September 2024 - Linux-stable-mirror

[PATCH v2 2/2] ufs: core: requeue MCQ abort request

by peter.wang＠mediatek.com

From: Peter Wang <peter.wang(a)mediatek.com> MCQ aborts a command using two methods below: 1. Nullified UTRD, Host controller skips this transfer request, reply Completion Queue entry to Host SW with OCS=ABORTED 2. SQ cleanup, The host controller will post to the Completion Queue to update the OCS field with ABORTED. For these two cases, set a flag to notify SCSI to requeue the command after receiving OCS_ABORTED. Fixes: ab248643d3d6 ("scsi: ufs: core: Add error handling for MCQ mode") Cc: stable(a)vger.kernel.org Signed-off-by: Peter Wang <peter.wang(a)mediatek.com> --- drivers/ufs/core/ufs-mcq.c | 1 + drivers/ufs/core/ufshcd.c | 21 ++++++++------------- include/ufs/ufshcd.h | 2 ++ 3 files changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index afd9541f4bd8..abdc55a8b960 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -642,6 +642,7 @@ static bool ufshcd_mcq_sqe_search(struct ufs_hba *hba, match = le64_to_cpu(utrd->command_desc_base_addr) & CQE_UCD_BA; if (addr == match) { ufshcd_mcq_nullify_sqe(utrd); + lrbp->host_initiate_abort = true; ret = true; goto out; } diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index a6f818cdef0e..fadea691d69d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -3006,6 +3006,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) ufshcd_prepare_lrbp_crypto(scsi_cmd_to_rq(cmd), lrbp); lrbp->req_abort_skip = false; + lrbp->host_initiate_abort = false; ufshcd_comp_scsi_upiu(hba, lrbp); @@ -5404,7 +5405,10 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, } break; case OCS_ABORTED: - result |= DID_ABORT << 16; + if (lrbp->host_initiate_abort) + result |= DID_REQUEUE << 16; + else + result |= DID_ABORT << 16; break; case OCS_INVALID_COMMAND_STATUS: result |= DID_REQUEUE << 16; @@ -6472,24 +6476,15 @@ static bool ufshcd_abort_one(struct request *rq, void *priv) struct Scsi_Host *shost = sdev->host; struct ufs_hba *hba = shost_priv(shost); struct ufshcd_lrb *lrbp = &hba->lrb[tag]; - struct ufs_hw_queue *hwq; - unsigned long flags; *ret = ufshcd_try_to_abort_task(hba, tag); dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag, hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1, *ret ? "failed" : "succeeded"); - /* Release cmd in MCQ mode if abort succeeds */ - if (hba->mcq_enabled && (*ret == 0)) { - hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(lrbp->cmd)); - if (!hwq) - return 0; - spin_lock_irqsave(&hwq->cq_lock, flags); - if (ufshcd_cmd_inflight(lrbp->cmd)) - ufshcd_release_scsi_cmd(hba, lrbp); - spin_unlock_irqrestore(&hwq->cq_lock, flags); - } + /* Host will post to CQ with OCS_ABORTED after SQ cleanup */ + if (hba->mcq_enabled && (*ret == 0)) + lrbp->host_initiate_abort = true; return *ret == 0; } diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 0fd2aebac728..49dd5ca8a4e7 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -173,6 +173,7 @@ struct ufs_pm_lvl_states { * @crypto_key_slot: the key slot to use for inline crypto (-1 if none) * @data_unit_num: the data unit number for the first block for inline crypto * @req_abort_skip: skip request abort task flag + * @host_initiate_abort: Abort flag initiated by host */ struct ufshcd_lrb { struct utp_transfer_req_desc *utr_descriptor_ptr; @@ -202,6 +203,7 @@ struct ufshcd_lrb { #endif bool req_abort_skip; + bool host_initiate_abort; }; /** -- 2.45.2

