Merge tag 'asm-generic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic

Pull asm-generic updates from Arnd Bergmann:
 "The asm-generic tree this time contains one series from Nicolas Pitre
  that makes the optimized do_div() implementation from the ARM
  architecture available to all architectures.

  This also adds stricter type checking for callers of do_div, which has
  uncovered a number of bugs in existing code, and fixes up the ones we
  have found"

* tag 'asm-generic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic:
  ARM: asm/div64.h: adjust to generic codde
  __div64_32(): make it overridable at compile time
  __div64_const32(): abstract out the actual 128-bit cross product code
  do_div(): generic optimization for constant divisor on 32-bit machines
  div64.h: optimize do_div() for power-of-two constant divisors
  mtd/sm_ftl.c: fix wrong do_div() usage
  drm/mgag200/mgag200_mode.c: fix wrong do_div() usage
  hid-sensor-hub.c: fix wrong do_div() usage
  ti/fapll: fix wrong do_div() usage
  ti/clkt_dpll: fix wrong do_div() usage
  tegra/clk-divider: fix wrong do_div() usage
  imx/clk-pllv2: fix wrong do_div() usage
  imx/clk-pllv1: fix wrong do_div() usage
  nouveau/nvkm/subdev/clk/gk20a.c: fix wrong do_div() usage

drivers/clk/tegra/clk-divider.c

@@ -32,7 +32,7 @@
 static int get_div(struct tegra_clk_frac_div *divider, unsigned long rate,
 		   unsigned long parent_rate)
 {
-	s64 divider_ux1 = parent_rate;
+	u64 divider_ux1 = parent_rate;
 	u8 flags = divider->flags;
 	int mul;
 
@@ -54,7 +54,7 @@ static int get_div(struct tegra_clk_frac_div *divider, unsigned long rate,
 
 	divider_ux1 -= mul;
 
-	if (divider_ux1 < 0)
+	if ((s64)divider_ux1 < 0)
 		return 0;
 
 	if (divider_ux1 > get_max_div(divider))

drivers/gpu/drm/mgag200/mgag200_mode.c

@@ -1564,7 +1564,7 @@ static uint32_t mga_vga_calculate_mode_bandwidth(struct drm_display_mode *mode,
 							int bits_per_pixel)
 {
 	uint32_t total_area, divisor;
-	int64_t active_area, pixels_per_second, bandwidth;
+	uint64_t active_area, pixels_per_second, bandwidth;
 	uint64_t bytes_per_pixel = (bits_per_pixel + 7) / 8;
 
 	divisor = 1024;

drivers/gpu/drm/nouveau/nvkm/subdev/clk/gk20a.c

@@ -141,9 +141,8 @@ gk20a_pllg_calc_rate(struct gk20a_clk *clk)
 
 	rate = clk->parent_rate * clk->n;
 	divider = clk->m * pl_to_div[clk->pl];
-	do_div(rate, divider);
 
-	return rate / 2;
+	return rate / divider / 2;
 }
 
 static int

drivers/hid/hid-sensor-hub.c

@@ -218,7 +218,8 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id,
 		goto done_proc;
 	}
 
-	remaining_bytes = do_div(buffer_size, sizeof(__s32));
+	remaining_bytes = buffer_size % sizeof(__s32);
+	buffer_size = buffer_size / sizeof(__s32);
 	if (buffer_size) {
 		for (i = 0; i < buffer_size; ++i) {
 			hid_set_field(report->field[field_index], i,

include/asm-generic/div64.h

@@ -4,6 +4,9 @@
  * Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
  * Based on former asm-ppc/div64.h and asm-m68knommu/div64.h
  *
+ * Optimization for constant divisors on 32-bit machines:
+ * Copyright (C) 2006-2015 Nicolas Pitre
+ *
  * The semantics of do_div() are:
  *
  * uint32_t do_div(uint64_t *n, uint32_t base)
@@ -32,7 +35,168 @@
 
