[PATCH 3/6] GenWQE Utility functions

From: Frank Haverkamp
Date: Wed Nov 06 2013 - 07:47:14 EST


Miscelanous functionality used in the other GenWQE driver parts.

Signed-off-by: Frank Haverkamp <haver@xxxxxxxxxxxxxxxxxx>
Co-authors: Joerg-Stephan Vogt <jsvogt@xxxxxxxxxx>,
Michael Jung <MIJUNG@xxxxxxxxxx>,
Michael Ruettger <michael@xxxxxxxx>
---
drivers/misc/genwqe/card_utils.c | 983 ++++++++++++++++++++++++++++++++++++++
1 files changed, 983 insertions(+), 0 deletions(-)
create mode 100644 drivers/misc/genwqe/card_utils.c

diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
new file mode 100644
index 0000000..5037e28
--- /dev/null
+++ b/drivers/misc/genwqe/card_utils.c
@@ -0,0 +1,983 @@
+/**
+ * IBM Accelerator Family 'GenWQE'
+ *
+ * (C) Copyright IBM Corp. 2013
+ *
+ * Author: Frank Haverkamp <haver@xxxxxxxxxxxxxxxxxx>
+ * Author: Joerg-Stephan Vogt <jsvogt@xxxxxxxxxx>
+ * Author: Michael Jung <mijung@xxxxxxxxxx>
+ * Author: Michael Ruettger <michael@xxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Miscelanous functionality used in the other GenWQE driver parts.
+ */
+
+#include <linux/kernel.h>
+#include <linux/dma-mapping.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
+#include <linux/page-flags.h>
+#include <linux/scatterlist.h>
+#include <linux/hugetlb.h>
+#include <linux/iommu.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <asm/pgtable.h>
+
+#include "genwqe_driver.h"
+#include "card_base.h"
+#include "card_ddcb.h"
+
+/**
+ * __genwqe_writeq() - Write 64-bit register
+ * @cd: genwqe device descriptor
+ * @byte_offs: byte offset within BAR
+ * @val: 64-bit value
+ *
+ * Return: 0 if success; < 0 if error
+ */
+int __genwqe_writeq(struct genwqe_dev *cd, u64 byte_offs, u64 val)
+{
+ genwqe_dprintk(cd, dbg_card_regs,
+ " genwqe_writeq: reg=%08llx val=%016llx\n",
+ byte_offs, val);
+
+ if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE)
+ return -EIO;
+
+ if (cd->mmio == NULL)
+ return -EIO;
+
+ __raw_writeq(cpu_to_be64((val)), (cd->mmio + byte_offs));
+ return 0;
+}
+
+/**
+ * __genwqe_readq() - Read 64-bit register
+ * @cd: genwqe device descriptor
+ * @byte_offs: offset within BAR
+ *
+ * Return: value from register
+ */
+u64 __genwqe_readq(struct genwqe_dev *cd, u64 byte_offs)
+{
+ u64 val;
+
+ if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE)
+ return 0xffffffffffffffffull;
+
+ if ((cd->err_inject & GENWQE_INJECT_GFIR_FATAL) &&
+ (byte_offs == IO_SLC_CFGREG_GFIR))
+ return 0x000000000000ffffull;
+
+ if ((cd->err_inject & GENWQE_INJECT_GFIR_INFO) &&
+ (byte_offs == IO_SLC_CFGREG_GFIR))
+ return 0x00000000ffff0000ull;
+
+ if (cd->mmio == NULL)
+ return 0xffffffffffffffffull;
+
+ val = be64_to_cpu(__raw_readq(cd->mmio + byte_offs));
+
+ genwqe_dprintk(cd, dbg_card_regs,
+ " genwqe_readq: reg=%08llx val=%016llx\n",
+ byte_offs, val);
+
+ return val;
+}
+
+/**
+ * __genwqe_writel() - Write 32-bit register
+ * @cd: genwqe device descriptor
+ * @byte_offs: byte offset within BAR
+ * @val: 32-bit value
+ *
+ * Return: 0 if success; < 0 if error
+ */
+int __genwqe_writel(struct genwqe_dev *cd, uint64_t byte_offs, u32 val)
+{
+ genwqe_dprintk(cd, dbg_card_regs,
+ " genwqe_writel: reg=%08llx val=%08x\n",
