aboutsummaryrefslogtreecommitdiff
path: root/arch/mips
diff options
context:
space:
mode:
Diffstat (limited to 'arch/mips')
-rw-r--r--arch/mips/ath79/clock.c7
-rw-r--r--arch/mips/include/asm/irq.h15
-rw-r--r--arch/mips/kernel/asm-offsets.c1
-rw-r--r--arch/mips/kernel/cps-vec.S2
-rw-r--r--arch/mips/kernel/genex.S8
-rw-r--r--arch/mips/kernel/process.c56
-rw-r--r--arch/mips/kernel/vmlinux.lds.S2
-rw-r--r--arch/mips/lantiq/xway/sysctrl.c4
-rw-r--r--arch/mips/math-emu/cp1emu.c2
-rw-r--r--arch/mips/math-emu/dp_fmax.c84
-rw-r--r--arch/mips/math-emu/dp_fmin.c86
-rw-r--r--arch/mips/math-emu/dp_maddf.c245
-rw-r--r--arch/mips/math-emu/ieee754int.h4
-rw-r--r--arch/mips/math-emu/ieee754sp.h4
-rw-r--r--arch/mips/math-emu/sp_fmax.c84
-rw-r--r--arch/mips/math-emu/sp_fmin.c86
-rw-r--r--arch/mips/math-emu/sp_maddf.c226
-rw-r--r--arch/mips/ralink/mt7620.c18
-rw-r--r--arch/mips/ralink/rt3883.c2
19 files changed, 603 insertions, 333 deletions
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index cc3a1e33a600..7e2bb12b64ea 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -508,16 +508,19 @@ static void __init ath79_clocks_init_dt_ng(struct device_node *np)
ar9330_clk_init(ref_clk, pll_base);
else {
pr_err("%s: could not find any appropriate clk_init()\n", dnfn);
- goto err_clk;
+ goto err_iounmap;
}
if (of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data)) {
pr_err("%s: could not register clk provider\n", dnfn);
- goto err_clk;
+ goto err_iounmap;
}
return;
+err_iounmap:
+ iounmap(pll_base);
+
err_clk:
clk_put(ref_clk);
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 956db6e201d1..c5d351786416 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -18,9 +18,24 @@
#include <irq.h>
#define IRQ_STACK_SIZE THREAD_SIZE
+#define IRQ_STACK_START (IRQ_STACK_SIZE - 16)
extern void *irq_stack[NR_CPUS];
+/*
+ * The highest address on the IRQ stack contains a dummy frame put down in
+ * genex.S (handle_int & except_vec_vi_handler) which is structured as follows:
+ *
+ * top ------------
+ * | task sp | <- irq_stack[cpu] + IRQ_STACK_START
+ * ------------
+ * | | <- First frame of IRQ context
+ * ------------
+ *
+ * task sp holds a copy of the task stack pointer where the struct pt_regs
+ * from exception entry can be found.
+ */
+
static inline bool on_irq_stack(int cpu, unsigned long sp)
{
unsigned long low = (unsigned long)irq_stack[cpu];
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index 4be2763f835d..bfff6ea45d51 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -103,6 +103,7 @@ void output_thread_info_defines(void)
DEFINE(_THREAD_SIZE, THREAD_SIZE);
DEFINE(_THREAD_MASK, THREAD_MASK);
DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
+ DEFINE(_IRQ_STACK_START, IRQ_STACK_START);
BLANK();
}
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 59476a607add..a00e87b0256d 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -361,7 +361,7 @@ LEAF(mips_cps_get_bootcfg)
END(mips_cps_get_bootcfg)
LEAF(mips_cps_boot_vpes)
- PTR_L ta2, COREBOOTCFG_VPEMASK(a0)
+ lw ta2, COREBOOTCFG_VPEMASK(a0)
PTR_L ta3, COREBOOTCFG_VPECONFIG(a0)
#if defined(CONFIG_CPU_MIPSR6)
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 2ac6c2625c13..ae810da4d499 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -215,9 +215,11 @@ NESTED(handle_int, PT_SIZE, sp)
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jal plat_irq_dispatch
@@ -325,9 +327,11 @@ NESTED(except_vec_vi_handler, 0, sp)
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jalr v0
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index fbbf5fcc695a..1b50958a1373 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -487,31 +487,52 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
unsigned long pc,
unsigned long *ra)
{
+ unsigned long low, high, irq_stack_high;
struct mips_frame_info info;
unsigned long size, ofs;
+ struct pt_regs *regs;
int leaf;
- extern void ret_from_irq(void);
- extern void ret_from_exception(void);
if (!stack_page)
return 0;
/*
- * If we reached the bottom of interrupt context,
- * return saved pc in pt_regs.
