Commit ec7a9318 authored by WANG Xuerui's avatar WANG Xuerui Committed by Thomas Bogendoerfer

MIPS: emulate CPUCFG instruction on older Loongson64 cores

CPUCFG is the instruction for querying processor characteristics on
newer Loongson processors, much like CPUID of x86. Since the instruction
is supposedly designed to provide a unified way to do feature detection
(without having to, for example, parse /proc/cpuinfo which is too
heavyweight), it is important to provide compatibility for older cores
without native support. Fortunately, most of the fields can be
synthesized without changes to semantics. Performance is not really big
a concern, because feature detection logic is not expected to be
invoked very often in typical userland applications.

The instruction can't be emulated on LOONGSON_2EF cores, according to
FlyGoat's experiments. Because the LWC2 opcode is assigned to other
valid instructions on 2E and 2F, no RI exception is raised for us to
intercept. So compatibility is only extended back furthest to
Loongson-3A1000. Loongson-2K is covered too, as it is basically a remix
of various blocks from the 3A/3B models from a kernel perspective.

This is lightly based on Loongson's work on their Linux 3.10 fork, for
being the authority on the right feature flags to fill in, where things
aren't otherwise discoverable.
Signed-off-by: default avatarWANG Xuerui <git@xen0n.name>
Reviewed-by: default avatarJiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: default avatarThomas Bogendoerfer <tsbogend@alpha.franken.de>
parent 8267e78f
......@@ -1441,6 +1441,18 @@ config CPU_LOONGSON3_WORKAROUNDS
If unsure, please say Y.
config CPU_LOONGSON3_CPUCFG_EMULATION
bool "Emulate the CPUCFG instruction on older Loongson cores"
default y
depends on CPU_LOONGSON64
help
Loongson-3A R4 and newer have the CPUCFG instruction available for
userland to query CPU capabilities, much like CPUID on x86. This
option provides emulation of the instruction on older Loongson
cores, back to Loongson-3A1000.
If unsure, please say Y.
config CPU_LOONGSON2E
bool "Loongson 2E"
depends on SYS_HAS_CPU_LOONGSON2E
......
......@@ -105,6 +105,15 @@ struct cpuinfo_mips {
unsigned int gtoffset_mask;
unsigned int guestid_mask;
unsigned int guestid_cache;
#ifdef CONFIG_CPU_LOONGSON3_CPUCFG_EMULATION
/* CPUCFG data for this CPU, synthesized at probe time.
*
* CPUCFG select 0 is PRId, 4 and above are unimplemented for now.
* So the only stored values are for CPUCFG selects 1-3 inclusive.
*/
u32 loongson3_cpucfg_data[3];
#endif
} __attribute__((aligned(SMP_CACHE_BYTES)));
extern struct cpuinfo_mips cpu_data[];
......
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_MACH_LOONGSON64_CPUCFG_EMUL_H_
#define _ASM_MACH_LOONGSON64_CPUCFG_EMUL_H_
#include <asm/cpu-info.h>
#ifdef CONFIG_CPU_LOONGSON3_CPUCFG_EMULATION
#include <loongson_regs.h>
#define LOONGSON_FPREV_MASK 0x7
void loongson3_cpucfg_synthesize_data(struct cpuinfo_mips *c);
static inline u32 loongson3_cpucfg_read_synthesized(struct cpuinfo_mips *c,
__u64 sel)
{
switch (sel) {
case LOONGSON_CFG0:
return c->processor_id;
case LOONGSON_CFG1:
case LOONGSON_CFG2:
case LOONGSON_CFG3:
return c->loongson3_cpucfg_data[sel - 1];
case LOONGSON_CFG4:
case LOONGSON_CFG5:
/* CPUCFG selects 4 and 5 are related to the input clock
* signal.
*
* Unimplemented for now.
*/
return 0;
case LOONGSON_CFG6:
/* CPUCFG select 6 is for the undocumented Safe Extension. */
return 0;
case LOONGSON_CFG7:
/* CPUCFG select 7 is for the virtualization extension.
* We don't know if the two currently known features are
* supported on older cores according to the public
* documentation, so leave this at zero.
*/
return 0;
}
/*
* Return 0 for unrecognized CPUCFG selects, which is real hardware
* behavior observed on Loongson 3A R4.
