Merge tag 'pinctrl-v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrlgrafted

Pull pin control updates from Linus Walleij:
 "Core changes:

   - Use the non-blocking mux_state_try_select() in the generic MUX pin
     control back-end

   - Free pin maps on pinctrl_generic_to_map() failure in the core
     helpers

  New hardware pin control:

   - Qualcomm Maili TLMM SoC, PMG1110 PMIC, and Eliza LPASS LPI TLMM SoC
     (this is for the low power audio, LPASS = Low Power Audio SubSystem
     portions)

   - Upboard support on top of the Intel pin controller

   - Apple T6030 and T6031 support (just compatible strings)

   - Samsung Exynos 8855 SoC

   - Mediatek MT6858 SoC

   - Rockchip RK3308B and RV1106 SoCs

   - Airoha EN7523 and AN7563 SoCs

  Improvements:

   - Qualcomm TLMM GPIOs are unconditionally marked as wakeup capable

   - Qualcomm improvements on top of the Qualcomm PDC (power domain
     controller) irqchip improvements from tglx:s tree

   - Qualcomm IPQ806x and IPQ9650 non-urgent pin grop fixups

   - The NPCM8xx driver has been put into shape fixing many pin and
     group definitions

   - Some non-urgent Tegra 264 pin assignments are fixed up

   - Some non-urgent fixups to Airoha AN7581 and AN7583 registers and
     pin assignments, missing features etc"

* tag 'pinctrl-v7.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl: (130 commits)
  dt-bindings: pinctrl: Convert TI DA850 pupd to DT schema
  pinctrl: meson: sync some modify from A4
  pinctrl: meson: a4: Add input enable pin configuration
  pinctrl: realtek: rtd1625: remove unused group name spdif_sel
  pinctrl: realtek: rtd1625: fix base_bit for VE4 GPIO 13
  dt-bindings: pinctrl: microchip,pic32mzda-pinctrl: Convert to DT schema
  Revert "Merge branch 'ib-rsk7204' into devel"
  pinctrl: rockchip: Add RV1106 pinctrl support
  dt-bindings: pinctrl: rockchip: Add RV1106 compatible
  pinctrl: rockchip: Decode drive strength in the get function
  pinctrl: fix PINCTRL_GENERIC_MUX not always being selectable
  pinctrl: airoha: add support of an7563 SoC
  dt-bindings: pinctrl: airoha: add support of an7563 pin controller
  pinctrl: airoha: try to find chip scu node by phandle first
  pinctrl: airoha: add support of en7523 SoC
  dt-bindings: pinctrl: airoha: add support of en7523 pin controller
  pinctrl: airoha: an7583: add support for olt pinmux
  pinctrl: airoha: an7583: add support for pon_alt pinmux
  pinctrl: airoha: an7583: add support for npu_uart pinmux
  dt-bindings: pinctrl: airoha: an7583: add missed features
  ...

1 files changed, 157 insertions, 0 deletions

diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c
new file mode 100644
index 000000000..2432683e4
--- /dev/null
+++ b/arch/arm64/lib/csum.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 Arm Ltd.
+
+#include <linux/compiler.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <net/checksum.h>
+
+/* Looks dumb, but generates nice-ish code */
+static u64 accumulate(u64 sum, u64 data)
+{
+	__uint128_t tmp = (__uint128_t)sum + data;
+	return tmp + (tmp >> 64);
+}
+
+/*
+ * We over-read the buffer and this makes KASAN unhappy. Instead, disable
+ * instrumentation and call kasan explicitly.
+ */
+unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift, sum;
+	const u64 *ptr;
+	u64 data, sum64 = 0;
+
+	if (unlikely(len <= 0))
+		return 0;
+
+	offset = (unsigned long)buff & 7;
+	/*
+	 * This is to all intents and purposes safe, since rounding down cannot
+	 * result in a different page or cache line being accessed, and @buff
+	 * should absolutely not be pointing to anything read-sensitive. We do,
+	 * however, have to be careful not to piss off KASAN, which means using
+	 * unchecked reads to accommodate the head and tail, for which we'll
+	 * compensate with an explicit check up-front.
+	 */
+	kasan_check_read(buff, len);
+	ptr = (u64 *)(buff - offset);
+	len = len + offset - 8;
+
+	/*
+	 * Head: zero out any excess leading bytes. Shifting back by the same
+	 * amount should be at least as fast as any other way of handling the
+	 * odd/even alignment, and means we can ignore it until the very end.
+	 */
+	shift = offset * 8;
+	data = *ptr++;
+#ifdef __LITTLE_ENDIAN
+	data = (data >> shift) << shift;
+#else
+	data = (data << shift) >> shift;
+#endif
+
+	/*
+	 * Body: straightforward aligned loads from here on (the paired loads
+	 * underlying the quadword type still only need dword alignment). The
+	 * main loop strictly excludes the tail, so the second loop will always
+	 * run at least once.
+	 */
+	while (unlikely(len > 64)) {
+		__uint128_t tmp1, tmp2, tmp3, tmp4;
+
+		tmp1 = *(__uint128_t *)ptr;
+		tmp2 = *(__uint128_t *)(ptr + 2);
+		tmp3 = *(__uint128_t *)(ptr + 4);
+		tmp4 = *(__uint128_t *)(ptr + 6);
+
+		len -= 64;
+		ptr += 8;
+
+		/* This is the "don't dump the carry flag into a GPR" idiom */
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp2 += (tmp2 >> 64) | (tmp2 << 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp4 += (tmp4 >> 64) | (tmp4 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | sum64;
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		sum64 = tmp1 >> 64;
+	}
+	while (len > 8) {
+		__uint128_t tmp;
+
+		sum64 = accumulate(sum64, data);
+		tmp = *(__uint128_t *)ptr;
+
+		len -= 16;
+		ptr += 2;
+
+#ifdef __LITTLE_ENDIAN
+		data = tmp >> 64;
+		sum64 = accumulate(sum64, tmp);
+#else
+		data = tmp;
+		sum64 = accumulate(sum64, tmp >> 64);
+#endif
+	}
+	if (len > 0) {
+		sum64 = accumulate(sum64, data);
+		data = *ptr;
+		len -= 8;
+	}
+	/*
+	 * Tail: zero any over-read bytes similarly to the head, again
+	 * preserving odd/even alignment.
+	 */
+	shift = len * -8;
+#ifdef __LITTLE_ENDIAN
+	data = (data << shift) >> shift;
+#else
+	data = (data >> shift) << shift;
+#endif
+	sum64 = accumulate(sum64, data);
+
+	/* Finally, folding */
+	sum64 += (sum64 >> 32) | (sum64 << 32);
+	sum = sum64 >> 32;
+	sum += (sum >> 16) | (sum << 16);
+	if (offset & 1)
+		return (u16)swab32(sum);
+
+	return sum >> 16;
+}
+
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum csum)
+{
+	__uint128_t src, dst;
+	u64 sum = (__force u64)csum;
+
+	src = *(const __uint128_t *)saddr->s6_addr;
+	dst = *(const __uint128_t *)daddr->s6_addr;
+
+	sum += (__force u32)htonl(len);
+#ifdef __LITTLE_ENDIAN
+	sum += (u32)proto << 24;
+#else
+	sum += proto;
+#endif
+	src += (src >> 64) | (src << 64);
+	dst += (dst >> 64) | (dst << 64);
+
+	sum = accumulate(sum, src >> 64);
+	sum = accumulate(sum, dst >> 64);
+
+	sum += ((sum >> 32) | (sum << 32));
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+EXPORT_SYMBOL(csum_ipv6_magic);