mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Kamal Mostafa <kamal@canonical.com>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org,
	kernel-team@lists.ubuntu.com
Cc: Honggang Li <honli@redhat.com>,
	Doug Ledford <dledford@redhat.com>,
	Kamal Mostafa <kamal@canonical.com>
Subject: [PATCH 3.13.y-ckt 89/95] mlx5: wrong page mask if CONFIG_ARCH_DMA_ADDR_T_64BIT enabled for 32Bit architectures
Date: Wed, 27 May 2015 12:00:37 -0700	[thread overview]
Message-ID: <1432753243-16151-90-git-send-email-kamal@canonical.com> (raw)
In-Reply-To: <1432753243-16151-1-git-send-email-kamal@canonical.com>

3.13.11-ckt21 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Honggang LI <honli@redhat.com>

commit 59d2d18cc4e9ba30b370db18d0e02d792699da96 upstream.

If CONFIG_ARCH_DMA_ADDR_T_64BIT enabled for x86 systems and physical
memory is more than 4GB, dma_map_page may return a valid memory
address which greater than 0xffffffff. As a result, the mlx5 device page
allocator RB tree will be initialized with valid addresses greater than
0xfffffff.

However, (addr & PAGE_MASK) set the high four bytes to zeros. So, it's
impossible for the function, free_4k, to release the pages whose
addresses greater than 4GB. Memory leaks. And mlx5_ib module can't
release the pages when user try to remove the module, as a result,
system hang.

[root@rdma05 root]# dmesg  | grep addr | head
addr             = 3fe384000
addr & PAGE_MASK =  fe384000
[root@rdma05 root]# rmmod mlx5_ib   <---- hang on

---------------------- cosnole log -----------------
mlx5_ib 0000:04:00.0: irq 138 for MSI/MSI-X
  alloc irq_desc for 139 on node -1
  alloc kstat_irqs on node -1
mlx5_ib 0000:04:00.0: irq 139 for MSI/MSI-X
0000:04:00.0:free_4k:221:(pid 1519): page not found
0000:04:00.0:free_4k:221:(pid 1519): page not found
0000:04:00.0:free_4k:221:(pid 1519): page not found
0000:04:00.0:free_4k:221:(pid 1519): page not found
---------------------- cosnole log -----------------

Fixes: bf0bf77f6519 ('mlx5: Support communicating arbitrary host page size to firmware')
Signed-off-by: Honggang Li <honli@redhat.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 9959199..b3202b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -213,26 +213,28 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
 	return 0;
 }
 
+#define MLX5_U64_4K_PAGE_MASK ((~(u64)0U) << PAGE_SHIFT)
+
 static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 {
 	struct fw_page *fwp;
 	int n;
 
-	fwp = find_fw_page(dev, addr & PAGE_MASK);
+	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
 	if (!fwp) {
 		mlx5_core_warn(dev, "page not found\n");
 		return;
 	}
 
-	n = (addr & ~PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
+	n = (addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
 	fwp->free_count++;
 	set_bit(n, &fwp->bitmask);
 	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) {
 		rb_erase(&fwp->rb_node, &dev->priv.page_root);
 		if (fwp->free_count != 1)
 			list_del(&fwp->list);
-		dma_unmap_page(&dev->pdev->dev, addr & PAGE_MASK, PAGE_SIZE,
-			       DMA_BIDIRECTIONAL);
+		dma_unmap_page(&dev->pdev->dev, addr & MLX5_U64_4K_PAGE_MASK,
+			       PAGE_SIZE, DMA_BIDIRECTIONAL);
 		__free_page(fwp->page);
 		kfree(fwp);
 	} else if (fwp->free_count == 1) {
-- 
1.9.1