+ * IRQ stacks start at IRQ_STACK_START
+ * task stacks at THREAD_SIZE - 32
*/
- if (pc == (unsigned long)ret_from_irq ||
- pc == (unsigned long)ret_from_exception) {
- struct pt_regs *regs;
- if (*sp >= stack_page &&
- *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
- regs = (struct pt_regs *)*sp;
- pc = regs->cp0_epc;
- if (!user_mode(regs) && __kernel_text_address(pc)) {
- *sp = regs->regs[29];
- *ra = regs->regs[31];
- return pc;
- }
+ low = stack_page;
+ if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
+ high = stack_page + IRQ_STACK_START;
+ irq_stack_high = high;
+ } else {
+ high = stack_page + THREAD_SIZE - 32;
+ irq_stack_high = 0;
+ }
+
+ /*
+ * If we reached the top of the interrupt stack, start unwinding
+ * the interrupted task stack.
+ */
+ if (unlikely(*sp == irq_stack_high)) {
+ unsigned long task_sp = *(unsigned long *)*sp;
+
+ /*
+ * Check that the pointer saved in the IRQ stack head points to
+ * something within the stack of the current task
+ */
+ if (!object_is_on_stack((void *)task_sp))
+ return 0;
+
+ /*
+ * Follow pointer to tasks kernel stack frame where interrupted
+ * state was saved.
+ */
+ regs = (struct pt_regs *)task_sp;
+ pc = regs->cp0_epc;
+ if (!user_mode(regs) && __kernel_text_address(pc)) {
+ *sp = regs->regs[29];
+ *ra = regs->regs[31];
+ return pc;
}
return 0;
}
@@ -532,8 +553,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
if (leaf < 0)
return 0;
- if (*sp < stack_page ||
- *sp + info.frame_size > stack_page + THREAD_SIZE - 32)
+ if (*sp < low || *sp + info.frame_size > high)
return 0;
if (leaf)
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index d5de67591735..f0a0e6d62be3 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -182,7 +182,7 @@ SECTIONS
* Force .bss to 64K alignment so that .bss..swapper_pg_dir
* gets that alignment. .sbss should be empty, so there will be
* no holes after __init_end. */
- BSS_SECTION(0, 0x10000, 0)
+ BSS_SECTION(0, 0x10000, 8)
_end = . ;
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index 90565477dfbd..95bec460b651 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -469,8 +469,8 @@ void __init ltq_soc_init(void)
panic("Failed to load xbar nodes from devicetree");
if (of_address_to_resource(np_xbar, 0, &res_xbar))
panic("Failed to get xbar resources");
- if (request_mem_region(res_xbar.start, resource_size(&res_xbar),
- res_xbar.name) < 0)
+ if (!request_mem_region(res_xbar.start, resource_size(&res_xbar),
+ res_xbar.name))
panic("Failed to get xbar resources");
ltq_xbar_membase = ioremap_nocache(res_xbar.start,
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index e9385bcd9723..9ade60ca08e0 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -2386,7 +2386,6 @@ dcopuop:
break;
default:
/* Reserved R6 ops */
- pr_err("Reserved MIPS R6 CMP.condn.S operation\n");
return SIGILL;
}
}
@@ -2460,7 +2459,6 @@ dcopuop:
break;
default:
/* Reserved R6 ops */
- pr_err("Reserved MIPS R6 CMP.condn.D operation\n");
return SIGILL;
}
}
diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c
index fd71b8daaaf2..5bec64f2884e 100644
--- a/arch/mips/math-emu/dp_fmax.c
+++ b/arch/mips/math-emu/dp_fmax.c
@@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754dp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
return ys ? x : y;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754dp_zero(1);
+ return ieee754dp_zero(xs & ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
DPDNORMX;
@@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y)
else if (xs < ys)
return x;
- /* Compare exponent */
- if (xe > ye)
- return x;
- else if (xe < ye)
- return y;
+ /* Signs of inputs are equal, let's compare exponents */
+ if (xs == 0) {
+ /* Inputs are both positive */
+ if (xe > ye)
+ return x;
+ else if (xe < ye)
+ return y;
+ } else {
+ /* Inputs are both negative */
+ if (xe > ye)
+ return y;
+ else if (xe < ye)
+ return x;
+ }
- /* Compare mantissa */
+ /* Signs and exponents of inputs are equal, let's compare mantissas */
+ if (xs == 0) {
+ /* Inputs are both positive, with equal signs and exponents */
+ if (xm <= ym)
+ return y;
+ return x;
+ }
+ /* Inputs are both negative, with equal signs and exponents */
if (xm <= ym)
- return y;
- return x;
+ return x;
+ return y;
}
union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
@@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754dp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,6 +202,9 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
/*
* Infinity and zero handling
*/
+ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+ return ieee754dp_inf(xs & ys);
+
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
@@ -171,7 +212,6 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
return x;
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -180,9 +220,7 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
return y;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754dp_zero(1);
+ return ieee754dp_zero(xs & ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
DPDNORMX;
