From patchwork Fri Oct 10 09:34:17 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alexey Ishchuk X-Patchwork-Id: 5064241 Return-Path: X-Original-To: patchwork-linux-rdma@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork1.web.kernel.org (Postfix) with ESMTP id C7B409F2F1 for ; Fri, 10 Oct 2014 09:35:49 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id ADCA72022D for ; Fri, 10 Oct 2014 09:35:48 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 79C9920220 for ; Fri, 10 Oct 2014 09:35:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753244AbaJJJfq (ORCPT ); Fri, 10 Oct 2014 05:35:46 -0400 Received: from e06smtp13.uk.ibm.com ([195.75.94.109]:34231 "EHLO e06smtp13.uk.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752579AbaJJJfq (ORCPT ); Fri, 10 Oct 2014 05:35:46 -0400 Received: from /spool/local by e06smtp13.uk.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 10 Oct 2014 10:35:44 +0100 Received: from d06dlp03.portsmouth.uk.ibm.com (9.149.20.15) by e06smtp13.uk.ibm.com (192.168.101.143) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Fri, 10 Oct 2014 10:35:42 +0100 Received: from b06cxnps4075.portsmouth.uk.ibm.com (d06relay12.portsmouth.uk.ibm.com [9.149.109.197]) by d06dlp03.portsmouth.uk.ibm.com (Postfix) with ESMTP id 9C1DA1B0804B for ; Fri, 10 Oct 2014 10:36:57 +0100 (BST) Received: from d06av04.portsmouth.uk.ibm.com (d06av04.portsmouth.uk.ibm.com [9.149.37.216]) by b06cxnps4075.portsmouth.uk.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id s9A9ZfxD63832300 for ; Fri, 10 Oct 2014 09:35:41 GMT Received: from d06av04.portsmouth.uk.ibm.com (localhost [127.0.0.1]) by d06av04.portsmouth.uk.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id s9A9Zdrh007639 for ; Fri, 10 Oct 2014 03:35:41 -0600 Received: from tuxmaker.boeblingen.de.ibm.com (tuxmaker.boeblingen.de.ibm.com [9.152.85.9]) by d06av04.portsmouth.uk.ibm.com (8.14.4/8.14.4/NCO v10.0 AVin) with ESMTP id s9A9YvTU005544; Fri, 10 Oct 2014 03:35:39 -0600 From: Alexey Ishchuk To: linux-rdma@vger.kernel.org Cc: blaschka@linux.vnet.ibm.com, schwidefsky@de.ibm.com, gmuelas@de.ibm.com, utz.bacher@de.ibm.com, roland@kernel.org, yishaih@mellanox.com, Alexey Ishchuk Subject: [PATCH 3/3] libmlx4: add support for the s390x platform Date: Fri, 10 Oct 2014 11:34:17 +0200 Message-Id: <1412933657-52641-4-git-send-email-aishchuk@linux.vnet.ibm.com> X-Mailer: git-send-email 1.8.5.5 In-Reply-To: <1412933657-52641-1-git-send-email-aishchuk@linux.vnet.ibm.com> References: <1412933657-52641-1-git-send-email-aishchuk@linux.vnet.ibm.com> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 14101009-0013-0000-0000-0000016AED41 Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org X-Spam-Status: No, score=-7.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Since, s390x platform requires execution of privileged CPU instructions to work with PCI I/O memory, the PCI I/O memory cannot be directly accessed from the userspace programs via the mapped memory areas. The current implementation of the Inifiniband verbs uses mapped memory areas to write data to device UAR and Blueflame page to initiate the I/O operations, these verbs currently cannot be used on the s390x platfrom without modification. This patch