stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Neal Cardwell <ncardwell@google.com>,
	Yuchung Cheng <ycheng@google.com>,
	Soheil Hassas Yeganeh <soheil@google.com>,
	Beyers Cronje <bcronje@gmail.com>,
	"David S. Miller" <davem@davemloft.net>
Subject: [PATCH 4.9 26/92] tcp_bbr: fix pacing_gain to always be unity when using lt_bw
Date: Fri,  9 Feb 2018 14:38:55 +0100	[thread overview]
Message-ID: <20180209133933.136876360@linuxfoundation.org> (raw)
In-Reply-To: <20180209133931.211869118@linuxfoundation.org>

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

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

From: Neal Cardwell <ncardwell@google.com>


[ Upstream commit 3aff3b4b986e51bcf4ab249e5d48d39596e0df6a ]

This commit fixes the pacing_gain to remain at BBR_UNIT (1.0) when
using lt_bw and returning from the PROBE_RTT state to PROBE_BW.

Previously, when using lt_bw, upon exiting PROBE_RTT and entering
PROBE_BW the bbr_reset_probe_bw_mode() code could sometimes randomly
end up with a cycle_idx of 0 and hence have bbr_advance_cycle_phase()
set a pacing gain above 1.0. In such cases this would result in a
pacing rate that is 1.25x higher than intended, potentially resulting
in a high loss rate for a little while until we stop using the lt_bw a
bit later.

This commit is a stable candidate for kernels back as far as 4.9.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Reported-by: Beyers Cronje <bcronje@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv4/tcp_bbr.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -452,7 +452,8 @@ static void bbr_advance_cycle_phase(stru
 
 	bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1);
 	bbr->cycle_mstamp = tp->delivered_mstamp;
-	bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx];
+	bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT :
+					    bbr_pacing_gain[bbr->cycle_idx];
 }
 
 /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */
@@ -461,8 +462,7 @@ static void bbr_update_cycle_phase(struc
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
-	if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw &&
-	    bbr_is_next_cycle_phase(sk, rs))
+	if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs))
 		bbr_advance_cycle_phase(sk);
 }
 

  parent reply	other threads:[~2018-02-09 13:41 UTC|newest]

