diff options
author | Jason Gunthorpe <jgg@mellanox.com> | 2019-04-24 16:20:34 -0300 |
---|---|---|
committer | Jason Gunthorpe <jgg@mellanox.com> | 2019-04-24 16:20:34 -0300 |
commit | 449a224c10a48d047c799c5c5d3b22d6aec98c60 (patch) | |
tree | 7ecff2cce22ad3875b70a772eae55a443752cfce /net/ipv4/tcp_dctcp.c | |
parent | IB/hfi1: Remove reference to RHF.VCRCErr (diff) | |
parent | RDMA: Remove rdma_user_mmap_page (diff) | |
download | linux-dev-449a224c10a48d047c799c5c5d3b22d6aec98c60.tar.xz linux-dev-449a224c10a48d047c799c5c5d3b22d6aec98c60.zip |
Merge branch 'rdma_mmap' into rdma.git for-next
Jason Gunthorpe says:
====================
Upon review it turns out there are some long standing problems in BAR
mapping area:
* BAR pages intended for read-only can be switched to writable via mprotect.
* Missing use of rdma_user_mmap_io for the mlx5 clock BAR page.
* Disassociate causes SIGBUS when touching the pages.
* CPU pages are being mapped through to the process via remap_pfn_range
instead of the more appropriate vm_insert_page, causing weird behaviors
during disassociation.
This series adds the missing VM_* flag manipulation, adds faulting a zero
page for disassociation and revises the CPU page mappings to use
vm_insert_page.
====================
For dependencies this branch is based on for-rc from
git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git
* branch 'rdma_mmap':
RDMA: Remove rdma_user_mmap_page
RDMA/mlx5: Use get_zeroed_page() for clock_info
RDMA/ucontext: Fix regression with disassociate
RDMA/mlx5: Use rdma_user_map_io for mapping BAR pages
RDMA/mlx5: Do not allow the user to write to the clock page
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Diffstat (limited to 'net/ipv4/tcp_dctcp.c')
-rw-r--r-- | net/ipv4/tcp_dctcp.c | 36 |
1 files changed, 18 insertions, 18 deletions
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index cd4814f7e962..359da68d7c06 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -67,11 +67,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; module_param(dctcp_alpha_on_init, uint, 0644); MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value"); -static unsigned int dctcp_clamp_alpha_on_loss __read_mostly; -module_param(dctcp_clamp_alpha_on_loss, uint, 0644); -MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss, - "parameter for clamping alpha on loss"); - static struct tcp_congestion_ops dctcp_reno; static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) @@ -164,21 +159,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) } } -static void dctcp_state(struct sock *sk, u8 new_state) +static void dctcp_react_to_loss(struct sock *sk) { - if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) { - struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); - /* If this extension is enabled, we clamp dctcp_alpha to - * max on packet loss; the motivation is that dctcp_alpha - * is an indicator to the extend of congestion and packet - * loss is an indicator of extreme congestion; setting - * this in practice turned out to be beneficial, and - * effectively assumes total congestion which reduces the - * window by half. - */ - ca->dctcp_alpha = DCTCP_MAX_ALPHA; - } + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +static void dctcp_state(struct sock *sk, u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != inet_csk(sk)->icsk_ca_state) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ } static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) @@ -190,6 +187,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; default: /* Don't care for the rest. */ break; |