@@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y)
return y;
/* Compare mantissa */
- if (xm <= ym)
+ if (xm < ym)
return y;
- return x;
+ else if (xm > ym)
+ return x;
+ else if (xs == 0)
+ return x;
+ return y;
}
diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c
index c1072b0dfb95..a287b23818d8 100644
--- a/arch/mips/math-emu/dp_fmin.c
+++ b/arch/mips/math-emu/dp_fmin.c
@@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754dp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
return ys ? y : x;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754dp_zero(1);
+ return ieee754dp_zero(xs | ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
DPDNORMX;
@@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y)
else if (xs < ys)
return y;
- /* Compare exponent */
- if (xe > ye)
- return y;
- else if (xe < ye)
- return x;
+ /* Signs of inputs are the same, let's compare exponents */
+ if (xs == 0) {
+ /* Inputs are both positive */
+ if (xe > ye)
+ return y;
+ else if (xe < ye)
+ return x;
+ } else {
+ /* Inputs are both negative */
+ if (xe > ye)
+ return x;
+ else if (xe < ye)
+ return y;
+ }
- /* Compare mantissa */
+ /* Signs and exponents of inputs are equal, let's compare mantissas */
+ if (xs == 0) {
+ /* Inputs are both positive, with equal signs and exponents */
+ if (xm <= ym)
+ return x;
+ return y;
+ }
+ /* Inputs are both negative, with equal signs and exponents */
if (xm <= ym)
- return x;
- return y;
+ return y;
+ return x;
}
union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
@@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754dp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,25 +202,25 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
/*
* Infinity and zero handling
*/
+ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+ return ieee754dp_inf(xs | ys);
+
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
- return x;
+ return y;
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
- return y;
+ return x;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754dp_zero(1);
+ return ieee754dp_zero(xs | ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
DPDNORMX;
@@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y)
return x;
/* Compare mantissa */
- if (xm <= ym)
+ if (xm < ym)
+ return x;
+ else if (xm > ym)
+ return y;
+ else if (xs == 1)
return x;
return y;
}
diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c
index 4a2d03c72959..e0d9be5fbf4c 100644
--- a/arch/mips/math-emu/dp_maddf.c
+++ b/arch/mips/math-emu/dp_maddf.c
@@ -14,22 +14,45 @@
#include "ieee754dp.h"
-enum maddf_flags {
- maddf_negate_product = 1 << 0,
-};
+
+/* 128 bits shift right logical with rounding. */
+void srl128(u64 *hptr, u64 *lptr, int count)
+{
+ u64 low;
+
+ if (count >= 128) {
+ *lptr = *hptr != 0 || *lptr != 0;
+ *hptr = 0;
+ } else if (count >= 64) {
+ if (count == 64) {
+ *lptr = *hptr | (*lptr != 0);
+ } else {
+ low = *lptr;
+ *lptr = *hptr >> (count - 64);
+ *lptr |= (*hptr << (128 - count)) != 0 || low != 0;
+ }
+ *hptr = 0;
+ } else {
+ low = *lptr;
+ *lptr = low >> count | *hptr << (64 - count);
+ *lptr |= (low << (64 - count)) != 0;
+ *hptr = *hptr >> count;
+ }
+}
static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
union ieee754dp y, enum maddf_flags flags)
{
int re;
int rs;
- u64 rm;
unsigned lxm;
unsigned hxm;
unsigned lym;
unsigned hym;
u64 lrm;
u64 hrm;
+ u64 lzm;
+ u64 hzm;
u64 t;
u64 at;
int s;
@@ -48,52 +71,34 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
ieee754_clearcx();
- switch (zc) {
- case IEEE754_CLASS_SNAN:
- ieee754_setcx(IEEE754_INVALID_OPERATION);
+ /*
+ * Handle the cases when at least one of x, y or z is a NaN.
+ * Order of precedence is sNaN, qNaN and z, x, y.
+ */
+ if (zc == IEEE754_CLASS_SNAN)
return ieee754dp_nanxcpt(z);
- case IEEE754_CLASS_DNORM:
- DPDNORMZ;
- /* QNAN is handled separately below */
- }
-
- switch (CLPAIR(xc, yc)) {
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
- return ieee754dp_nanxcpt(y);
-
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
+ if (xc == IEEE754_CLASS_SNAN)
return ieee754dp_nanxcpt(x);
-
- case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
+ if (yc == IEEE754_CLASS_SNAN)
+ return ieee754dp_nanxcpt(y);
+ if (zc == IEEE754_CLASS_QNAN)
+ return z;
+ if (xc == IEEE754_CLASS_QNAN)
+ return x;
+ if (yc == IEEE754_CLASS_QNAN)
return y;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
- return x;
+ if (zc == IEEE754_CLASS_DNORM)
+ DPDNORMZ;
+ /* ZERO z cases are handled separately below */
+ switch (CLPAIR(xc, yc)) {
/*
* Infinity handling
*/
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
ieee754_setcx(IEEE754_INVALID_OPERATION);
return ieee754dp_indef();
@@ -102,9 +107,27 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- return ieee754dp_inf(xs ^ ys);
+ if ((zc == IEEE754_CLASS_INF) &&
+ ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) ||
+ ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) {
+ /*
+ * Cases of addition of infinities with opposite signs
+ * or subtraction of infinities with same signs.