 #elif BITS_PER_LONG == 32
 
+#include <linux/log2.h>
+
+/*
+ * If the divisor happens to be constant, we determine the appropriate
+ * inverse at compile time to turn the division into a few inline
+ * multiplications which ought to be much faster. And yet only if compiling
+ * with a sufficiently recent gcc version to perform proper 64-bit constant
+ * propagation.
+ *
+ * (It is unfortunate that gcc doesn't perform all this internally.)
+ */
+
+#ifndef __div64_const32_is_OK
+#define __div64_const32_is_OK (__GNUC__ >= 4)
+#endif
+
+#define __div64_const32(n, ___b)					\
+({									\
+	/*								\
+	 * Multiplication by reciprocal of b: n / b = n * (p / b) / p	\
+	 *								\
+	 * We rely on the fact that most of this code gets optimized	\
+	 * away at compile time due to constant propagation and only	\
+	 * a few multiplication instructions should remain.		\
+	 * Hence this monstrous macro (static inline doesn't always	\
+	 * do the trick here).						\
+	 */								\
+	uint64_t ___res, ___x, ___t, ___m, ___n = (n);			\
+	uint32_t ___p, ___bias;						\
+									\
+	/* determine MSB of b */					\
+	___p = 1 << ilog2(___b);					\
+									\
+	/* compute m = ((p << 64) + b - 1) / b */			\
+	___m = (~0ULL / ___b) * ___p;					\
+	___m += (((~0ULL % ___b + 1) * ___p) + ___b - 1) / ___b;	\
+									\
+	/* one less than the dividend with highest result */		\
+	___x = ~0ULL / ___b * ___b - 1;					\
+									\
+	/* test our ___m with res = m * x / (p << 64) */		\
+	___res = ((___m & 0xffffffff) * (___x & 0xffffffff)) >> 32;	\
+	___t = ___res += (___m & 0xffffffff) * (___x >> 32);		\
+	___res += (___x & 0xffffffff) * (___m >> 32);			\
+	___t = (___res < ___t) ? (1ULL << 32) : 0;			\
+	___res = (___res >> 32) + ___t;					\
+	___res += (___m >> 32) * (___x >> 32);				\
+	___res /= ___p;							\
+									\
+	/* Now sanitize and optimize what we've got. */			\
+	if (~0ULL % (___b / (___b & -___b)) == 0) {			\
+		/* special case, can be simplified to ... */		\
+		___n /= (___b & -___b);					\
+		___m = ~0ULL / (___b / (___b & -___b));			\
+		___p = 1;						\
+		___bias = 1;						\
+	} else if (___res != ___x / ___b) {				\
+		/*							\
+		 * We can't get away without a bias to compensate	\
+		 * for bit truncation errors.  To avoid it we'd need an	\
+		 * additional bit to represent m which would overflow	\
+		 * a 64-bit variable.					\
+		 *							\
+		 * Instead we do m = p / b and n / b = (n * m + m) / p.	\
+		 */							\
+		___bias = 1;						\
+		/* Compute m = (p << 64) / b */				\
+		___m = (~0ULL / ___b) * ___p;				\
+		___m += ((~0ULL % ___b + 1) * ___p) / ___b;		\
+	} else {							\
+		/*							\
+		 * Reduce m / p, and try to clear bit 31 of m when	\
+		 * possible, otherwise that'll need extra overflow	\
+		 * handling later.					\
+		 */							\
+		uint32_t ___bits = -(___m & -___m);			\
+		___bits |= ___m >> 32;					\
+		___bits = (~___bits) << 1;				\
+		/*							\
+		 * If ___bits == 0 then setting bit 31 is  unavoidable.	\
+		 * Simply apply the maximum possible reduction in that	\
+		 * case. Otherwise the MSB of ___bits indicates the	\
+		 * best reduction we should apply.			\
+		 */							\
+		if (!___bits) {						\
+			___p /= (___m & -___m);				\
+			___m /= (___m & -___m);				\
+		} else {						\
+			___p >>= ilog2(___bits);			\
+			___m >>= ilog2(___bits);			\
+		}							\
+		/* No bias needed. */					\
+		___bias = 0;						\
+	}								\
+									\
+	/*								\
+	 * Now we have a combination of 2 conditions:			\
+	 *								\
+	 * 1) whether or not we need to apply a bias, and		\
+	 *								\
+	 * 2) whether or not there might be an overflow in the cross	\
+	 *    product determined by (___m & ((1 << 63) | (1 << 31))).	\
+	 *								\
+	 * Select the best way to do (m_bias + m * n) / (1 << 64).	\
+	 * From now on there will be actual runtime code generated.	\
+	 */								\
+	___res = __arch_xprod_64(___m, ___n, ___bias);			\
+									\
+	___res /= ___p;							\
+})
+
+#ifndef __arch_xprod_64
+/*
+ * Default C implementation for __arch_xprod_64()
+ *
+ * Prototype: uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
+ * Semantic:  retval = ((bias ? m : 0) + m * n) >> 64
+ *
+ * The product is a 128-bit value, scaled down to 64 bits.
+ * Assuming constant propagation to optimize away unused conditional code.
+ * Architectures may provide their own optimized assembly implementation.
+ */
+static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
+{
+	uint32_t m_lo = m;
+	uint32_t m_hi = m >> 32;
+	uint32_t n_lo = n;
+	uint32_t n_hi = n >> 32;
+	uint64_t res, tmp;
+
+	if (!bias) {
+		res = ((uint64_t)m_lo * n_lo) >> 32;
+	} else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+		/* there can't be any overflow here */
+		res = (m + (uint64_t)m_lo * n_lo) >> 32;
+	} else {
+		res = m + (uint64_t)m_lo * n_lo;
+		tmp = (res < m) ? (1ULL << 32) : 0;
+		res = (res >> 32) + tmp;
+	}
+
+	if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+		/* there can't be any overflow here */
+		res += (uint64_t)m_lo * n_hi;
+		res += (uint64_t)m_hi * n_lo;
+		res >>= 32;
+	} else {
+		tmp = res += (uint64_t)m_lo * n_hi;
+		res += (uint64_t)m_hi * n_lo;
+		tmp = (res < tmp) ? (1ULL << 32) : 0;
+		res = (res >> 32) + tmp;
+	}
+
+	res += (uint64_t)m_hi * n_hi;
+
+	return res;
+}
+#endif
+
+#ifndef __div64_32
 extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
+#endif
 