contains the changes to the libmlx4 userspace Mellanox device driver library required to provide support for the DAPL API on the s390x platform. The original code that directly used mapped memory areas to access the PCI I/O memory of the Mellanox networking device is replaced with the new system call invocation for writing the data to mapped memory areas. Signed-off-by: Alexey Ishchuk --- Makefile.am | 2 Makefile.in | 2 src/doorbell.h | 8 ++- src/mlx4.h | 2 src/mmio.h | 115 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ src/qp.c | 17 -------- 6 files changed, 126 insertions(+), 20 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html --- a/Makefile.am +++ b/Makefile.am @@ -12,7 +12,7 @@ src_libmlx4_la_LDFLAGS = -avoid-version mlx4confdir = $(sysconfdir)/libibverbs.d mlx4conf_DATA = mlx4.driver -EXTRA_DIST = src/doorbell.h src/mlx4.h src/mlx4-abi.h src/wqe.h \ +EXTRA_DIST = src/doorbell.h src/mlx4.h src/mlx4-abi.h src/wqe.h src/mmio.h \ src/mlx4.map libmlx4.spec.in mlx4.driver dist-hook: libmlx4.spec --- a/Makefile.in +++ b/Makefile.in @@ -353,7 +353,7 @@ src_libmlx4_la_LDFLAGS = -avoid-version mlx4confdir = $(sysconfdir)/libibverbs.d mlx4conf_DATA = mlx4.driver -EXTRA_DIST = src/doorbell.h src/mlx4.h src/mlx4-abi.h src/wqe.h \ +EXTRA_DIST = src/doorbell.h src/mlx4.h src/mlx4-abi.h src/wqe.h src/mmio.h \ src/mlx4.map libmlx4.spec.in mlx4.driver all: config.h --- a/src/doorbell.h +++ b/src/doorbell.h @@ -33,6 +33,8 @@ #ifndef DOORBELL_H #define DOORBELL_H +#include "mmio.h" + #if SIZEOF_LONG == 8 #if __BYTE_ORDER == __LITTLE_ENDIAN @@ -45,7 +47,7 @@ static inline void mlx4_write64(uint32_t val[2], struct mlx4_context *ctx, int offset) { - *(volatile uint64_t *) (ctx->uar + offset) = MLX4_PAIR_TO_64(val); + mmio_writeq((unsigned long)(ctx->uar + offset), MLX4_PAIR_TO_64(val)); } #else @@ -53,8 +55,8 @@ static inline void mlx4_write64(uint32_t static inline void mlx4_write64(uint32_t val[2], struct mlx4_context *ctx, int offset) { pthread_spin_lock(&ctx->uar_lock); - *(volatile uint32_t *) (ctx->uar + offset) = val[0]; - *(volatile uint32_t *) (ctx->uar + offset + 4) = val[1]; + mmio_writel((unsigned long)(ctx->uar + offset), val[0]); + mmio_writel((unsigned long)(ctx->uar + offset + 4), val[1]); pthread_spin_unlock(&ctx->uar_lock); } --- a/src/mlx4.h +++ b/src/mlx4.h @@ -74,6 +74,8 @@ #define wc_wmb() asm volatile("sfence" ::: "memory") #elif defined(__ia64__) #define wc_wmb() asm volatile("fwb" ::: "memory") +#elif defined(__s390x__) +#define wc_wmb { asm volatile("" : : : "memory") } #else #define wc_wmb() wmb() #endif --- /dev/null +++ b/src/mmio.h @@ -0,0 +1,115 @@ +#ifndef MMIO_H +#define MMIO_H + +#include +#include +#include +#ifdef __s390x__ + +static inline long mmio_writeb(const unsigned long mmio_addr, + const uint8_t val) +{ + return syscall(__NR_s390_pci_mmio_write, mmio_addr, &val, sizeof(val)); +} + +static inline long mmio_writew(const unsigned long mmio_addr, + const uint16_t val) +{ + return syscall(__NR_s390_pci_mmio_write, mmio_addr, &val, sizeof(val)); +} + +static inline long mmio_writel(const unsigned long mmio_addr, + const uint32_t val) +{ + return syscall(__NR_s390_pci_mmio_write, mmio_addr, &val, sizeof(val)); +} + +static inline long mmio_writeq(const