*/
return 0;
}
#else
static inline void loongson3_cpucfg_synthesize_data(struct cpuinfo_mips *c)
{
}
static inline u32 loongson3_cpucfg_read_synthesized(struct cpuinfo_mips *c,
__u64 sel)
{
return 0;
}
#endif
#endif /* _ASM_MACH_LOONGSON64_CPUCFG_EMUL_H_ */
......@@ -28,6 +28,8 @@
#include <asm/spram.h>
#include <linux/uaccess.h>
#include <asm/mach-loongson64/cpucfg-emul.h>
/* Hardware capabilities */
unsigned int elf_hwcap __read_mostly;
EXPORT_SYMBOL_GPL(elf_hwcap);
......@@ -2400,6 +2402,13 @@ void cpu_probe(void)
cpu_probe_vmbits(c);
/* Synthesize CPUCFG data if running on Loongson processors;
* no-op otherwise.
*
* This looks at previously probed features, so keep this at bottom.
*/
loongson3_cpucfg_synthesize_data(c);
#ifdef CONFIG_64BIT
if (cpu == 0)
__ua_limit = ~((1ull << cpu_vmbits) - 1);
......
......@@ -71,6 +71,8 @@
#include <asm/tlbex.h>
#include <asm/uasm.h>
#include <asm/mach-loongson64/cpucfg-emul.h>
extern void check_wait(void);
extern asmlinkage void rollback_handle_int(void);
extern asmlinkage void handle_int(void);
......@@ -693,6 +695,44 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
return -1; /* Must be something else ... */
}
/*
* Loongson-3 CSR instructions emulation
*/
#ifdef CONFIG_CPU_LOONGSON3_CPUCFG_EMULATION
#define LWC2 0xc8000000
#define RS BASE
#define CSR_OPCODE2 0x00000118
#define CSR_OPCODE2_MASK 0x000007ff
#define CSR_FUNC_MASK RT
#define CSR_FUNC_CPUCFG 0x8
static int simulate_loongson3_cpucfg(struct pt_regs *regs,
unsigned int opcode)
{
int op = opcode & OPCODE;
int op2 = opcode & CSR_OPCODE2_MASK;
int csr_func = (opcode & CSR_FUNC_MASK) >> 16;
if (op == LWC2 && op2 == CSR_OPCODE2 && csr_func == CSR_FUNC_CPUCFG) {
int rd = (opcode & RD) >> 11;
int rs = (opcode & RS) >> 21;
__u64 sel = regs->regs[rs];
perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
regs->regs[rd] = loongson3_cpucfg_read_synthesized(
&current_cpu_data, sel);
return 0;
}
/* Not ours. */
return -1;
}
#endif /* CONFIG_CPU_LOONGSON3_CPUCFG_EMULATION */
asmlinkage void do_ov(struct pt_regs *regs)
{
enum ctx_state prev_state;
......@@ -1166,6 +1206,11 @@ asmlinkage void do_ri(struct pt_regs *regs)
if (status < 0)
status = simulate_fp(regs, opcode, old_epc, old31);
#ifdef CONFIG_CPU_LOONGSON3_CPUCFG_EMULATION
if (status < 0)
status = simulate_loongson3_cpucfg(regs, opcode);
#endif
} else if (cpu_has_mmips) {
unsigned short mmop[2] = { 0 };
......