  parent reply	other threads:[~2015-05-27 19:04 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-27 18:59 [3.13.y-ckt stable] Linux 3.13.11-ckt21 stable review Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 01/95] [3.13-stable only] Revert "gianfar: Carefully free skbs in functions called by netpoll." Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 02/95] Bluetooth: ath3k: Add support Atheros AR5B195 combo Mini PCIe card Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 03/95] power_supply: twl4030_madc: Check return value of power_supply_register Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 04/95] power_supply: lp8788-charger: Fix leaked power supply on probe fail Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 05/95] ARM: dts: dove: Fix uart[23] reg property Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 06/95] xtensa: xtfpga: fix hardware lockup caused by LCD driver Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 07/95] Drivers: hv: vmbus: Fix a bug in the error path in vmbus_open() Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 08/95] xtensa: provide __NR_sync_file_range2 instead of __NR_sync_file_range Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 09/95] KVM: s390: Zero out current VMDB of STSI before including level3 data Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 10/95] usb: musb: core: fix TX/RX endpoint order Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 11/95] drm/radeon: fix doublescan modes (v2) Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 12/95] usb: phy: Find the right match in devm_usb_phy_match Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 13/95] x86: kvm: Revert "remove sched notifier for cross-cpu migrations" Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 14/95] tools lib traceevent kbuffer: Remove extra update to data pointer in PADDING Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 15/95] ring-buffer: Replace this_cpu_*() with __this_cpu_*() Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 16/95] ASoC: wm8741: Fix rates constraints values Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 17/95] cdc-wdm: fix endianness bug in debug statements Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 18/95] staging: panel: fix lcd type Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 19/95] UBI: account for bitflips in both the VID header and data Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 20/95] UBI: fix out of bounds write Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 21/95] UBI: initialize LEB number variable Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 22/95] UBI: fix check for "too many bytes" Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 23/95] ARM: S3C64XX: Use fixed IRQ bases to avoid conflicts on Cragganmore Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 24/95] ASoC: davinci-evm: drop un-necessary remove function Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 25/95] iscsi-target: Convert iscsi_thread_set usage to kthread.h Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 26/95] Drivers: hv: vmbus: Don't wait after requesting offers Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 27/95] Btrfs: fix log tree corruption when fs mounted with -o discard Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 28/95] btrfs: don't accept bare namespace as a valid xattr Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 29/95] ARM: 8320/1: fix integer overflow in ELF_ET_DYN_BASE Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 30/95] rtlwifi: rtl8192cu: Add new USB ID Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 31/95] MIPS: Hibernate: flush TLB entries earlier Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 32/95] ASoC: cs4271: Increase delay time after reset Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 33/95] [media] stk1160: Make sure current buffer is released Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 34/95] mnt: Improve the umount_tree flags Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 35/95] ext4: make fsync to sync parent dir in no-journal for real this time Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 36/95] Input: elantech - fix absolute mode setting on some ASUS laptops Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 37/95] usb: define a generic USB_RESUME_TIMEOUT macro Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 38/95] usb: host: xhci: use new USB_RESUME_TIMEOUT Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 39/95] usb: host: ehci: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 40/95] usb: host: uhci: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 41/95] usb: musb: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 42/95] usb: host: isp116x: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 43/95] usb: host: fotg210: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 44/95] usb: host: fusbh200: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 45/95] usb: host: oxu210hp: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 46/95] usb: host: r8a66597: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 47/95] usb: host: sl811: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 48/95] usb: dwc2: hcd: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 49/95] usb: isp1760: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 50/95] usb: core: hub: " Kamal Mostafa
2015-05-27 18:59 ` [PATCH 3.13.y-ckt 51/95] iser-target: Fix possible deadlock in RDMA_CM connection error Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 52/95] x86: vdso: fix pvclock races with task migration Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 53/95] gpio: mvebu: Fix mask/unmask managment per irq chip type Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 54/95] scsi: storvsc: Fix a bug in copy_from_bounce_buffer() Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 55/95] ALSA: emu10k1: don't deadlock in proc-functions Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 56/95] xtensa: ISS: fix locking in TAP network adapter Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 57/95] s390/hibernate: fix save and restore of kernel text section Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 58/95] Btrfs: fix inode eviction infinite loop after extent_same ioctl Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 59/95] Btrfs: fix inode eviction infinite loop after cloning into it Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 60/95] powerpc/perf: Cap 64bit userspace backtraces to PERF_MAX_STACK_DEPTH Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 61/95] ACPICA: Utilities: split IO address types from data type models Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 62/95] drm/i915: Dont enable CS_PARSER_ERROR interrupts at all Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 63/95] target: Fix COMPARE_AND_WRITE with SG_TO_MEM_NOALLOC handling Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 64/95] mm/hugetlb: use pmd_page() in follow_huge_pmd() Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 65/95] fs/binfmt_elf.c: fix bug in loading of PIE binaries Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 66/95] IB/core: disallow registering 0-sized memory region Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 67/95] IB/core: don't disallow registering region starting at 0x0 Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 68/95] ptrace: fix race between ptrace_resume() and wait_task_stopped() Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 69/95] mvsas: fix panic on expander attached SATA devices Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 70/95] drm/i915: cope with large i2c transfers Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 71/95] RCU pathwalk breakage when running into a symlink overmounting something Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 72/95] compal-laptop: Check return value of power_supply_register Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 73/95] sched/idle/x86: Restore mwait_idle() to fix boot hangs, to improve power savings and to improve performance Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 74/95] nfs: don't call blocking operations while !TASK_RUNNING Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 75/95] nfs: fix high load average due to callback thread sleeping Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 76/95] e1000: add dummy allocator to fix race condition between mtu change and netpoll Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 77/95] wl18xx: show rx_frames_per_rates as an array as it really is Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 78/95] lib: memzero_explicit: use barrier instead of OPTIMIZER_HIDE_VAR Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 79/95] driver core: bus: Goto appropriate labels on failure in bus_add_device Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 80/95] C6x: time: Ensure consistency in __init Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 81/95] crypto: omap-aes - Fix support for unequal lengths Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 82/95] jhash: Update jhash_[321]words functions to use correct initval Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 83/95] KVM: use slowpath for cross page cached accesses Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 84/95] powerpc: Fix missing L2 cache size in /sys/devices/system/cpu Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 85/95] NFS: fix BUG() crash in notify_change() with patch to chown_common() Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 86/95] i2c: core: Export bus recovery functions Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 87/95] IB/mlx4: Fix WQE LSO segment calculation Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 88/95] mlx5_core: Fix PowerPC support Kamal Mostafa
2015-05-27 19:00 ` Kamal Mostafa [this message]
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 90/95] skbuff: Do not scrub skb mark within the same name space Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 91/95] firmware/ihex2fw.c: restore missing default in switch statement Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 92/95] memstick: mspro_block: add missing curly braces Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 93/95] tools/power turbostat: Use $(CURDIR) instead of $(PWD) and add support for O= option in Makefile Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 94/95] ext4: fix data corruption caused by unwritten and delayed extents Kamal Mostafa
2015-05-27 19:00 ` [PATCH 3.13.y-ckt 95/95] powerpc: Add vr save/restore functions Kamal Mostafa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1432753243-16151-90-git-send-email-kamal@canonical.com \
    --to=kamal@canonical.com \
    --cc=dledford@redhat.com \
    --cc=honli@redhat.com \
    --cc=kernel-team@lists.ubuntu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®