+ byte_offs, val);
+
+ if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE)
+ return -EIO;
+
+ if (cd->mmio == NULL)
+ return -EIO;
+
+ __raw_writel(cpu_to_be32((val)), cd->mmio + byte_offs);
+ return 0;
+}
+
+/**
+ * __genwqe_readl() - Read 32-bit register
+ * @cd: genwqe device descriptor
+ * @byte_offs: offset within BAR
+ *
+ * Return: Value from register
+ */
+u32 __genwqe_readl(struct genwqe_dev *cd, uint64_t byte_offs)
+{
+ if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE)
+ return 0xffffffff;
+
+ if (cd->mmio == NULL)
+ return 0xffffffff;
+
+ return be32_to_cpu(__raw_readl(cd->mmio + byte_offs));
+}
+
+/**
+ * genwqe_read_app_id() - Extract app_id
+ *
+ * app_unitcfg need to be filled with valid data first
+ */
+int genwqe_read_app_id(struct genwqe_dev *cd, char *app_name, int len)
+{
+ int i, j;
+ u32 app_id = (u32)cd->app_unitcfg;
+
+ memset(app_name, 0, len);
+ for (i = 0, j = 0; j < min(len, 4); j++) {
+ char ch = (char)((app_id >> (24 - j*8)) & 0xff);
+ if (ch == ' ')
+ continue;
+ app_name[i++] = isprint(ch) ? ch : 'X';
+ }
+ return i;
+}
+
+/**
+ * init_crc32() - Prepare a lookup table for fast crc32 calculations
+ *
+ * Existing kernel functions seem to use a different polynom,
+ * therefore we could not use them here.
+ *
+ * Genwqe's Polynomial = 0x20044009
+ */
+#define CRC32_POLYNOMIAL 0x20044009
+static u32 crc32_tab[256]; /* crc32 lookup table */
+
+void init_crc32(void)
+{
+ int i, j;
+ u32 crc;
+
+ for (i = 0; i < 256; i++) {
+ crc = i << 24;
+ for (j = 0; j < 8; j++) {
+ if (crc & 0x80000000)
+ crc = (crc << 1) ^ CRC32_POLYNOMIAL;
+ else
+ crc = (crc << 1);
+ }
+ crc32_tab[i] = crc;
+ }
+}
+
+/**
+ * genwqe_crc32() - Generate 32-bit crc as required for DDCBs
+ * @buff: pointer to data buffer
+ * @len: length of data for calculation
+ * @init: initial crc (0xffffffff at start)
+ *
+ * polynomial = x^32 * + x^29 + x^18 + x^14 + x^3 + 1 (0x20044009)
+
+ * Example: 4 bytes 0x01 0x02 0x03 0x04 with init=0xffffffff should
+ * result in a crc32 of 0xf33cb7d3.
+ *
+ * The existing kernel crc functions did not cover this polynom yet.
+ *
+ * Return: crc32 checksum.
+ */
+u32 genwqe_crc32(u8 *buff, size_t len, u32 init)
+{
+ int i;
+ u32 crc;
+
+ crc = init;
+ while (len--) {
+ i = ((crc >> 24) ^ *buff++) & 0xFF;
+ crc = (crc << 8) ^ crc32_tab[i];
+ }
+ return crc;
+}
+
+void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size,
+ dma_addr_t *dma_handle)
+{
+ if (get_order(size) > MAX_ORDER)
+ return NULL;
+
+ return pci_alloc_consistent(cd->pci_dev, size, dma_handle);
+}
+
+void __genwqe_free_consistent(struct genwqe_dev *cd, size_t size,
+ void *vaddr, dma_addr_t dma_handle)
+{
+ if (vaddr == NULL)
+ return;
+ pci_free_consistent(cd->pci_dev, size, vaddr, dma_handle);
+}
+
+static void genwqe_unmap_pages(struct genwqe_dev *cd, dma_addr_t *dma_list,
+ int num_pages)
+{
+ int i;
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ for (i = 0; (i < num_pages) && (dma_list[i] != 0x0); i++) {
+ pci_unmap_page(pci_dev, dma_list[i],
+ PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+ dma_list[i] = 0x0;
+ }
+}
+
+static int genwqe_map_pages(struct genwqe_dev *cd,