+ */
+ ieee754_setcx(IEEE754_INVALID_OPERATION);
+ return ieee754dp_indef();
+ }
+ /*
+ * z is here either not an infinity, or an infinity having the
+ * same sign as product (x*y) (in case of MADDF.D instruction)
+ * or product -(x*y) (in MSUBF.D case). The result must be an
+ * infinity, and its sign is determined only by the value of
+ * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y.
+ */
+ if (flags & MADDF_NEGATE_PRODUCT)
+ return ieee754dp_inf(1 ^ (xs ^ ys));
+ else
+ return ieee754dp_inf(xs ^ ys);
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
@@ -113,32 +136,42 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
if (zc == IEEE754_CLASS_INF)
return ieee754dp_inf(zs);
- /* Multiplication is 0 so just return z */
+ if (zc == IEEE754_CLASS_ZERO) {
+ /* Handle cases +0 + (-0) and similar ones. */
+ if ((!(flags & MADDF_NEGATE_PRODUCT)
+ && (zs == (xs ^ ys))) ||
+ ((flags & MADDF_NEGATE_PRODUCT)
+ && (zs != (xs ^ ys))))
+ /*
+ * Cases of addition of zeros of equal signs
+ * or subtraction of zeroes of opposite signs.
+ * The sign of the resulting zero is in any
+ * such case determined only by the sign of z.
+ */
+ return z;
+
+ return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
+ }
+ /* x*y is here 0, and z is not 0, so just return z */
return z;
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
DPDNORMX;
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- else if (zc == IEEE754_CLASS_INF)
+ if (zc == IEEE754_CLASS_INF)
return ieee754dp_inf(zs);
DPDNORMY;
break;
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- else if (zc == IEEE754_CLASS_INF)
+ if (zc == IEEE754_CLASS_INF)
return ieee754dp_inf(zs);
DPDNORMX;
break;
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- else if (zc == IEEE754_CLASS_INF)
+ if (zc == IEEE754_CLASS_INF)
return ieee754dp_inf(zs);
/* fall through to real computations */
}
@@ -157,7 +190,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
re = xe + ye;
rs = xs ^ ys;
- if (flags & maddf_negate_product)
+ if (flags & MADDF_NEGATE_PRODUCT)
rs ^= 1;
/* shunt to top of word */
@@ -165,7 +198,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
ym <<= 64 - (DP_FBITS + 1);
/*
- * Multiply 64 bits xm, ym to give high 64 bits rm with stickness.
+ * Multiply 64 bits xm and ym to give 128 bits result in hrm:lrm.
*/
/* 32 * 32 => 64 */
@@ -195,78 +228,110 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
hrm = hrm + (t >> 32);
- rm = hrm | (lrm != 0);
-
- /*
- * Sticky shift down to normal rounding precision.
- */
- if ((s64) rm < 0) {
- rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
- ((rm << (DP_FBITS + 1 + 3)) != 0);
+ /* Put explicit bit at bit 126 if necessary */
+ if ((int64_t)hrm < 0) {
+ lrm = (hrm << 63) | (lrm >> 1);
+ hrm = hrm >> 1;
re++;
- } else {
- rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
- ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
}
- assert(rm & (DP_HIDDEN_BIT << 3));
- /* And now the addition */
- assert(zm & DP_HIDDEN_BIT);
+ assert(hrm & (1 << 62));
- /*
- * Provide guard,round and stick bit space.
- */
- zm <<= 3;
+ if (zc == IEEE754_CLASS_ZERO) {
+ /*
+ * Move explicit bit from bit 126 to bit 55 since the
+ * ieee754dp_format code expects the mantissa to be
+ * 56 bits wide (53 + 3 rounding bits).
+ */
+ srl128(&hrm, &lrm, (126 - 55));
+ return ieee754dp_format(rs, re, lrm);
+ }
+
+ /* Move explicit bit from bit 52 to bit 126 */
+ lzm = 0;
+ hzm = zm << 10;
+ assert(hzm & (1 << 62));
+ /* Make the exponents the same */
if (ze > re) {
/*
* Have to shift y fraction right to align.
*/
s = ze - re;
- rm = XDPSRS(rm, s);
+ srl128(&hrm, &lrm, s);
re += s;
} else if (re > ze) {
/*
* Have to shift x fraction right to align.
*/
s = re - ze;
- zm = XDPSRS(zm, s);
+ srl128(&hzm, &lzm, s);
ze += s;
}
assert(ze == re);
assert(ze <= DP_EMAX);
+ /* Do the addition */
if (zs == rs) {
/*
- * Generate 28 bit result of adding two 27 bit numbers
- * leaving result in xm, xs and xe.
+ * Generate 128 bit result by adding two 127 bit numbers
+ * leaving result in hzm:lzm, zs and ze.
*/
- zm = zm + rm;
-
- if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */
- zm = XDPSRS1(zm);
+ hzm = hzm + hrm + (lzm > (lzm + lrm));
+ lzm = lzm + lrm;
+ if ((int64_t)hzm < 0) { /* carry out */
+ srl128(&hzm, &lzm, 1);
ze++;
}
} else {
- if (zm >= rm) {
- zm = zm - rm;
+ if (hzm > hrm || (hzm == hrm && lzm >= lrm)) {
+ hzm = hzm - hrm - (lzm < lrm);
+ lzm = lzm - lrm;
} else {
- zm = rm - zm;
+ hzm = hrm - hzm - (lrm < lzm);
+ lzm = lrm - lzm;
zs = rs;
}
- if (zm == 0)
+ if (lzm == 0 && hzm == 0)
return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
/*
- * Normalize to rounding precision.