......@@ -10,3 +10,4 @@ obj-$(CONFIG_NUMA) += numa.o
obj-$(CONFIG_RS780_HPET) += hpet.o
obj-$(CONFIG_PCI) += pci.o
obj-$(CONFIG_SUSPEND) += pm.o
obj-$(CONFIG_CPU_LOONGSON3_CPUCFG_EMULATION) += cpucfg-emul.o
// SPDX-License-Identifier: GPL-2.0
#include <linux/smp.h>
#include <linux/types.h>
#include <asm/cpu.h>
#include <asm/cpu-info.h>
#include <loongson_regs.h>
#include <cpucfg-emul.h>
static bool is_loongson(struct cpuinfo_mips *c)
{
switch (c->processor_id & PRID_COMP_MASK) {
case PRID_COMP_LEGACY:
return ((c->processor_id & PRID_IMP_MASK) ==
PRID_IMP_LOONGSON_64C);
case PRID_COMP_LOONGSON:
return true;
default:
return false;
}
}
static u32 get_loongson_fprev(struct cpuinfo_mips *c)
{
return c->fpu_id & LOONGSON_FPREV_MASK;
}
static bool cpu_has_uca(void)
{
u32 diag = read_c0_diag();
u32 new_diag;
if (diag & LOONGSON_DIAG_UCAC)
/* UCA is already enabled. */
return true;
/* See if UCAC bit can be flipped on. This should be safe. */
new_diag = diag | LOONGSON_DIAG_UCAC;
write_c0_diag(new_diag);
new_diag = read_c0_diag();
write_c0_diag(diag);
return (new_diag & LOONGSON_DIAG_UCAC) != 0;
}
static void probe_uca(struct cpuinfo_mips *c)
{
if (cpu_has_uca())
c->loongson3_cpucfg_data[0] |= LOONGSON_CFG1_LSUCA;
}
static void decode_loongson_config6(struct cpuinfo_mips *c)
{
u32 config6 = read_c0_config6();
if (config6 & MIPS_CONF6_LOONGSON_SFBEN)
c->loongson3_cpucfg_data[0] |= LOONGSON_CFG1_SFBP;
if (config6 & MIPS_CONF6_LOONGSON_LLEXC)
c->loongson3_cpucfg_data[0] |= LOONGSON_CFG1_LLEXC;
if (config6 & MIPS_CONF6_LOONGSON_SCRAND)
c->loongson3_cpucfg_data[0] |= LOONGSON_CFG1_SCRAND;
}
static void patch_cpucfg_sel1(struct cpuinfo_mips *c)
{
u64 ases = c->ases;
u64 options = c->options;
u32 data = c->loongson3_cpucfg_data[0];
if (options & MIPS_CPU_FPU) {
data |= LOONGSON_CFG1_FP;
data |= get_loongson_fprev(c) << LOONGSON_CFG1_FPREV_OFFSET;
}
if (ases & MIPS_ASE_LOONGSON_MMI)
data |= LOONGSON_CFG1_MMI;
if (ases & MIPS_ASE_MSA)
data |= LOONGSON_CFG1_MSA1;
c->loongson3_cpucfg_data[0] = data;
}
static void patch_cpucfg_sel2(struct cpuinfo_mips *c)
{
u64 ases = c->ases;
u64 options = c->options;
u32 data = c->loongson3_cpucfg_data[1];
if (ases & MIPS_ASE_LOONGSON_EXT)
data |= LOONGSON_CFG2_LEXT1;
if (ases & MIPS_ASE_LOONGSON_EXT2)
data |= LOONGSON_CFG2_LEXT2;
if (options & MIPS_CPU_LDPTE)
data |= LOONGSON_CFG2_LSPW;
if (ases & MIPS_ASE_VZ)
data |= LOONGSON_CFG2_LVZP;
else
data &= ~LOONGSON_CFG2_LVZREV;
c->loongson3_cpucfg_data[1] = data;
}
static void patch_cpucfg_sel3(struct cpuinfo_mips *c)
{
u64 ases = c->ases;
u32 data = c->loongson3_cpucfg_data[2];
if (ases & MIPS_ASE_LOONGSON_CAM) {
data |= LOONGSON_CFG3_LCAMP;
} else {
data &= ~LOONGSON_CFG3_LCAMREV;
data &= ~LOONGSON_CFG3_LCAMNUM;
data &= ~LOONGSON_CFG3_LCAMKW;
data &= ~LOONGSON_CFG3_LCAMVW;
}
c->loongson3_cpucfg_data[2] = data;
}
void loongson3_cpucfg_synthesize_data(struct cpuinfo_mips *c)
{
/* Only engage the logic on Loongson processors. */
if (!is_loongson(c))
return;
/* CPUs with CPUCFG support don't need to synthesize anything. */
if (cpu_has_cfg())
return;
c->loongson3_cpucfg_data[0] = 0;
c->loongson3_cpucfg_data[1] = 0;
c->loongson3_cpucfg_data[2] = 0;
/* Add CPUCFG features non-discoverable otherwise.
*
* All Loongson processors covered by CPUCFG emulation have distinct
* PRID_REV, so take advantage of this.