+ struct page **page_list, int num_pages,
+ dma_addr_t *dma_list)
+{
+ int i;
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ /* establish DMA mapping for requested pages */
+ for (i = 0; i < num_pages; i++) {
+ dma_addr_t daddr;
+
+ dma_list[i] = 0x0;
+ daddr = pci_map_page(pci_dev, page_list[i],
+ 0, /* map_offs */
+ PAGE_SIZE,
+ PCI_DMA_BIDIRECTIONAL); /* FIXME rd/rw */
+
+ if (pci_dma_mapping_error(pci_dev, daddr)) {
+ dev_err(&pci_dev->dev,
+ "[%s] err: no dma addr daddr=%016llx!\n",
+ __func__, (long long)daddr);
+ goto err;
+ }
+
+ dma_list[i] = daddr;
+ }
+ return 0;
+
+ err:
+ genwqe_unmap_pages(cd, dma_list, num_pages);
+ return -EIO;
+}
+
+static int genwqe_sgl_size(int num_pages)
+{
+ int len, num_tlb = num_pages / 7;
+
+ len = sizeof(struct sg_entry) * (num_pages+num_tlb + 1);
+ return roundup(len, PAGE_SIZE);
+}
+
+struct sg_entry *genwqe_alloc_sgl(struct genwqe_dev *cd, int num_pages,
+ dma_addr_t *dma_addr, size_t *sgl_size)
+{
+ struct pci_dev *pci_dev = cd->pci_dev;
+ struct sg_entry *sgl;
+
+ *sgl_size = genwqe_sgl_size(num_pages);
+ if (get_order(*sgl_size) > MAX_ORDER) {
+ dev_err(&pci_dev->dev,
+ "[%s] err: too much memory requested!\n", __func__);
+ return NULL;
+ }
+
+ sgl = __genwqe_alloc_consistent(cd, *sgl_size, dma_addr);
+ if (sgl == NULL) {
+ dev_err(&pci_dev->dev,
+ "[%s] err: no memory available!\n", __func__);
+ return NULL;
+ }
+
+ return sgl;
+}
+
+static void genwqe_dump_sgl(struct genwqe_dev *cd, struct sg_entry *sgl,
+ size_t sgl_size)
+{
+ unsigned int i, j;
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ for (j = 0, i = 0; i < sgl_size/sizeof(struct sg_entry); i++, j++) {
+ if (j == 8) {
+ dev_info(&pci_dev->dev, " --\n");
+ j = 0;
+ }
+ dev_info(&pci_dev->dev, " %016llx %08x %08x %s\n",
+ be64_to_cpu(sgl[i].target_addr),
+ be32_to_cpu(sgl[i].len),
+ be32_to_cpu(sgl[i].flags),
+ (be32_to_cpu(sgl[i].len) > PAGE_SIZE) ? "C" : "");
+
+ if (be32_to_cpu(sgl[i].flags) == SG_END_LIST)
+ break;
+ }
+}
+
+int genwqe_setup_sgl(struct genwqe_dev *cd,
+ unsigned long offs,
+ unsigned long size,
+ struct sg_entry *sgl, /* genwqe sgl */
+ dma_addr_t dma_addr, size_t sgl_size,
+ dma_addr_t *dma_list, int page_offs, int num_pages)
+{
+ int i = 0, j = 0, p;
+ unsigned long dma_offs, map_offs;
+ struct pci_dev *pci_dev = cd->pci_dev;
+ dma_addr_t prev_daddr = 0;
+ struct sg_entry *s, *last_s = NULL;
+
+ /* sanity checks */
+ if (offs > PAGE_SIZE) {
+ dev_err(&pci_dev->dev,
+ "[%s] too large start offs %08lx\n", __func__, offs);
+ return -EFAULT;
+ }
+ if (sgl_size < genwqe_sgl_size(num_pages)) {
+ dev_err(&pci_dev->dev,
+ "[%s] sgl_size too small %08lx for %d pages\n",
+ __func__, sgl_size, num_pages);
+ return -EFAULT;
+ }
+
+ dma_offs = 128; /* next block if needed/dma_offset */
+ map_offs = offs; /* offset in first page */
+
+ s = &sgl[0]; /* first set of 8 entries */
+ p = 0; /* page */
+ while (p < num_pages) {
+ dma_addr_t daddr;
+ unsigned int size_to_map;
+
+ /* always write the chaining entry, cleanup is done later */
+ j = 0;
+ s[j].target_addr = cpu_to_be64(dma_addr + dma_offs);
+ s[j].len = cpu_to_be32(128);
+ s[j].flags = cpu_to_be32(SG_CHAINED);
+ j++;
+
+ while (j < 8) {
