diff options
author | Akihiko Odaki <akihiko.odaki@daynix.com> | 2024-02-28 20:33:12 +0900 |
---|---|---|
committer | Michael S. Tsirkin <mst@redhat.com> | 2024-03-12 17:56:55 -0400 |
commit | 91bb64a8d2014fda33a81fcf0fce37340f0d3b0c (patch) | |
tree | 8faee6c9031349a521b04b5033607f67d519c91a | |
parent | 04f143d828845d0fd52dd4a52664d81a4f5431f7 (diff) | |
download | qemu-91bb64a8d2014fda33a81fcf0fce37340f0d3b0c.zip qemu-91bb64a8d2014fda33a81fcf0fce37340f0d3b0c.tar.gz qemu-91bb64a8d2014fda33a81fcf0fce37340f0d3b0c.tar.bz2 |
hw/nvme: Use pcie_sriov_num_vfs()
nvme_sriov_pre_write_ctrl() used to directly inspect SR-IOV
configurations to know the number of VFs being disabled due to SR-IOV
configuration writes, but the logic was flawed and resulted in
out-of-bound memory access.
It assumed PCI_SRIOV_NUM_VF always has the number of currently enabled
VFs, but it actually doesn't in the following cases:
- PCI_SRIOV_NUM_VF has been set but PCI_SRIOV_CTRL_VFE has never been.
- PCI_SRIOV_NUM_VF was written after PCI_SRIOV_CTRL_VFE was set.
- VFs were only partially enabled because of realization failure.
It is a responsibility of pcie_sriov to interpret SR-IOV configurations
and pcie_sriov does it correctly, so use pcie_sriov_num_vfs(), which it
provides, to get the number of enabled VFs before and after SR-IOV
configuration writes.
Cc: qemu-stable@nongnu.org
Fixes: CVE-2024-26328
Fixes: 11871f53ef8e ("hw/nvme: Add support for the Virtualization Management command")
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Message-Id: <20240228-reuse-v8-1-282660281e60@daynix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
-rw-r--r-- | hw/nvme/ctrl.c | 26 |
1 files changed, 8 insertions, 18 deletions
diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c index 76fe039..2860a9b 100644 --- a/hw/nvme/ctrl.c +++ b/hw/nvme/ctrl.c @@ -8466,36 +8466,26 @@ static void nvme_pci_reset(DeviceState *qdev) nvme_ctrl_reset(n, NVME_RESET_FUNCTION); } -static void nvme_sriov_pre_write_ctrl(PCIDevice *dev, uint32_t address, - uint32_t val, int len) +static void nvme_sriov_post_write_config(PCIDevice *dev, uint16_t old_num_vfs) { NvmeCtrl *n = NVME(dev); NvmeSecCtrlEntry *sctrl; - uint16_t sriov_cap = dev->exp.sriov_cap; - uint32_t off = address - sriov_cap; - int i, num_vfs; + int i; - if (!sriov_cap) { - return; - } - - if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) { - if (!(val & PCI_SRIOV_CTRL_VFE)) { - num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF); - for (i = 0; i < num_vfs; i++) { - sctrl = &n->sec_ctrl_list.sec[i]; - nvme_virt_set_state(n, le16_to_cpu(sctrl->scid), false); - } - } + for (i = pcie_sriov_num_vfs(dev); i < old_num_vfs; i++) { + sctrl = &n->sec_ctrl_list.sec[i]; + nvme_virt_set_state(n, le16_to_cpu(sctrl->scid), false); } } static void nvme_pci_write_config(PCIDevice *dev, uint32_t address, uint32_t val, int len) { - nvme_sriov_pre_write_ctrl(dev, address, val, len); + uint16_t old_num_vfs = pcie_sriov_num_vfs(dev); + pci_default_write_config(dev, address, val, len); pcie_cap_flr_write_config(dev, address, val, len); + nvme_sriov_post_write_config(dev, old_num_vfs); } static const VMStateDescription nvme_vmstate = { |