+ * Put explicit bit at bit 126 if necessary.
*/
- while ((zm >> (DP_FBITS + 3)) == 0) {
- zm <<= 1;
- ze--;
+ if (hzm == 0) {
+ /* left shift by 63 or 64 bits */
+ if ((int64_t)lzm < 0) {
+ /* MSB of lzm is the explicit bit */
+ hzm = lzm >> 1;
+ lzm = lzm << 63;
+ ze -= 63;
+ } else {
+ hzm = lzm;
+ lzm = 0;
+ ze -= 64;
+ }
+ }
+
+ t = 0;
+ while ((hzm >> (62 - t)) == 0)
+ t++;
+
+ assert(t <= 62);
+ if (t) {
+ hzm = hzm << t | lzm >> (64 - t);
+ lzm = lzm << t;
+ ze -= t;
}
}
- return ieee754dp_format(zs, ze, zm);
+ /*
+ * Move explicit bit from bit 126 to bit 55 since the
+ * ieee754dp_format code expects the mantissa to be
+ * 56 bits wide (53 + 3 rounding bits).
+ */
+ srl128(&hzm, &lzm, (126 - 55));
+
+ return ieee754dp_format(zs, ze, lzm);
}
union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
@@ -278,5 +343,5 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
union ieee754dp y)
{
- return _dp_maddf(z, x, y, maddf_negate_product);
+ return _dp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
}
diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h
index 8bc2f6963324..dd2071f430e0 100644
--- a/arch/mips/math-emu/ieee754int.h
+++ b/arch/mips/math-emu/ieee754int.h
@@ -26,6 +26,10 @@
#define CLPAIR(x, y) ((x)*6+(y))
+enum maddf_flags {
+ MADDF_NEGATE_PRODUCT = 1 << 0,
+};
+
static inline void ieee754_clearcx(void)
{
ieee754_csr.cx = 0;
diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h
index 8476067075fe..0f63e4202cff 100644
--- a/arch/mips/math-emu/ieee754sp.h
+++ b/arch/mips/math-emu/ieee754sp.h
@@ -45,6 +45,10 @@ static inline int ieee754sp_finite(union ieee754sp x)
return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS;
}
+/* 64 bit right shift with rounding */
+#define XSPSRS64(v, rs) \
+ (((rs) >= 64) ? ((v) != 0) : ((v) >> (rs)) | ((v) << (64-(rs)) != 0))
+
/* 3bit extended single precision sticky right shift */
#define XSPSRS(v, rs) \
((rs > (SP_FBITS+3))?1:((v) >> (rs)) | ((v) << (32-(rs)) != 0))
diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c
index 4d000844e48e..74a5a00d2f22 100644
--- a/arch/mips/math-emu/sp_fmax.c
+++ b/arch/mips/math-emu/sp_fmax.c
@@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754sp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
return ys ? x : y;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754sp_zero(1);
+ return ieee754sp_zero(xs & ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
SPDNORMX;
@@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y)
else if (xs < ys)
return x;
- /* Compare exponent */
- if (xe > ye)
- return x;
- else if (xe < ye)
- return y;
+ /* Signs of inputs are equal, let's compare exponents */
+ if (xs == 0) {
+ /* Inputs are both positive */
+ if (xe > ye)
+ return x;
+ else if (xe < ye)
+ return y;
+ } else {
+ /* Inputs are both negative */
+ if (xe > ye)
+ return y;
+ else if (xe < ye)
+ return x;
+ }
- /* Compare mantissa */
+ /* Signs and exponents of inputs are equal, let's compare mantissas */
+ if (xs == 0) {
+ /* Inputs are both positive, with equal signs and exponents */
+ if (xm <= ym)
+ return y;
+ return x;
+ }
+ /* Inputs are both negative, with equal signs and exponents */
if (xm <= ym)
- return y;
- return x;
+ return x;
+ return y;
}
union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
@@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754sp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,6 +202,9 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
/*
* Infinity and zero handling
*/
+ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+ return ieee754sp_inf(xs & ys);
+
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
@@ -171,7 +212,6 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
return x;
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -180,9 +220,7 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
return y;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754sp_zero(1);
+ return ieee754sp_zero(xs & ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
SPDNORMX;
@@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y)
return y;
/* Compare mantissa */
- if (xm <= ym)
+ if (xm < ym)
return y;
- return x;
+ else if (xm > ym)
+ return x;
+ else if (xs == 0)
+ return x;
+ return y;
}
diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c
index 4eb1bb9e9dec..c51385f46b09 100644
--- a/arch/mips/math-emu/sp_fmin.c
+++ b/arch/mips/math-emu/sp_fmin.c
@@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754sp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
return ys ? y : x;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754sp_zero(1);
+ return ieee754sp_zero(xs | ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
SPDNORMX;
@@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y)
else if (xs < ys)
return y;
- /* Compare exponent */
- if (xe > ye)
- return y;