+ /* DMA mapping for requested page, offs, size */
+ size_to_map = min(size, PAGE_SIZE - map_offs);
+ daddr = dma_list[page_offs + p] + map_offs;
+ size -= size_to_map;
+ map_offs = 0;
+
+ if (prev_daddr == daddr) {
+ u32 prev_len = be32_to_cpu(last_s->len);
+
+ /* pr_info("daddr combining: "
+ "%016llx/%08x -> %016llx\n",
+ prev_daddr, prev_len, daddr); */
+
+ last_s->len = cpu_to_be32(prev_len +
+ size_to_map);
+
+ p++; /* process next page */
+ if (p == num_pages)
+ goto fixup; /* nothing to do */
+
+ prev_daddr = daddr + size_to_map;
+ continue;
+ }
+
+ /* start new entry */
+ s[j].target_addr = cpu_to_be64(daddr);
+ s[j].len = cpu_to_be32(size_to_map);
+ s[j].flags = cpu_to_be32(SG_DATA);
+ prev_daddr = daddr + size_to_map;
+ last_s = &s[j];
+ j++;
+
+ p++; /* process next page */
+ if (p == num_pages)
+ goto fixup; /* nothing to do */
+ }
+ dma_offs += 128;
+ s += 8; /* continue 8 elements further */
+ }
+ fixup:
+ if (j == 1) { /* combining happend on last entry! */
+ s -= 8; /* full shift needed on previous sgl block */
+ j = 7; /* shift all elements */
+ }
+
+ for (i = 0; i < j; i++) /* move elements 1 up */
+ s[i] = s[i + 1];
+
+ s[i].target_addr = cpu_to_be64(0);
+ s[i].len = cpu_to_be32(0);
+ s[i].flags = cpu_to_be32(SG_END_LIST);
+
+ if (cd->debug & dbg_card_sglist) {
+ genwqe_dprintk(cd, dbg_card_sglist,
+ " genwqe_sglist %d/sgl poffs=%d %d\n",
+ j, page_offs, num_pages);
+ genwqe_dump_sgl(cd, sgl, sgl_size);
+ }
+ return 0;
+}
+
+void genwqe_free_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list,
+ dma_addr_t dma_addr, size_t size)
+{
+ __genwqe_free_consistent(cd, size, sg_list, dma_addr);
+}
+
+/**
+ * free_user_pages() - Give pinned pages back
+ *
+ * Documentation of get_user_pages is in mm/memory.c:
+ *
+ * If the page is written to, set_page_dirty (or set_page_dirty_lock,
+ * as appropriate) must be called after the page is finished with, and
+ * before put_page is called.
+ */
+static int free_user_pages(struct page **page_list, unsigned int nr_pages,
+ int dirty)
+{
+ unsigned int i;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (page_list[i] != NULL) {
+ if (dirty)
+ set_page_dirty_lock(page_list[i]);
+ put_page(page_list[i]);
+ }
+ }
+ return 0;
+}
+
+/**
+ * user_vmap() - Map user-space memory to virtual kernel memory
+ * @cd: pointer to genwqe device
+ * @m: mapping params
+ * @uaddr: user virtual address
+ * @size: size of memory to be mapped
+ *
+ * We need to think about how we could speed this up. Of course it is
+ * not a good idea to do this over and over again, like we are
+ * currently doing it. Nevertheless, I am curious where on the path
+ * the performance is spend. Most probably within the memory
+ * allocation functions, but maybe also in the DMA mapping code.
+ *
+ * Restrictions: The maximum size of the possible mapping currently depends
+ * on the amount of memory we can get using kzalloc() for the
+ * page_list and pci_alloc_coherent for the sg_list.
+ * The sg_list is currently itself not scattered, which could
+ * be fixed with some effort. The page_list must be split into
+ * PAGE_SIZE chunks too. All that will make the complicated
+ * code more complicated.