unsigned long mmio_addr, + const uint64_t val) +{ + return syscall(__NR_s390_pci_mmio_write, mmio_addr, &val, sizeof(val)); +} + +static inline long mmio_write(const unsigned long mmio_addr, + const void *val, + const size_t length) +{ + return syscall(__NR_s390_pci_mmio_write, mmio_addr, val, length); +} + +static inline long mmio_readb(const unsigned long mmio_addr, uint8_t *val) +{ + return syscall(__NR_s390_pci_mmio_read, mmio_addr, val, sizeof(*val)); +} + +static inline long mmio_readw(const unsigned long mmio_addr, uint16_t *val) +{ + return syscall(__NR_s390_pci_mmio_read, mmio_addr, val, sizeof(*val)); +} + +static inline long mmio_readl(const unsigned long mmio_addr, uint32_t *val) +{ + return syscall(__NR_s390_pci_mmio_read, mmio_addr, val, sizeof(*val)); +} + +static inline long mmio_readq(const unsigned long mmio_addr, uint64_t *val) +{ + return syscall(__NR_s390_pci_mmio_read, mmio_addr, val, sizeof(*val)); +} + +static inline long mmio_read(const unsigned long mmio_addr, + void *val, + const size_t length) +{ + return syscall(__NR_s390_pci_mmio_read, mmio_addr, val, length); +} + +static inline void mlx4_bf_copy(unsigned long *dst, + unsigned long *src, + unsigned bytecnt) +{ + mmio_write((unsigned long)dst, src, bytecnt); +} + +#else + +#define mmio_writeb(addr, value) \ + (*((volatile uint8_t *)addr) = value) +#define mmio_writew(addr, value) \ + (*((volatile uint16_t *)addr) = value) +#define mmio_writel(addr, value) \ + (*((volatile uint32_t *)addr) = value) +#define mmio_writeq(addr, value) \ + (*((volatile uint64_t *)addr) = value) +#define mmio_write(addr, value, length) \ + memcpy(addr, value, length) + +#define mmio_readb(addr, value) \ + (value = *((volatile uint8_t *)addr)) +#define mmio_readw(addr, value) \ + (value = *((volatile uint16_t *)addr)) +#define mmio_readl(addr, value) \ + (value = *((volatile uint32_t *)addr)) +#define mmio_readq(addr, value) \ + (value = *((volatile uint64_t *)addr)) +#define mmio_read(addr, value, length) \ + memcpy(value, addr, length) + +/* + * Avoid using memcpy() to copy to BlueFlame page, since memcpy() + * implementations may use move-string-buffer assembler instructions, + * which do not guarantee order of copying. + */ +static inline void mlx4_bf_copy(unsigned long *dst, + unsigned long *src, + unsigned bytecnt) +{ + while (bytecnt > 0) { + *dst++ = *src++; + *dst++ = *src++; + bytecnt -= 2 * sizeof(long); + } +} +#endif + +#endif --- a/src/qp.c +++ b/src/qp.c @@ -173,20 +173,6 @@ static void set_data_seg(struct mlx4_wqe dseg->byte_count = htonl(sg->length); } -/* - * Avoid using memcpy() to copy to BlueFlame page, since memcpy() - * implementations may use move-string-buffer assembler instructions, - * which do not guarantee order of copying. - */ -static void mlx4_bf_copy(unsigned long *dst, unsigned long *src, unsigned bytecnt) -{ - while (bytecnt > 0) { - *dst++ = *src++; - *dst++ = *src++; - bytecnt -= 2 * sizeof (long); - } -} - int mlx4_post_send(struct ibv_qp *ibqp, struct ibv_send_wr *wr, struct ibv_send_wr **bad_wr) { @@ -434,7 +420,8 @@ out: */ wmb(); - *(uint32_t *) (ctx->uar + MLX4_SEND_DOORBELL) = qp->doorbell_qpn; + mmio_writel((unsigned long)(ctx->uar + MLX4_SEND_DOORBELL), + qp->doorbell_qpn); } if (nreq)