1 week, 4 days

3
2
0 0

Re: Patch "irqchip/gic-v4: Make sure a VPE is locked when VMAPP is issued" has been added to the 6.6-stable tree

by Marc Zyngier

On Sun, 08 Sep 2024 14:36:37 +0100, Sasha Levin <sashal(a)kernel.org> wrote: > > This is a note to let you know that I've just added the patch titled > > irqchip/gic-v4: Make sure a VPE is locked when VMAPP is issued > > to the 6.6-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > irqchip-gic-v4-make-sure-a-vpe-is-locked-when-vmapp-.patch > and it can be found in the queue-6.6 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. > > > > commit 1a232324773145ff7ce59b6a1b52b3247223f9d4 > Author: Marc Zyngier <maz(a)kernel.org> > Date: Fri Jul 5 10:31:55 2024 +0100 > > irqchip/gic-v4: Make sure a VPE is locked when VMAPP is issued > > [ Upstream commit a84a07fa3100d7ad46a3d6882af25a3df9c9e7e3 ] > > In order to make sure that vpe->col_idx is correctly sampled when a VMAPP > command is issued, the vpe_lock must be held for the VPE. This is now > possible since the introduction of the per-VM vmapp_lock, which can be > taken before vpe_lock in the correct locking order. > > Signed-off-by: Marc Zyngier <maz(a)kernel.org> > Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> > Tested-by: Nianyao Tang <tangnianyao(a)huawei.com> > Link: https://lore.kernel.org/r/20240705093155.871070-4-maz@kernel.org > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c > index e25dea0e50c7..1e0f0e1bf481 100644 > --- a/drivers/irqchip/irq-gic-v3-its.c > +++ b/drivers/irqchip/irq-gic-v3-its.c > @@ -1804,7 +1804,9 @@ static void its_map_vm(struct its_node *its, struct its_vm *vm) > for (i = 0; i < vm->nr_vpes; i++) { > struct its_vpe *vpe = vm->vpes[i]; > > - its_send_vmapp(its, vpe, true); > + scoped_guard(raw_spinlock, &vpe->vpe_lock) > + its_send_vmapp(its, vpe, true); > + > its_send_vinvall(its, vpe); > } > } > @@ -1825,8 +1827,10 @@ static void its_unmap_vm(struct its_node *its, struct its_vm *vm) > if (!--vm->vlpi_count[its->list_nr]) { > int i; > > - for (i = 0; i < vm->nr_vpes; i++) > + for (i = 0; i < vm->nr_vpes; i++) { > + guard(raw_spinlock)(&vm->vpes[i]->vpe_lock); > its_send_vmapp(its, vm->vpes[i], false); > + } > } > > raw_spin_unlock_irqrestore(&vmovp_lock, flags); > No please. Not only you are missing the essential part of the series (the patch introducing the per-VM lock that this change relies on), you are also missing the fixes that followed. So please drop this patch from the 6.6 and 6.1 queues. M. -- Without deviation from the norm, progress is not possible.

1 week, 4 days

2
1
0 0

Re: Patch "bcachefs: Add error code to defer option parsing" has been added to the 6.10-stable tree

by Kent Overstreet

On Sun, Sep 08, 2024 at 09:25:58AM GMT, Sasha Levin wrote: > This is a note to let you know that I've just added the patch titled > > bcachefs: Add error code to defer option parsing ??? Sasha, this and the other patch aren't bugfixes at all, they're prep work for the new mount API, i.e. feature work. Please just drop the bcachefs patches from stable entirely; the lockless IO patch revert is a fix but I'll be sending that with a couple other fixes in a day or so.

1 week, 4 days

2
1
0 0

Re: Patch "wifi: mt76: mt7921: fix NULL pointer access in mt7921_ipv6_addr_change" has been added to the 6.6-stable tree