+ *
+ * Return: 0 if success
+ */
+int user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr,
+ unsigned long size, struct ddcb_requ *req)
+{
+ int rc = -EINVAL;
+ unsigned long data, offs;
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ if ((uaddr == NULL) || (size == 0)) {
+ m->size = 0; /* mark unused and not added */
+ return -EINVAL;
+ }
+ m->u_vaddr = uaddr;
+ m->size = size;
+
+ /* determine space needed for page_list. */
+ data = (unsigned long)uaddr;
+ offs = offset_in_page(data);
+ m->nr_pages = DIV_ROUND_UP(offs + size, PAGE_SIZE);
+
+ m->page_list = kcalloc(m->nr_pages,
+ sizeof(struct page *) + sizeof(dma_addr_t),
+ GFP_KERNEL);
+ if (!m->page_list) {
+ dev_err(&pci_dev->dev, "err: alloc page_list failed\n");
+ m->nr_pages = 0;
+ m->u_vaddr = NULL;
+ m->size = 0; /* mark unused and not added */
+ return -ENOMEM;
+ }
+ m->dma_list = (dma_addr_t *)(m->page_list + m->nr_pages);
+
+ /* pin user pages in memory */
+ rc = get_user_pages_fast(data & PAGE_MASK, /* page aligned addr */
+ m->nr_pages,
+ 1, /* write by caller */
+ m->page_list); /* ptrs to pages */
+
+ /* assumption: get_user_pages can be killed by signals. */
+ if (rc < m->nr_pages) {
+ free_user_pages(m->page_list, rc, 0);
+ rc = -EFAULT;
+ goto fail_get_user_pages;
+ }
+
+ rc = genwqe_map_pages(cd, m->page_list, m->nr_pages, m->dma_list);
+ if (rc != 0)
+ goto fail_free_user_pages;
+
+ return 0;
+
+ fail_free_user_pages:
+ free_user_pages(m->page_list, m->nr_pages, 0);
+
+ fail_get_user_pages:
+ kfree(m->page_list);
+ m->page_list = NULL;
+ m->dma_list = NULL;
+ m->nr_pages = 0;
+ m->u_vaddr = NULL;
+ m->size = 0; /* mark unused and not added */
+ return rc;
+}
+
+/**
+ * user_vunmap() - Undo mapping of user-space memory to virtual kernel memory
+ * @cd: pointer to genwqe device
+ * @m: mapping params
+ */
+int user_vunmap(struct genwqe_dev *cd, struct dma_mapping *m,
+ struct ddcb_requ *req)
+{
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ if (!dma_mapping_used(m)) {
+ dev_err(&pci_dev->dev, "[%s] err: mapping %p not used!\n",
+ __func__, m);
+ return -EINVAL;
+ }
+
+ if (m->dma_list)
+ genwqe_unmap_pages(cd, m->dma_list, m->nr_pages);
+
+ if (m->page_list) {
+ free_user_pages(m->page_list, m->nr_pages, 1);
+
+ kfree(m->page_list);
+ m->page_list = NULL;
+ m->dma_list = NULL;
+ m->nr_pages = 0;
+ }
+
+ m->u_vaddr = NULL;
+ m->size = 0; /* mark as unused and not added */
+ return 0;
+}
+
+/**
+ * genwqe_card_type() - Get chip type SLU Configuration Register
+ * @cd: pointer to the genwqe device descriptor
+ * Return: 0: Altera Stratix-IV 230
+ * 1: Altera Stratix-IV 530
+ * 2: Altera Stratix-V A4
+ * 3: Altera Stratix-V A7
+ */
+u8 genwqe_card_type(struct genwqe_dev *cd)
+{
+ u64 card_type = cd->slu_unitcfg;
+ return (u8)((card_type & SLU_UNITCFG_TYPE_MASK) >> 20);
+}
+
+/**
+ * genwqe_card_reset() - Reset the card
+ * @cd: pointer to the genwqe device descriptor
+ */
+int genwqe_card_reset(struct genwqe_dev *cd)
+{
+ u64 softrst;
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ if (!genwqe_is_privileged(cd))
+ return -ENODEV;
+
+ /* new SL */
+ __genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, 0x1ull);
+ msleep(1000);
+ __genwqe_readq(cd, IO_HSU_FIR_CLR);
+ __genwqe_readq(cd, IO_APP_FIR_CLR);
+ __genwqe_readq(cd, IO_SLU_FIR_CLR);
+
+ /*
+ * Read-modify-write to preserve the stealth bits
+ *
+ * For SL >= 039, Stealth WE bit allows removing
+ * the read-modify-wrote.
+ * r-m-w may require a mask 0x3C to avoid hitting hard
+ * reset again for error reset (should be 0, chicken).