Thread overview: 113+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-09 13:38 [PATCH 4.9 00/92] 4.9.81-stable review Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 01/92] powerpc/pseries: Add H_GET_CPU_CHARACTERISTICS flags & wrapper Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 02/92] powerpc/64: Add macros for annotating the destination of rfid/hrfid Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 03/92] powerpc/64: Convert fast_exception_return to use RFI_TO_USER/KERNEL Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 04/92] powerpc/64: Convert the syscall exit path " Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 05/92] powerpc/64s: Convert slb_miss_common " Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 06/92] powerpc/64s: Add support for RFI flush of L1-D cache Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 07/92] powerpc/64s: Support disabling RFI flush with no_rfi_flush and nopti Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 08/92] powerpc/pseries: Query hypervisor for RFI flush settings Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 09/92] powerpc/powernv: Check device-tree " Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 10/92] powerpc/64s: Wire up cpu_show_meltdown() Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 11/92] powerpc/64s: Allow control of RFI flush via debugfs Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 12/92] auxdisplay: img-ascii-lcd: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 13/92] pinctrl: pxa: pxa2xx: " Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 14/92] ASoC: pcm512x: " Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 16/92] x86/pti: Make unpoison of pgd for trusted boot work for real Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 17/92] kaiser: allocate pgd with order 0 when pti=off Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 18/92] serial: core: mark port as initialized after successful IRQ change Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 19/92] ip6mr: fix stale iterator Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 20/92] net: igmp: add a missing rcu locking section Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 21/92] qlcnic: fix deadlock bug Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 23/92] r8169: fix RTL8168EP take too long to complete driver initialization Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 24/92] tcp: release sk_frag.page in tcp_disconnect Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 25/92] vhost_net: stop device during reset owner Greg Kroah-Hartman
2018-02-09 13:38 ` Greg Kroah-Hartman [this message]
2018-02-09 13:38 ` [PATCH 4.9 27/92] cls_u32: add missing RCU annotation Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 28/92] ipv6: Fix SO_REUSEPORT UDP socket with implicit sk_ipv6only Greg Kroah-Hartman
2018-02-09 13:38 ` [PATCH 4.9 30/92] x86/asm: Fix inline asm call constraints for GCC 4.4 Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 31/92] x86/microcode/AMD: Do not load when running on a hypervisor Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 32/92] media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 33/92] b43: Add missing MODULE_FIRMWARE() Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 34/92] KEYS: encrypted: fix buffer overread in valid_master_desc() Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 35/92] x86/retpoline: Remove the esp/rsp thunk Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 36/92] KVM: x86: Make indirect calls in emulator speculation safe Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 37/92] KVM: VMX: Make indirect call " Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 38/92] module/retpoline: Warn about missing retpoline in module Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 39/92] x86/cpufeatures: Add CPUID_7_EDX CPUID leaf Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 40/92] x86/cpufeatures: Add Intel feature bits for Speculation Control Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 41/92] x86/cpufeatures: Add AMD " Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 42/92] x86/msr: Add definitions for new speculation control MSRs Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 43/92] x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown Greg Kroah-Hartman
2018-02-13 13:34   ` Nick Lowe
2018-02-13 15:00     ` Greg Kroah-Hartman
2018-02-13 15:09       ` Arjan van de Ven
2018-02-13 15:27         ` Nick Lowe
2018-02-13 16:32           ` Greg Kroah-Hartman
2018-02-16 13:15             ` Nick Lowe
2018-02-16 16:56               ` Nick Lowe
2018-02-13 15:56         ` Andi Kleen
2018-02-13 16:02           ` Thomas Gleixner
2018-02-13 16:10             ` Borislav Petkov
2018-02-13 16:18           ` Dave Hansen
2018-02-09 13:39 ` [PATCH 4.9 44/92] x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 45/92] x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 46/92] x86/alternative: Print unadorned pointers Greg Kroah-Hartman
2018-02-09 22:01   ` Kees Cook
2018-02-10  7:23     ` Greg Kroah-Hartman
2018-02-10 19:14       ` Kees Cook
2018-02-10 19:21         ` Borislav Petkov
2018-02-13  9:16           ` Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 47/92] x86/nospec: Fix header guards names Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 48/92] x86/bugs: Drop one "mitigation" from dmesg Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 50/92] x86/cpufeatures: Clean up Spectre v2 related CPUID flags Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 51/92] x86/retpoline: Simplify vmexit_fill_RSB() Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 52/92] x86/spectre: Check CONFIG_RETPOLINE in command line parser Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 53/92] x86/entry/64: Remove the SYSCALL64 fast path Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 54/92] x86/entry/64: Push extra regs right away Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 55/92] x86/asm: Move status from thread_struct to thread_info Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 56/92] Documentation: Document array_index_nospec Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 57/92] array_index_nospec: Sanitize speculative array de-references Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 58/92] x86: Implement array_index_mask_nospec Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 59/92] x86: Introduce barrier_nospec Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 60/92] x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 61/92] x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end} Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 62/92] x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 63/92] x86/get_user: Use pointer masking to limit speculation Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 64/92] x86/syscall: Sanitize syscall table de-references under speculation Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 65/92] vfs, fdtable: Prevent bounds-check bypass via speculative execution Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 66/92] nl80211: Sanitize array index in parse_txq_params Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 67/92] x86/spectre: Report get_user mitigation for spectre_v1 Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 68/92] x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable" Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 69/92] x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 70/92] x86/paravirt: Remove noreplace-paravirt cmdline option Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 71/92] x86/kvm: Update spectre-v1 mitigation Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 72/92] x86/retpoline: Avoid retpolines for built-in __init functions Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 73/92] x86/spectre: Simplify spectre_v2 command line parsing Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 74/92] x86/pti: Mark constant arrays as __initconst Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 75/92] x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 76/92] KVM: nVMX: kmap() cant fail Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 77/92] KVM: nVMX: vmx_complete_nested_posted_interrupt() " Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 80/92] KVM: VMX: introduce alloc_loaded_vmcs Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 81/92] KVM: VMX: make MSR bitmaps per-VCPU Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 82/92] KVM/x86: Add IBPB support Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 83/92] KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 84/92] KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 85/92] KVM/SVM: " Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 87/92] ASoC: simple-card: Fix misleading error message Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 88/92] ASoC: rsnd: dont call free_irq() on Parent SSI Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 89/92] ASoC: rsnd: avoid duplicate free_irq() Greg Kroah-Hartman
2018-02-09 13:39 ` [PATCH 4.9 90/92] drm: rcar-du: Use the VBK interrupt for vblank events Greg Kroah-Hartman
2018-02-09 13:40 ` [PATCH 4.9 91/92] drm: rcar-du: Fix race condition when disabling planes at CRTC stop Greg Kroah-Hartman
2018-02-09 13:40 ` [PATCH 4.9 92/92] x86/microcode: Do the family check first Greg Kroah-Hartman
2018-02-09 20:18 ` [PATCH 4.9 00/92] 4.9.81-stable review Shuah Khan
2018-02-09 21:32 ` Dan Rue
2018-02-10 15:46 ` Guenter Roeck
2018-02-13  9:36   ` Greg Kroah-Hartman
2018-02-13 14:30     ` Guenter Roeck
2018-02-13 15:29       ` Greg Kroah-Hartman
2018-02-17 13:31         ` Yves-Alexis Perez
2018-02-17 13:45           ` Greg Kroah-Hartman
2018-02-17 17:35             ` Guenter Roeck
2018-02-18 17:25               ` Yves-Alexis Perez
2018-02-20 10:40               ` Greg Kroah-Hartman

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=20180209133933.136876360@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=bcronje@gmail.com \
    --cc=davem@davemloft.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ncardwell@google.com \
    --cc=soheil@google.com \
    --cc=stable@vger.kernel.org \
    --cc=ycheng@google.com \
    /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;
as well as URLs for NNTP newsgroup(s).