- else if (xe < ye)
- return x;
+ /* Signs of inputs are the same, let's compare exponents */
+ if (xs == 0) {
+ /* Inputs are both positive */
+ if (xe > ye)
+ return y;
+ else if (xe < ye)
+ return x;
+ } else {
+ /* Inputs are both negative */
+ if (xe > ye)
+ return x;
+ else if (xe < ye)
+ return y;
+ }
- /* Compare mantissa */
+ /* Signs and exponents of inputs are equal, let's compare mantissas */
+ if (xs == 0) {
+ /* Inputs are both positive, with equal signs and exponents */
+ if (xm <= ym)
+ return x;
+ return y;
+ }
+ /* Inputs are both negative, with equal signs and exponents */
if (xm <= ym)
- return x;
- return y;
+ return y;
+ return x;
}
union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
@@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
return ieee754sp_nanxcpt(x);
- /* numbers are preferred to NaNs */
+ /*
+ * Quiet NaN handling
+ */
+
+ /*
+ * The case of both inputs quiet NaNs
+ */
+ case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
+ return x;
+
+ /*
+ * The cases of exactly one input quiet NaN (numbers
+ * are here preferred as returned values to NaNs)
+ */
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
return x;
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
@@ -164,25 +202,25 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
/*
* Infinity and zero handling
*/
+ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
+ return ieee754sp_inf(xs | ys);
+
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
- return x;
+ return y;
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
- return y;
+ return x;
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
- if (xs == ys)
- return x;
- return ieee754sp_zero(1);
+ return ieee754sp_zero(xs | ys);
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
SPDNORMX;
@@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y)
return x;
/* Compare mantissa */
- if (xm <= ym)
+ if (xm < ym)
+ return x;
+ else if (xm > ym)
+ return y;
+ else if (xs == 1)
return x;
return y;
}
diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c
index a8cd8b4f235e..7195fe785d81 100644
--- a/arch/mips/math-emu/sp_maddf.c
+++ b/arch/mips/math-emu/sp_maddf.c
@@ -14,9 +14,6 @@
#include "ieee754sp.h"
-enum maddf_flags {
- maddf_negate_product = 1 << 0,
-};
static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
union ieee754sp y, enum maddf_flags flags)
@@ -24,14 +21,8 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
int re;
int rs;
unsigned rm;
- unsigned short lxm;
- unsigned short hxm;
- unsigned short lym;
- unsigned short hym;
- unsigned lrm;
- unsigned hrm;
- unsigned t;
- unsigned at;
+ uint64_t rm64;
+ uint64_t zm64;
int s;
COMPXSP;
@@ -48,51 +39,35 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
ieee754_clearcx();
- switch (zc) {
- case IEEE754_CLASS_SNAN:
- ieee754_setcx(IEEE754_INVALID_OPERATION);
+ /*
+ * Handle the cases when at least one of x, y or z is a NaN.
+ * Order of precedence is sNaN, qNaN and z, x, y.
+ */
+ if (zc == IEEE754_CLASS_SNAN)
return ieee754sp_nanxcpt(z);
- case IEEE754_CLASS_DNORM:
- SPDNORMZ;
- /* QNAN is handled separately below */
- }
-
- switch (CLPAIR(xc, yc)) {
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN):
+ if (xc == IEEE754_CLASS_SNAN)
+ return ieee754sp_nanxcpt(x);
+ if (yc == IEEE754_CLASS_SNAN)
return ieee754sp_nanxcpt(y);
+ if (zc == IEEE754_CLASS_QNAN)
+ return z;
+ if (xc == IEEE754_CLASS_QNAN)
+ return x;
+ if (yc == IEEE754_CLASS_QNAN)
+ return y;
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
- case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
- return ieee754sp_nanxcpt(x);
+ if (zc == IEEE754_CLASS_DNORM)
+ SPDNORMZ;
+ /* ZERO z cases are handled separately below */
- case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN):
- return y;
+ switch (CLPAIR(xc, yc)) {
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM):
- case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF):
- return x;
/*
* Infinity handling
*/
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
ieee754_setcx(IEEE754_INVALID_OPERATION);
return ieee754sp_indef();
@@ -101,9 +76,27 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- return ieee754sp_inf(xs ^ ys);
+ if ((zc == IEEE754_CLASS_INF) &&
+ ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) ||
+ ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) {
+ /*
+ * Cases of addition of infinities with opposite signs
+ * or subtraction of infinities with same signs.
+ */
+ ieee754_setcx(IEEE754_INVALID_OPERATION);
+ return ieee754sp_indef();
+ }
+ /*
+ * z is here either not an infinity, or an infinity having the
+ * same sign as product (x*y) (in case of MADDF.D instruction)
+ * or product -(x*y) (in MSUBF.D case). The result must be an
+ * infinity, and its sign is determined only by the value of
+ * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y.