+ */
+ softrst = __genwqe_readq(cd, IO_SLC_CFGREG_SOFTRESET) & 0x3cull;
+ __genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, softrst | 0x2ull);
+
+ /* give ERRORRESET some time to finish */
+ msleep(50);
+
+ if (genwqe_need_err_masking(cd)) {
+ dev_info(&pci_dev->dev,
+ "[%s] masking errors for old bitstreams\n", __func__);
+ __genwqe_writeq(cd, IO_SLC_MISC_DEBUG, 0x0aull);
+ }
+ return 0;
+}
+
+int genwqe_read_softreset(struct genwqe_dev *cd)
+{
+ u64 bitstream;
+
+ if (!genwqe_is_privileged(cd))
+ return -ENODEV;
+
+ bitstream = __genwqe_readq(cd, IO_SLU_BITSTREAM) & 0x1;
+ cd->softreset = (bitstream == 0) ? 0x8ull : 0xcull;
+ return 0;
+}
+
+/**
+ * genwqe_set_interrupt_capability() - Configure MSI capability structure
+ * @cd: pointer to the device
+ * Return: 0 if no error
+ */
+int genwqe_set_interrupt_capability(struct genwqe_dev *cd, int count)
+{
+ int rc;
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ rc = pci_enable_msi_block(pci_dev, count);
+ if (rc == 0)
+ cd->flags |= GENWQE_FLAG_MSI_ENABLED;
+ return rc;
+}
+
+/**
+ * genwqe_reset_interrupt_capability() - Undo genwqe_set_interrupt_capability()
+ * @cd: pointer to the device
+ */
+void genwqe_reset_interrupt_capability(struct genwqe_dev *cd)
+{
+ struct pci_dev *pci_dev = cd->pci_dev;
+
+ if (cd->flags & GENWQE_FLAG_MSI_ENABLED) {
+ pci_disable_msi(pci_dev);
+ cd->flags &= ~GENWQE_FLAG_MSI_ENABLED;
+ }
+}
+
+/**
+ * set_reg_idx() - Fill array with data. Ignore illegal offsets.
+ * @cd: card device
+ * @r: debug register array
+ * @i: index to desired entry
+ * @m: maximum possible entries
+ * @addr: addr which is read
+ * @index: index in debug array
+ * @val: read value
+ */
+static int set_reg_idx(struct genwqe_dev *cd, struct genwqe_reg *r,
+ unsigned int *i, unsigned int m, u32 addr, u32 idx,
+ u64 val)
+{
+ if (WARN_ON_ONCE(*i >= m))
+ return -EFAULT;
+
+ r[*i].addr = addr;
+ r[*i].idx = idx;
+ r[*i].val = val;
+ ++*i;
+ return 0;
+}
+
+static int set_reg(struct genwqe_dev *cd, struct genwqe_reg *r,
+ unsigned int *i, unsigned int m, u32 addr, u64 val)
+{
+ return set_reg_idx(cd, r, i, m, addr, 0, val);
+}
+
+int genwqe_read_ffdc_regs(struct genwqe_dev *cd, struct genwqe_reg *regs,
+ unsigned int max_regs, int all)
+{
+ unsigned int i, j, idx = 0;
+ u32 ufir_addr, ufec_addr, sfir_addr, sfec_addr;
+ u64 gfir, sluid, appid, ufir, ufec, sfir, sfec;
+
+ /* Global FIR */
+ gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
+ set_reg(cd, regs, &idx, max_regs, IO_SLC_CFGREG_GFIR, gfir);
+
+ /* UnitCfg for SLU */
+ sluid = __genwqe_readq(cd, IO_SLU_UNITCFG); /* 0x00000000 */
+ set_reg(cd, regs, &idx, max_regs, IO_SLU_UNITCFG, sluid);
+
+ /* UnitCfg for APP */
+ appid = __genwqe_readq(cd, IO_APP_UNITCFG); /* 0x02000000 */
+ set_reg(cd, regs, &idx, max_regs, IO_APP_UNITCFG, appid);
+
+ /* Check all chip Units */
+ for (i = 0; i < GENWQE_MAX_UNITS; i++) {
+
+ /* Unit FIR */
+ ufir_addr = (i << 24) | 0x008;
+ ufir = __genwqe_readq(cd, ufir_addr);
+ set_reg(cd, regs, &idx, max_regs, ufir_addr, ufir);
+
+ /* Unit FEC */
+ ufec_addr = (i << 24) | 0x018;
+ ufec = __genwqe_readq(cd, ufec_addr);
+ set_reg(cd, regs, &idx, max_regs, ufec_addr, ufec);