by Bert Karwatzki

Am Sonntag, dem 08.09.2024 um 09:37 -0400 schrieb Sasha Levin: > This is a note to let you know that I've just added the patch titled > > wifi: mt76: mt7921: fix NULL pointer access in mt7921_ipv6_addr_change > > to the 6.6-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > wifi-mt76-mt7921-fix-null-pointer-access-in-mt7921_i.patch > and it can be found in the queue-6.6 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. > > > > commit 857d7854c40324bfc70a6d32c9eb0792bc7c0b56 > Author: Bert Karwatzki <spasswolf(a)web.de> > Date: Mon Aug 12 12:45:41 2024 +0200 > > wifi: mt76: mt7921: fix NULL pointer access in mt7921_ipv6_addr_change > > [ Upstream commit 479ffee68d59c599f8aed8fa2dcc8e13e7bd13c3 ] > > When disabling wifi mt7921_ipv6_addr_change() is called as a notifier. > At this point mvif->phy is already NULL so we cannot use it here. > > Signed-off-by: Bert Karwatzki <spasswolf(a)web.de> > Signed-off-by: Felix Fietkau <nbd(a)nbd.name> > Signed-off-by: Kalle Valo <kvalo(a)kernel.org> > Link: https://patch.msgid.link/20240812104542.80760-1-spasswolf@web.de > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c > index 6a5c2cae087d..6dec54431312 100644 > --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c > +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c > @@ -1095,7 +1095,7 @@ static void mt7921_ipv6_addr_change(struct ieee80211_hw *hw, > struct inet6_dev *idev) > { > struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; > - struct mt792x_dev *dev = mvif->phy->dev; > + struct mt792x_dev *dev = mt792x_hw_dev(hw); > struct inet6_ifaddr *ifa; > struct in6_addr ns_addrs[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; > struct sk_buff *skb; The patch is only fixes a NULL pointer if the tree also contains this commit: commit 574e609c4e6a0843a9ed53de79e00da8fb3e7437 Author: Felix Fietkau <nbd(a)nbd.name> Date: Thu Jul 4 15:09:47 2024 +0200 wifi: mac80211: clear vif drv_priv after remove_interface when stopping Avoid reusing stale driver data when an interface is brought down and up again. In order to avoid having to duplicate the memset in every single driver, do it here. Signed-off-by: Felix Fietkau <nbd(a)nbd.name> Link: https://patch.msgid.link/20240704130947.48609-1-nbd@nbd.name Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> In trees which do not contain this the patch is not necessary. Bert Karwatzki

1 week, 4 days

2
3
0 0

Please pick up "intel: legacy: Partial revert of field get conversion" for 6.6

by Florian Larysch

The patch "intel: legacy: Partial revert of field get conversion" (commit ba54b1a276a6b69d80649942fe5334d19851443e in mainline) fixes a broken refactoring that prevents Wake-on-LAN from working on some e1000e devices. v6.10 already includes that fix and v6.1 and earlier did not yet contain the offending refactoring, so it should only be necessary to apply this to 6.6. Thanks!

1 week, 4 days

2
1
0 0

FAILED: patch "[PATCH] mm/memcontrol: respect zswap.writeback setting from parent cg" failed to apply to 6.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.10.y git checkout FETCH_HEAD git cherry-pick -x e399257349098bf7c84343f99efb2bc9c22eb9fd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024090839-crimp-posted-6a31@gregkh' --subject-prefix 'PATCH 6.10.y' HEAD^.. Possible dependencies: e39925734909 ("mm/memcontrol: respect zswap.writeback setting from parent cg too") 2b33a97c94bc ("mm: zswap: rename is_zswap_enabled() to zswap_is_enabled()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e399257349098bf7c84343f99efb2bc9c22eb9fd Mon Sep 17 00:00:00 2001 From: Mike Yuan <me(a)yhndnzj.com> Date: Fri, 23 Aug 2024 16:27:06 +0000 Subject: [PATCH] mm/memcontrol: respect zswap.writeback setting from parent cg too MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, the behavior of zswap.writeback wrt. the cgroup hierarchy seems a bit odd. Unlike zswap.max, it doesn't honor the value from parent cgroups. This surfaced when people tried to globally disable zswap writeback, i.e. reserve physical swap space only for hibernation [1] - disabling zswap.writeback only for the root cgroup results in subcgroups with zswap.writeback=1 still performing writeback. The inconsistency became more noticeable after I introduced the MemoryZSwapWriteback= systemd unit setting [2] for controlling the knob. The patch assumed that the kernel would enforce the value of parent cgroups. It could probably be workarounded from systemd's side, by going up the slice unit tree and inheriting the value. Yet I think it's more sensible to make it behave consistently with zswap.max and friends. [1] https://wiki.archlinux.org/title/Power_management/Suspend_and_hibernate#Dis… [2] https://github.com/systemd/systemd/pull/31734 Link: https://lkml.kernel.org/r/20240823162506.12117-1-me@yhndnzj.com Fixes: 501a06fe8e4c ("zswap: memcontrol: implement zswap writeback disabling") Signed-off-by: Mike Yuan <me(a)yhndnzj.com> Reviewed-by: Nhat Pham <nphamcs(a)gmail.com> Acked-by: Yosry Ahmed <yosryahmed(a)google.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Michal Koutný <mkoutny(a)suse.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Roman Gushchin <roman.gushchin(a)linux.dev> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 86311c2907cd..95c18bc17083 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1717,9 +1717,10 @@ The following nested keys are defined. entries fault back in or are written out to disk. memory.zswap.writeback - A read-write single value file. The default value is "1". The - initial value of the root cgroup is 1, and when a new cgroup is - created, it inherits the current value of its parent. + A read-write single value file. The default value is "1". + Note that this setting is hierarchical, i.e. the writeback would be + implicitly disabled for child cgroups if the upper hierarchy + does so. When this is set to 0, all swapping attempts to swapping devices are disabled. This included both zswap writebacks, and swapping due diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f29157288b7d..d563fb515766 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3613,8 +3613,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) memcg1_soft_limit_reset(memcg); #ifdef CONFIG_ZSWAP memcg->zswap_max = PAGE_COUNTER_MAX; - WRITE_ONCE(memcg->zswap_writeback, - !parent || READ_ONCE(parent->zswap_writeback)); + WRITE_ONCE(memcg->zswap_writeback, true); #endif page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { @@ -5320,7 +5319,14 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) { /* if zswap is disabled, do not block pages going to the swapping device */ - return !zswap_is_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback); + if (!zswap_is_enabled()) + return true; + + for (; memcg; memcg = parent_mem_cgroup(memcg)) + if (!READ_ONCE(memcg->zswap_writeback)) + return false; + + return true; } static u64 zswap_current_read(struct cgroup_subsys_state *css,