*/
switch (c->processor_id & PRID_REV_MASK) {
case PRID_REV_LOONGSON3A_R1:
c->loongson3_cpucfg_data[0] |= (LOONGSON_CFG1_LSLDR0 |
LOONGSON_CFG1_LSSYNCI | LOONGSON_CFG1_LSUCA |
LOONGSON_CFG1_LLSYNC | LOONGSON_CFG1_TGTSYNC);
c->loongson3_cpucfg_data[1] |= (LOONGSON_CFG2_LBT1 |
LOONGSON_CFG2_LPMP | LOONGSON_CFG2_LPM_REV1);
c->loongson3_cpucfg_data[2] |= (
LOONGSON_CFG3_LCAM_REV1 |
LOONGSON_CFG3_LCAMNUM_REV1 |
LOONGSON_CFG3_LCAMKW_REV1 |
LOONGSON_CFG3_LCAMVW_REV1);
break;
case PRID_REV_LOONGSON3B_R1:
case PRID_REV_LOONGSON3B_R2:
c->loongson3_cpucfg_data[0] |= (LOONGSON_CFG1_LSLDR0 |
LOONGSON_CFG1_LSSYNCI | LOONGSON_CFG1_LSUCA |
LOONGSON_CFG1_LLSYNC | LOONGSON_CFG1_TGTSYNC);
c->loongson3_cpucfg_data[1] |= (LOONGSON_CFG2_LBT1 |
LOONGSON_CFG2_LPMP | LOONGSON_CFG2_LPM_REV1);
c->loongson3_cpucfg_data[2] |= (
LOONGSON_CFG3_LCAM_REV1 |
LOONGSON_CFG3_LCAMNUM_REV1 |
LOONGSON_CFG3_LCAMKW_REV1 |
LOONGSON_CFG3_LCAMVW_REV1);
break;
case PRID_REV_LOONGSON2K_R1_0:
case PRID_REV_LOONGSON2K_R1_1:
case PRID_REV_LOONGSON2K_R1_2:
case PRID_REV_LOONGSON2K_R1_3:
decode_loongson_config6(c);
probe_uca(c);
c->loongson3_cpucfg_data[0] |= (LOONGSON_CFG1_LSLDR0 |
LOONGSON_CFG1_LSSYNCI | LOONGSON_CFG1_LLSYNC |
LOONGSON_CFG1_TGTSYNC);
c->loongson3_cpucfg_data[1] |= (LOONGSON_CFG2_LBT1 |
LOONGSON_CFG2_LBT2 | LOONGSON_CFG2_LPMP |
LOONGSON_CFG2_LPM_REV2);
c->loongson3_cpucfg_data[2] = 0;
break;
case PRID_REV_LOONGSON3A_R2_0:
case PRID_REV_LOONGSON3A_R2_1:
case PRID_REV_LOONGSON3A_R3_0:
case PRID_REV_LOONGSON3A_R3_1:
decode_loongson_config6(c);
probe_uca(c);
c->loongson3_cpucfg_data[0] |= (LOONGSON_CFG1_CNT64 |
LOONGSON_CFG1_LSLDR0 | LOONGSON_CFG1_LSPREF |
LOONGSON_CFG1_LSPREFX | LOONGSON_CFG1_LSSYNCI |
LOONGSON_CFG1_LLSYNC | LOONGSON_CFG1_TGTSYNC);
c->loongson3_cpucfg_data[1] |= (LOONGSON_CFG2_LBT1 |
LOONGSON_CFG2_LBT2 | LOONGSON_CFG2_LBTMMU |
LOONGSON_CFG2_LPMP | LOONGSON_CFG2_LPM_REV1 |
LOONGSON_CFG2_LVZ_REV1);
c->loongson3_cpucfg_data[2] |= (LOONGSON_CFG3_LCAM_REV1 |
LOONGSON_CFG3_LCAMNUM_REV1 |
LOONGSON_CFG3_LCAMKW_REV1 |
LOONGSON_CFG3_LCAMVW_REV1);
break;
}
/* This feature is set by firmware, but all known Loongson-64 systems
* are configured this way.
*/
c->loongson3_cpucfg_data[0] |= LOONGSON_CFG1_CDMAP;
/* Patch in dynamically probed bits. */
patch_cpucfg_sel1(c);
patch_cpucfg_sel2(c);
patch_cpucfg_sel3(c);
}
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