+
+ for (j = 0; j < 64; j++) {
+ /* wherever there is a primary 1, read the 2ndary */
+ if (!all && (!(ufir & (1ull << j))))
+ continue;
+
+ sfir_addr = (i << 24) | (0x100 + 8 * j);
+ sfir = __genwqe_readq(cd, sfir_addr);
+ set_reg(cd, regs, &idx, max_regs, sfir_addr, sfir);
+
+ sfec_addr = (i << 24) | (0x300 + 8 * j);
+ sfec = __genwqe_readq(cd, sfec_addr);
+ set_reg(cd, regs, &idx, max_regs, sfec_addr, sfec);
+ }
+ }
+
+ /* fill with invalid data until end */
+ for (i = idx; i < max_regs; i++) {
+ regs[i].addr = 0xffffffff;
+ regs[i].val = 0xffffffffffffffffull;
+ }
+ return idx;
+}
+
+/**
+ * genwqe_ffdc_buff_size() - Calculates the number of dump registers
+ */
+int genwqe_ffdc_buff_size(struct genwqe_dev *cd, int uid)
+{
+ int entries = 0, ring, traps, traces, trace_entries;
+ uint32_t eevptr_addr, l_addr, d_len, d_type;
+ uint64_t eevptr, val, addr;
+
+ eevptr_addr = UID_OFFS(uid) | IO_EXTENDED_ERROR_POINTER;
+ eevptr = __genwqe_readq(cd, eevptr_addr);
+
+ if ((eevptr != 0x0) && (eevptr != -1ull)) {
+ l_addr = UID_OFFS(uid) | eevptr;
+
+ while (1) {
+ val = __genwqe_readq(cd, l_addr);
+
+ if ((val == 0x0) || (val == -1ull))
+ break;
+
+ /* 38:24 */
+ d_len = (val & 0x0000007fff000000ull) >> 24;
+
+ /* 39 */
+ d_type = (val & 0x0000008000000000ull) >> 36;
+
+ if (d_type) { /* repeat */
+ entries += d_len;
+ } else { /* size in bytes! */
+ entries += d_len >> 3;
+ }
+
+ l_addr += 8;
+ }
+ }
+
+ for (ring = 0; ring < 8; ring++) {
+ addr = UID_OFFS(uid) | IO_EXTENDED_DIAG_MAP(ring);
+ val = __genwqe_readq(cd, addr);
+
+ if ((val == 0x0ull) || (val == -1ull))
+ continue;
+
+ traps = (val >> 24) & 0xff;
+ traces = (val >> 16) & 0xff;
+ trace_entries = val & 0xffff;
+
+ entries += traps + (traces * trace_entries);
+ }
+ return entries;
+}
+
+/**
+ * genwqe_ffdc_buff_read() - Implements LogoutExtendedErrorRegisters procedure
+ */
+int genwqe_ffdc_buff_read(struct genwqe_dev *cd, int uid,
+ struct genwqe_reg *regs, unsigned int max_regs)
+{
+ int i, traps, traces, trace, trace_entries, trace_entry, ring;
+ unsigned int idx = 0;
+ uint32_t eevptr_addr, l_addr, d_addr, d_len, d_type;
+ uint64_t eevptr, e, val, addr;
+
+ eevptr_addr = UID_OFFS(uid) | IO_EXTENDED_ERROR_POINTER;
+ eevptr = __genwqe_readq(cd, eevptr_addr);
+
+ if ((eevptr != 0x0) && (eevptr != 0xffffffffffffffffull)) {
+ l_addr = UID_OFFS(uid) | eevptr;
+ while (1) {
+ e = __genwqe_readq(cd, l_addr);
+ if ((e == 0x0) || (e == 0xffffffffffffffffull))
+ break;
+
+ d_addr = (e & 0x0000000000ffffffull); /* 23:0 */
+ d_len = (e & 0x0000007fff000000ull) >> 24; /* 38:24 */
+ d_type = (e & 0x0000008000000000ull) >> 36; /* 39 */
+ d_addr |= UID_OFFS(uid);
+
+ if (d_type) {
+ for (i = 0; i < (int)d_len; i++) {
+ val = __genwqe_readq(cd, d_addr);
+ set_reg_idx(cd, regs, &idx, max_regs,
+ d_addr, i, val);
+ }
+ } else {
+ d_len >>= 3; /* Size in bytes! */
+ for (i = 0; i < (int)d_len; i++, d_addr += 8) {
+ val = __genwqe_readq(cd, d_addr);
+ set_reg_idx(cd, regs, &idx, max_regs,
+ d_addr, 0, val);
+ }
+ }
+ l_addr += 8;
+ }
+ }
+
+ /*
+ * To save time, there are only 6 traces poplulated on Uid=2,
+ * Ring=1. each with iters=512.