+ */
+ if (flags & MADDF_NEGATE_PRODUCT)
+ return ieee754sp_inf(1 ^ (xs ^ ys));
+ else
+ return ieee754sp_inf(xs ^ ys);
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
@@ -112,32 +105,42 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
if (zc == IEEE754_CLASS_INF)
return ieee754sp_inf(zs);
- /* Multiplication is 0 so just return z */
+ if (zc == IEEE754_CLASS_ZERO) {
+ /* Handle cases +0 + (-0) and similar ones. */
+ if ((!(flags & MADDF_NEGATE_PRODUCT)
+ && (zs == (xs ^ ys))) ||
+ ((flags & MADDF_NEGATE_PRODUCT)
+ && (zs != (xs ^ ys))))
+ /*
+ * Cases of addition of zeros of equal signs
+ * or subtraction of zeroes of opposite signs.
+ * The sign of the resulting zero is in any
+ * such case determined only by the sign of z.
+ */
+ return z;
+
+ return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
+ }
+ /* x*y is here 0, and z is not 0, so just return z */
return z;
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
SPDNORMX;
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- else if (zc == IEEE754_CLASS_INF)
+ if (zc == IEEE754_CLASS_INF)
return ieee754sp_inf(zs);
SPDNORMY;
break;
case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- else if (zc == IEEE754_CLASS_INF)
+ if (zc == IEEE754_CLASS_INF)
return ieee754sp_inf(zs);
SPDNORMX;
break;
case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM):
- if (zc == IEEE754_CLASS_QNAN)
- return z;
- else if (zc == IEEE754_CLASS_INF)
+ if (zc == IEEE754_CLASS_INF)
return ieee754sp_inf(zs);
/* fall through to real computations */
}
@@ -158,108 +161,93 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
re = xe + ye;
rs = xs ^ ys;
- if (flags & maddf_negate_product)
+ if (flags & MADDF_NEGATE_PRODUCT)
rs ^= 1;
- /* shunt to top of word */
- xm <<= 32 - (SP_FBITS + 1);
- ym <<= 32 - (SP_FBITS + 1);
-
- /*
- * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
- */
- lxm = xm & 0xffff;
- hxm = xm >> 16;
- lym = ym & 0xffff;
- hym = ym >> 16;
-
- lrm = lxm * lym; /* 16 * 16 => 32 */
- hrm = hxm * hym; /* 16 * 16 => 32 */
+ /* Multiple 24 bit xm and ym to give 48 bit results */
+ rm64 = (uint64_t)xm * ym;
- t = lxm * hym; /* 16 * 16 => 32 */
- at = lrm + (t << 16);
- hrm += at < lrm;
- lrm = at;
- hrm = hrm + (t >> 16);
+ /* Shunt to top of word */
+ rm64 = rm64 << 16;
- t = hxm * lym; /* 16 * 16 => 32 */
- at = lrm + (t << 16);
- hrm += at < lrm;
- lrm = at;
- hrm = hrm + (t >> 16);
-
- rm = hrm | (lrm != 0);
-
- /*
- * Sticky shift down to normal rounding precision.
- */
- if ((int) rm < 0) {
- rm = (rm >> (32 - (SP_FBITS + 1 + 3))) |
- ((rm << (SP_FBITS + 1 + 3)) != 0);
+ /* Put explicit bit at bit 62 if necessary */
+ if ((int64_t) rm64 < 0) {
+ rm64 = rm64 >> 1;
re++;
- } else {
- rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) |
- ((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
}
- assert(rm & (SP_HIDDEN_BIT << 3));
- /* And now the addition */
+ assert(rm64 & (1 << 62));
- assert(zm & SP_HIDDEN_BIT);
+ if (zc == IEEE754_CLASS_ZERO) {
+ /*
+ * Move explicit bit from bit 62 to bit 26 since the
+ * ieee754sp_format code expects the mantissa to be
+ * 27 bits wide (24 + 3 rounding bits).
+ */
+ rm = XSPSRS64(rm64, (62 - 26));
+ return ieee754sp_format(rs, re, rm);
+ }
- /*
- * Provide guard,round and stick bit space.
- */
- zm <<= 3;
+ /* Move explicit bit from bit 23 to bit 62 */
+ zm64 = (uint64_t)zm << (62 - 23);
+ assert(zm64 & (1 << 62));
+ /* Make the exponents the same */
if (ze > re) {
/*
* Have to shift r fraction right to align.
*/
s = ze - re;
- rm = XSPSRS(rm, s);
+ rm64 = XSPSRS64(rm64, s);
re += s;
} else if (re > ze) {
/*
* Have to shift z fraction right to align.
*/
s = re - ze;
- zm = XSPSRS(zm, s);
+ zm64 = XSPSRS64(zm64, s);
ze += s;
}
assert(ze == re);
assert(ze <= SP_EMAX);
+ /* Do the addition */
if (zs == rs) {
/*
- * Generate 28 bit result of adding two 27 bit numbers
- * leaving result in zm, zs and ze.