 /* The unnecessary pointer compare is there
  * to check for type safety (n must be 64bit)
@@ -41,7 +205,19 @@ extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
 	uint32_t __base = (base);			\
 	uint32_t __rem;					\
 	(void)(((typeof((n)) *)0) == ((uint64_t *)0));	\
-	if (likely(((n) >> 32) == 0)) {			\
+	if (__builtin_constant_p(__base) &&		\
+	    is_power_of_2(__base)) {			\
+		__rem = (n) & (__base - 1);		\
+		(n) >>= ilog2(__base);			\
+	} else if (__div64_const32_is_OK &&		\
+		   __builtin_constant_p(__base) &&	\
+		   __base != 0) {			\
+		uint32_t __res_lo, __n_lo = (n);	\
+		(n) = __div64_const32(n, __base);	\
+		/* the remainder can be computed with 32-bit regs */ \
+		__res_lo = (n);				\
+		__rem = __n_lo - __res_lo * __base;	\
+	} else if (likely(((n) >> 32) == 0)) {		\
 		__rem = (uint32_t)(n) % __base;		\
 		(n) = (uint32_t)(n) / __base;		\
 	} else 						\

lib/div64.c

@@ -13,7 +13,8 @@
  *
  * Code generated for this function might be very inefficient
  * for some CPUs. __div64_32() can be overridden by linking arch-specific
- * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
+ * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S
+ * or by defining a preprocessor macro in arch/include/asm/div64.h.
  */
 
 #include <linux/export.h>
@@ -23,6 +24,7 @@
 /* Not needed on 64bit architectures */
 #if BITS_PER_LONG == 32
 
+#ifndef __div64_32
 uint32_t __attribute__((weak)) __div64_32(uint64_t *n, uint32_t base)
 {
 	uint64_t rem = *n;
@@ -55,8 +57,8 @@ uint32_t __attribute__((weak)) __div64_32(uint64_t *n, uint32_t base)
 	*n = res;
 	return rem;
 }
-
 EXPORT_SYMBOL(__div64_32);
+#endif
 
 #ifndef div_s64_rem
 s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)