+ */
+ for (ring = 0; ring < 8; ring++) { /* 0 is fls, 1 is fds,
+ 2...7 are ASI rings */
+ addr = UID_OFFS(uid) | IO_EXTENDED_DIAG_MAP(ring);
+ val = __genwqe_readq(cd, addr);
+
+ if ((val == 0x0ull) || (val == -1ull))
+ continue;
+
+ traps = (val >> 24) & 0xff; /* Number of Traps */
+ traces = (val >> 16) & 0xff; /* Number of Traces */
+ trace_entries = val & 0xffff; /* Entries per trace */
+
+ /* Note: This is a combined loop that dumps both the traps */
+ /* (for the trace == 0 case) as well as the traces 1 to */
+ /* 'traces'. */
+ for (trace = 0; trace <= traces; trace++) {
+ uint32_t diag_sel =
+ EXTENDED_DIAG_SELECTOR(ring, trace);
+
+ addr = UID_OFFS(uid) | IO_EXTENDED_DIAG_SELECTOR;
+ __genwqe_writeq(cd, addr, diag_sel);
+
+ for (trace_entry = 0;
+ trace_entry < (trace ? trace_entries : traps);
+ trace_entry++) {
+ addr = UID_OFFS(uid)|IO_EXTENDED_DIAG_READ_MBX;
+ val = __genwqe_readq(cd, addr);
+ set_reg_idx(cd, regs, &idx, max_regs, addr,
+ (diag_sel<<16) | trace_entry, val);
+ }
+ }
+ }
+ return 0;
+}
+
+/**
+ * genwqe_write_jtimer() - Write jobtimeout register
+ *
+ * Sets the jobtimeout and heartbeat rate timers for this queue.
+ * Note, this register is accessible only to the PF through the
+ * VF-window. It is not intended for the VF to initialize this.
+ *
+ * It is an error to write to this register while the queue is active,
+ * i.e. when Queue Status(7:6) != 0.
+ */
+int genwqe_write_jtimer(struct genwqe_dev *cd, int func, u64 jtimer)
+{
+ __genwqe_writeq(cd, IO_PF_SLC_VIRTUAL_WINDOW, func & 0xf);
+ __genwqe_writeq(cd, IO_SLC_VF_APPJOB_TIMEOUT, jtimer);
+ return 0;
+}
+
+u64 genwqe_read_jtimer(struct genwqe_dev *cd, int func)
+{
+ u64 jtimer;
+
+ __genwqe_writeq(cd, IO_PF_SLC_VIRTUAL_WINDOW, func & 0xf);
+ jtimer = __genwqe_readq(cd, IO_SLC_VF_APPJOB_TIMEOUT);
+
+ return jtimer;
+}
+
+/**
+ * genwqe_base_clock_frequency() - Deteremine base clock frequency of the card
+ *
+ * Note: From a design perspective it turned out to be a bad idea to
+ * use codes here to specifiy the frequency/speed values. An old
+ * driver cannot understand new codes and is therefore always a
+ * problem. Better is to measure out the value or put the
+ * speed/frequency directly into a register which is always a valid
+ * value for old as well as for new software.
+ *
+ * Return: Card clock in MHz
+ */
+int genwqe_base_clock_frequency(struct genwqe_dev *cd)
+{
+ u16 speed; /* MHz MHz MHz MHz */
+ static const int speed_grade[] = { 250, 200, 166, 175 };
+
+ speed = (u16)((cd->slu_unitcfg >> 28) & 0x0full);
+ if (speed >= ARRAY_SIZE(speed_grade))
+ return 0; /* illegal value */
+
+ return speed_grade[speed];
+}
+
+/**
+ * genwqe_stop_traps() - Stop traps
+ *
+ * Before reading out the analysis data, we need to stop the traps.
+ */
+void genwqe_stop_traps(struct genwqe_dev *cd)
+{
+ /* Halt the traps while dumping FFDC. */
+ __genwqe_writeq(cd, IO_SLC_MISC_DEBUG_SET, 0xcull);
+}
+
+/**
+ * genwqe_start_traps() - Start traps
+ *
+ * After having read the data, we can/must enable the traps again.
+ */
+void genwqe_start_traps(struct genwqe_dev *cd)
+{
+ /* Restart the traps. */
+ __genwqe_writeq(cd, IO_SLC_MISC_DEBUG_CLR, 0xcull);
+
+ if (genwqe_need_err_masking(cd))
+ __genwqe_writeq(cd, IO_SLC_MISC_DEBUG, 0x0aull);
+}
--
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/