+ * Generate 64 bit result by adding two 63 bit numbers
+ * leaving result in zm64, zs and ze.
*/
- zm = zm + rm;
-
- if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */
- zm = XSPSRS1(zm);
+ zm64 = zm64 + rm64;
+ if ((int64_t)zm64 < 0) { /* carry out */
+ zm64 = XSPSRS1(zm64);
ze++;
}
} else {
- if (zm >= rm) {
- zm = zm - rm;
+ if (zm64 >= rm64) {
+ zm64 = zm64 - rm64;
} else {
- zm = rm - zm;
+ zm64 = rm64 - zm64;
zs = rs;
}
- if (zm == 0)
+ if (zm64 == 0)
return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
/*
- * Normalize in extended single precision
+ * Put explicit bit at bit 62 if necessary.
*/
- while ((zm >> (SP_MBITS + 3)) == 0) {
- zm <<= 1;
+ while ((zm64 >> 62) == 0) {
+ zm64 <<= 1;
ze--;
}
-
}
+
+ /*
+ * Move explicit bit from bit 62 to bit 26 since the
+ * ieee754sp_format code expects the mantissa to be
+ * 27 bits wide (24 + 3 rounding bits).
+ */
+ zm = XSPSRS64(zm64, (62 - 26));
+
return ieee754sp_format(zs, ze, zm);
}
@@ -272,5 +260,5 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
union ieee754sp y)
{
- return _sp_maddf(z, x, y, maddf_negate_product);
+ return _sp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
}
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index 3c7c9bf57bf3..6f892c1f3ad7 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -176,7 +176,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = {
static struct rt2880_pmx_func spis_grp_mt7628[] = {
FUNC("pwm_uart2", 3, 14, 4),
- FUNC("util", 2, 14, 4),
+ FUNC("utif", 2, 14, 4),
FUNC("gpio", 1, 14, 4),
FUNC("spis", 0, 14, 4),
};
@@ -190,28 +190,28 @@ static struct rt2880_pmx_func gpio_grp_mt7628[] = {
static struct rt2880_pmx_func p4led_kn_grp_mt7628[] = {
FUNC("jtag", 3, 30, 1),
- FUNC("util", 2, 30, 1),
+ FUNC("utif", 2, 30, 1),
FUNC("gpio", 1, 30, 1),
FUNC("p4led_kn", 0, 30, 1),
};
static struct rt2880_pmx_func p3led_kn_grp_mt7628[] = {
FUNC("jtag", 3, 31, 1),
- FUNC("util", 2, 31, 1),
+ FUNC("utif", 2, 31, 1),
FUNC("gpio", 1, 31, 1),
FUNC("p3led_kn", 0, 31, 1),
};
static struct rt2880_pmx_func p2led_kn_grp_mt7628[] = {
FUNC("jtag", 3, 32, 1),
- FUNC("util", 2, 32, 1),
+ FUNC("utif", 2, 32, 1),
FUNC("gpio", 1, 32, 1),
FUNC("p2led_kn", 0, 32, 1),
};
static struct rt2880_pmx_func p1led_kn_grp_mt7628[] = {
FUNC("jtag", 3, 33, 1),
- FUNC("util", 2, 33, 1),
+ FUNC("utif", 2, 33, 1),
FUNC("gpio", 1, 33, 1),
FUNC("p1led_kn", 0, 33, 1),
};
@@ -232,28 +232,28 @@ static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
static struct rt2880_pmx_func p4led_an_grp_mt7628[] = {
FUNC("jtag", 3, 39, 1),
- FUNC("util", 2, 39, 1),
+ FUNC("utif", 2, 39, 1),
FUNC("gpio", 1, 39, 1),
FUNC("p4led_an", 0, 39, 1),
};
static struct rt2880_pmx_func p3led_an_grp_mt7628[] = {
FUNC("jtag", 3, 40, 1),
- FUNC("util", 2, 40, 1),
+ FUNC("utif", 2, 40, 1),
FUNC("gpio", 1, 40, 1),
FUNC("p3led_an", 0, 40, 1),
};
static struct rt2880_pmx_func p2led_an_grp_mt7628[] = {
FUNC("jtag", 3, 41, 1),
- FUNC("util", 2, 41, 1),
+ FUNC("utif", 2, 41, 1),
FUNC("gpio", 1, 41, 1),
FUNC("p2led_an", 0, 41, 1),
};
static struct rt2880_pmx_func p1led_an_grp_mt7628[] = {
FUNC("jtag", 3, 42, 1),
- FUNC("util", 2, 42, 1),
+ FUNC("utif", 2, 42, 1),
FUNC("gpio", 1, 42, 1),
FUNC("p1led_an", 0, 42, 1),
};
diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c
index 9e4631acfcb5..3e68e35daf21 100644
--- a/arch/mips/ralink/rt3883.c
+++ b/arch/mips/ralink/rt3883.c
@@ -145,5 +145,5 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
rt2880_pinmux_data = rt3883_pinmux_data;
- ralink_soc == RT3883_SOC;
+ ralink_soc = RT3883_SOC;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-20 00:31:51 +0000