigned int last_dom;
u32 subleaf;
/* Read all available subleafs and populate the levels */
for (subleaf = 0, last_dom = 0; topo_subleaf(tscan, leaf, subleaf, &last_dom); subleaf++);
/* If subleaf 0 failed to parse, give up */
if (!subleaf)
return false;
/*
* There are machines in the wild which have shift 0 in the subleaf
* 0, but advertise 2 logical processors at that level. They are
* truly SMT.
*/
if (!tscan->dom_shifts[TOPO_SMT_DOMAIN] && tscan->dom_ncpus[TOPO_SMT_DOMAIN] > 1) {
unsigned int sft = get_count_order(tscan->dom_ncpus[TOPO_SMT_DOMAIN]);
pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf 0 has shift level 0 but %u CPUs. Fixing it up.\n",
leaf, tscan->dom_ncpus[TOPO_SMT_DOMAIN]);
topology_update_dom(tscan, TOPO_SMT_DOMAIN, sft, tscan->dom_ncpus[TOPO_SMT_DOMAIN]);
}
set_cpu_cap(tscan->c, X86_FEATURE_XTOPOLOGY);
return true;
}
bool cpu_parse_topology_ext(struct topo_scan *tscan)
{
/* Intel: Try leaf 0x1F first. */
if (tscan->c->cpuid_level >= 0x1f && parse_topology_leaf(tscan, 0x1f))
return true;
/* Intel/AMD: Fall back to leaf 0xB if available */
return tscan->c->cpuid_level >= 0x0b && parse_topology_leaf(tscan, 0x0b);
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment