Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "API:
   - Restrict crypto_cipher to internal API users only.

  Algorithms:
   - Add x86 aesni acceleration for cts.
   - Improve x86 aesni acceleration for xts.
   - Remove x86 acceleration of some uncommon algorithms.
   - Remove RIPE-MD, Tiger and Salsa20.
   - Remove tnepres.
   - Add ARM acceleration for BLAKE2s and BLAKE2b.

  Drivers:
   - Add Keem Bay OCS HCU driver.
   - Add Marvell OcteonTX2 CPT PF driver.
   - Remove PicoXcell driver.
   - Remove mediatek driver"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (154 commits)
  hwrng: timeriomem - Use device-managed registration API
  crypto: hisilicon/qm - fix printing format issue
  crypto: hisilicon/qm - do not reset hardware when CE happens
  crypto: hisilicon/qm - update irqflag
  crypto: hisilicon/qm - fix the value of 'QM_SQC_VFT_BASE_MASK_V2'
  crypto: hisilicon/qm - fix request missing error
  crypto: hisilicon/qm - removing driver after reset
  crypto: octeontx2 - fix -Wpointer-bool-conversion warning
  crypto: hisilicon/hpre - enable Elliptic curve cryptography
  crypto: hisilicon - PASID fixed on Kunpeng 930
  crypto: hisilicon/qm - fix use of 'dma_map_single'
  crypto: hisilicon/hpre - tiny fix
  crypto: hisilicon/hpre - adapt the number of clusters
  crypto: cpt - remove casting dma_alloc_coherent
  crypto: keembay-ocs-aes - Fix 'q' assignment during CCM B0 generation
  crypto: xor - Fix typo of optimization
  hwrng: optee - Use device-managed registration API
  crypto: arm64/crc-t10dif - move NEON yield to C code
  crypto: arm64/aes-ce-mac - simplify NEON yield
  crypto: arm64/aes-neonbs - remove NEON yield calls
  ...

1 files changed, 428 insertions, 0 deletions

diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c
new file mode 100644
index 000000000000..823a4571fd67
--- /dev/null
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Marvell. */
+
+#include "otx2_cpt_common.h"
+#include "otx2_cptlf.h"
+#include "rvu_reg.h"
+
+#define CPT_TIMER_HOLD 0x03F
+#define CPT_COUNT_HOLD 32
+
+static void cptlf_do_set_done_time_wait(struct otx2_cptlf_info *lf,
+					int time_wait)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+
+	done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				      OTX2_CPT_LF_DONE_WAIT);
+	done_wait.s.time_wait = time_wait;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+}
+
+static void cptlf_do_set_done_num_wait(struct otx2_cptlf_info *lf, int num_wait)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+
+	done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				      OTX2_CPT_LF_DONE_WAIT);
+	done_wait.s.num_wait = num_wait;
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+}
+
+static void cptlf_set_done_time_wait(struct otx2_cptlfs_info *lfs,
+				     int time_wait)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		cptlf_do_set_done_time_wait(&lfs->lf[slot], time_wait);
+}
+
+static void cptlf_set_done_num_wait(struct otx2_cptlfs_info *lfs, int num_wait)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		cptlf_do_set_done_num_wait(&lfs->lf[slot], num_wait);
+}
+
+static int cptlf_set_pri(struct otx2_cptlf_info *lf, int pri)
+{
+	struct otx2_cptlfs_info *lfs = lf->lfs;
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	int ret;
+
+	ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+				   CPT_AF_LFX_CTL(lf->slot),
+				   &lf_ctrl.u);
+	if (ret)
+		return ret;
+
+	lf_ctrl.s.pri = pri ? 1 : 0;
+
+	ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+				    CPT_AF_LFX_CTL(lf->slot),
+				    lf_ctrl.u);
+	return ret;
+}
+
+static int cptlf_set_eng_grps_mask(struct otx2_cptlf_info *lf,
+				   int eng_grps_mask)
+{
+	struct otx2_cptlfs_info *lfs = lf->lfs;
+	union otx2_cptx_af_lf_ctrl lf_ctrl;
+	int ret;
+
+	ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
+				   CPT_AF_LFX_CTL(lf->slot),
+				   &lf_ctrl.u);
+	if (ret)
+		return ret;
+
+	lf_ctrl.s.grp = eng_grps_mask;
+
+	ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
+				    CPT_AF_LFX_CTL(lf->slot),
+				    lf_ctrl.u);
+	return ret;
+}
+
+static int cptlf_set_grp_and_pri(struct otx2_cptlfs_info *lfs,
+				 int eng_grp_mask, int pri)
+{
+	int slot, ret = 0;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		ret = cptlf_set_pri(&lfs->lf[slot], pri);
+		if (ret)
+			return ret;
+
+		ret = cptlf_set_eng_grps_mask(&lfs->lf[slot], eng_grp_mask);
+		if (ret)
+			return ret;
+	}
+	return ret;
+}
+
+static void cptlf_hw_init(struct otx2_cptlfs_info *lfs)
+{
+	/* Disable instruction queues */
+	otx2_cptlf_disable_iqueues(lfs);
+
+	/* Set instruction queues base addresses */
+	otx2_cptlf_set_iqueues_base_addr(lfs);
+
+	/* Set instruction queues sizes */
+	otx2_cptlf_set_iqueues_size(lfs);
+
+	/* Set done interrupts time wait */
+	cptlf_set_done_time_wait(lfs, CPT_TIMER_HOLD);
+
+	/* Set done interrupts num wait */
+	cptlf_set_done_num_wait(lfs, CPT_COUNT_HOLD);
+
+	/* Enable instruction queues */
+	otx2_cptlf_enable_iqueues(lfs);
+}
+
+static void cptlf_hw_cleanup(struct otx2_cptlfs_info *lfs)
+{
+	/* Disable instruction queues */
+	otx2_cptlf_disable_iqueues(lfs);
+}
+
+static void cptlf_set_misc_intrs(struct otx2_cptlfs_info *lfs, u8 enable)
+{
+	union otx2_cptx_lf_misc_int_ena_w1s irq_misc = { .u = 0x0 };
+	u64 reg = enable ? OTX2_CPT_LF_MISC_INT_ENA_W1S :
+			   OTX2_CPT_LF_MISC_INT_ENA_W1C;
+	int slot;
+
+	irq_misc.s.fault = 0x1;
+	irq_misc.s.hwerr = 0x1;
+	irq_misc.s.irde = 0x1;
+	irq_misc.s.nqerr = 0x1;
+	irq_misc.s.nwrp = 0x1;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot, reg,
+				 irq_misc.u);
+}
+
+static void cptlf_enable_intrs(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	/* Enable done interrupts */
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot,
+				 OTX2_CPT_LF_DONE_INT_ENA_W1S, 0x1);
+	/* Enable Misc interrupts */
+	cptlf_set_misc_intrs(lfs, true);
+}
+
+static void cptlf_disable_intrs(struct otx2_cptlfs_info *lfs)
+{
+	int slot;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++)
+		otx2_cpt_write64(lfs->reg_base, BLKADDR_CPT0, slot,
+				 OTX2_CPT_LF_DONE_INT_ENA_W1C, 0x1);
+	cptlf_set_misc_intrs(lfs, false);
+}
+
+static inline int cptlf_read_done_cnt(struct otx2_cptlf_info *lf)
+{
+	union otx2_cptx_lf_done irq_cnt;
+
+	irq_cnt.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				    OTX2_CPT_LF_DONE);
+	return irq_cnt.s.done;
+}
+
+static irqreturn_t cptlf_misc_intr_handler(int __always_unused irq, void *arg)
+{
+	union otx2_cptx_lf_misc_int irq_misc, irq_misc_ack;
+	struct otx2_cptlf_info *lf = arg;
+	struct device *dev;
+
+	dev = &lf->lfs->pdev->dev;
+	irq_misc.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				     OTX2_CPT_LF_MISC_INT);
+	irq_misc_ack.u = 0x0;
+
+	if (irq_misc.s.fault) {
+		dev_err(dev, "Memory error detected while executing CPT_INST_S, LF %d.\n",
+			lf->slot);
+		irq_misc_ack.s.fault = 0x1;
+
+	} else if (irq_misc.s.hwerr) {
+		dev_err(dev, "HW error from an engine executing CPT_INST_S, LF %d.",
+			lf->slot);
+		irq_misc_ack.s.hwerr = 0x1;
+
+	} else if (irq_misc.s.nwrp) {
+		dev_err(dev, "SMMU fault while writing CPT_RES_S to CPT_INST_S[RES_ADDR], LF %d.\n",
+			lf->slot);
+		irq_misc_ack.s.nwrp = 0x1;
+
+	} else if (irq_misc.s.irde) {
+		dev_err(dev, "Memory error when accessing instruction memory queue CPT_LF_Q_BASE[ADDR].\n");
+		irq_misc_ack.s.irde = 0x1;
+
+	} else if (irq_misc.s.nqerr) {
+		dev_err(dev, "Error enqueuing an instruction received at CPT_LF_NQ.\n");
+		irq_misc_ack.s.nqerr = 0x1;
+
+	} else {
+		dev_err(dev, "Unhandled interrupt in CPT LF %d\n", lf->slot);
+		return IRQ_NONE;
+	}
+
+	/* Acknowledge interrupts */
+	otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+			 OTX2_CPT_LF_MISC_INT, irq_misc_ack.u);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cptlf_done_intr_handler(int irq, void *arg)
+{
+	union otx2_cptx_lf_done_wait done_wait;
+	struct otx2_cptlf_info *lf = arg;
+	int irq_cnt;
+
+	/* Read the number of completed requests */
+	irq_cnt = cptlf_read_done_cnt(lf);
+	if (irq_cnt) {
+		done_wait.u = otx2_cpt_read64(lf->lfs->reg_base, BLKADDR_CPT0,
+					      lf->slot, OTX2_CPT_LF_DONE_WAIT);
+		/* Acknowledge the number of completed requests */
+		otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				 OTX2_CPT_LF_DONE_ACK, irq_cnt);
+
+		otx2_cpt_write64(lf->lfs->reg_base, BLKADDR_CPT0, lf->slot,
+				 OTX2_CPT_LF_DONE_WAIT, done_wait.u);
+		if (unlikely(!lf->wqe)) {
+			dev_err(&lf->lfs->pdev->dev, "No work for LF %d\n",
+				lf->slot);
+			return IRQ_NONE;
+		}
+
+		/* Schedule processing of completed requests */
+		tasklet_hi_schedule(&lf->wqe->work);
+	}
+	return IRQ_HANDLED;
+}
+
+void otx2_cptlf_unregister_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	int i, offs, vector;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) {
+			if (!lfs->lf[i].is_irq_reg[offs])
+				continue;
+
+			vector = pci_irq_vector(lfs->pdev,
+						lfs->lf[i].msix_offset + offs);
+			free_irq(vector, &lfs->lf[i]);
+			lfs->lf[i].is_irq_reg[offs] = false;
+		}
+	}
+	cptlf_disable_intrs(lfs);
+}
+
+static int cptlf_do_register_interrrupts(struct otx2_cptlfs_info *lfs,
+					 int lf_num, int irq_offset,
+					 irq_handler_t handler)
+{
+	int ret, vector;
+
+	vector = pci_irq_vector(lfs->pdev, lfs->lf[lf_num].msix_offset +
+				irq_offset);
+	ret = request_irq(vector, handler, 0,
+			  lfs->lf[lf_num].irq_name[irq_offset],
+			  &lfs->lf[lf_num]);
+	if (ret)
+		return ret;
+
+	lfs->lf[lf_num].is_irq_reg[irq_offset] = true;
+
+	return ret;
+}
+
+int otx2_cptlf_register_interrupts(struct otx2_cptlfs_info *lfs)
+{
+	int irq_offs, ret, i;
+
+	for (i = 0; i < lfs->lfs_num; i++) {
+		irq_offs = OTX2_CPT_LF_INT_VEC_E_MISC;
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "CPTLF Misc%d", i);
+		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
+						    cptlf_misc_intr_handler);
+		if (ret)
+			goto free_irq;
+
+		irq_offs = OTX2_CPT_LF_INT_VEC_E_DONE;
+		snprintf(lfs->lf[i].irq_name[irq_offs], 32, "OTX2_CPTLF Done%d",
+			 i);
+		ret = cptlf_do_register_interrrupts(lfs, i, irq_offs,
+						    cptlf_done_intr_handler);
+		if (ret)
+			goto free_irq;
+	}
+	cptlf_enable_intrs(lfs);
+	return 0;
+
+free_irq:
+	otx2_cptlf_unregister_interrupts(lfs);
+	return ret;
+}
+
+void otx2_cptlf_free_irqs_affinity(struct otx2_cptlfs_info *lfs)
+{
+	int slot, offs;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++)
+			irq_set_affinity_hint(pci_irq_vector(lfs->pdev,
+					      lfs->lf[slot].msix_offset +
+					      offs), NULL);
+		free_cpumask_var(lfs->lf[slot].affinity_mask);
+	}
+}
+
+int otx2_cptlf_set_irqs_affinity(struct otx2_cptlfs_info *lfs)
+{
+	struct otx2_cptlf_info *lf = lfs->lf;
+	int slot, offs, ret;
+
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		if (!zalloc_cpumask_var(&lf[slot].affinity_mask, GFP_KERNEL)) {
+			dev_err(&lfs->pdev->dev,
+				"cpumask allocation failed for LF %d", slot);
+			ret = -ENOMEM;
+			goto free_affinity_mask;
+		}
+
+		cpumask_set_cpu(cpumask_local_spread(slot,
+				dev_to_node(&lfs->pdev->dev)),
+				lf[slot].affinity_mask);
+
+		for (offs = 0; offs < OTX2_CPT_LF_MSIX_VECTORS; offs++) {
+			ret = irq_set_affinity_hint(pci_irq_vector(lfs->pdev,
+						lf[slot].msix_offset + offs),
+						lf[slot].affinity_mask);
+			if (ret)
+				goto free_affinity_mask;
+		}
+	}
+	return 0;
+
+free_affinity_mask:
+	otx2_cptlf_free_irqs_affinity(lfs);
+	return ret;
+}
+
+int otx2_cptlf_init(struct otx2_cptlfs_info *lfs, u8 eng_grp_mask, int pri,
+		    int lfs_num)
+{
+	int slot, ret;
+
+	if (!lfs->pdev || !lfs->reg_base)
+		return -EINVAL;
+
+	lfs->lfs_num = lfs_num;
+	for (slot = 0; slot < lfs->lfs_num; slot++) {
+		lfs->lf[slot].lfs = lfs;
+		lfs->lf[slot].slot = slot;
+		lfs->lf[slot].lmtline = lfs->reg_base +
+			OTX2_CPT_RVU_FUNC_ADDR_S(BLKADDR_LMT, slot,
+						 OTX2_CPT_LMT_LF_LMTLINEX(0));
+		lfs->lf[slot].ioreg = lfs->reg_base +
+			OTX2_CPT_RVU_FUNC_ADDR_S(BLKADDR_CPT0, slot,
+						 OTX2_CPT_LF_NQX(0));
+	}
+	/* Send request to attach LFs */
+	ret = otx2_cpt_attach_rscrs_msg(lfs);
+	if (ret)
+		goto clear_lfs_num;
+
+	ret = otx2_cpt_alloc_instruction_queues(lfs);
+	if (ret) {
+		dev_err(&lfs->pdev->dev,
+			"Allocating instruction queues failed\n");
+		goto detach_rsrcs;
+	}
+	cptlf_hw_init(lfs);
+	/*
+	 * Allow each LF to execute requests destined to any of 8 engine
+	 * groups and set queue priority of each LF to high
+	 */
+	ret = cptlf_set_grp_and_pri(lfs, eng_grp_mask, pri);
+	if (ret)
+		goto free_iq;
+
+	return 0;
+
+free_iq:
+	otx2_cpt_free_instruction_queues(lfs);
+	cptlf_hw_cleanup(lfs);
+detach_rsrcs:
+	otx2_cpt_detach_rsrcs_msg(lfs);
+clear_lfs_num:
+	lfs->lfs_num = 0;
+	return ret;
+}
+
+void otx2_cptlf_shutdown(struct otx2_cptlfs_info *lfs)
+{
+	lfs->lfs_num = 0;
+	/* Cleanup LFs hardware side */
+	cptlf_hw_cleanup(lfs);
+	/* Send request to detach LFs */
+	otx2_cpt_detach_rsrcs_msg(lfs);
+}