1 week, 4 days

2
1
0 0

linux-6.6.y regression on amd-pstate

by Mario Limonciello

+ stable + regressions New subject Great news. Greg, Sasha, Can you please pull in these 3 commits specifically to 6.6.y to fix a regression that was reported by Morgan in 6.6.y: commit 12753d71e8c5 ("ACPI: CPPC: Add helper to get the highest performance value") commit ed429c686b79 ("cpufreq: amd-pstate: Enable amd-pstate preferred core support") commit 3d291fe47fe1 ("cpufreq: amd-pstate: fix the highest frequency issue which limits performance") Further details are below. Thanks! On 9/5/2024 16:09, Jones, Morgan wrote: > Mario, > > Confirmed. Thank you for the help! Slightly different refs on my end: > > Remotes: > > next https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git (fetch) > next https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git (push) > origin git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git (fetch) > origin git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git (push) > superm1 https://git.kernel.org/pub/scm/linux/kernel/git/superm1/linux.git/ (fetch) > superm1 https://git.kernel.org/pub/scm/linux/kernel/git/superm1/linux.git/ (push) > torvalds git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git (fetch) > torvalds git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git (push) > > Patches: > > git format-patch 12753d71e8c5^..12753d71e8c5 > git format-patch f3a052391822b772b4e27f2594526cf1eb103cab^..f3a052391822b772b4e27f2594526cf1eb103cab > git format-patch bf202e654bfa57fb8cf9d93d4c6855890b70b9c4^..bf202e654bfa57fb8cf9d93d4c6855890b70b9c4 > > Results: > > Linux redact 6.6.48 #1-NixOS SMP PREEMPT_DYNAMIC Tue Jan 1 00:00:00 UTC 1980 x86_64 GNU/Linux > > analyzing CPU 56: > driver: amd-pstate-epp > CPUs which run at the same hardware frequency: 56 > CPUs which need to have their frequency coordinated by software: 56 > maximum transition latency: Cannot determine or is not supported. > hardware limits: 400 MHz - 3.35 GHz > available cpufreq governors: performance powersave > current policy: frequency should be within 400 MHz and 3.35 GHz. > The governor "performance" may decide which speed to use > within this range. > current CPU frequency: Unable to call hardware > current CPU frequency: 2.09 GHz (asserted by call to kernel) > boost state support: > Supported: yes > Active: yes > AMD PSTATE Highest Performance: 255. Maximum Frequency: 3.35 GHz. > AMD PSTATE Nominal Performance: 152. Nominal Frequency: 2.00 GHz. > AMD PSTATE Lowest Non-linear Performance: 115. Lowest Non-linear Frequency: 1.51 GHz. > AMD PSTATE Lowest Performance: 31. Lowest Frequency: 400 MHz. > > And our builds are back to being fast with `amd_pstate=active amd_prefcore=enable amd_pstate.shared_mem=1`. > > Morgan > > -----Original Message----- > From: Mario Limonciello <mario.limonciello(a)amd.com> > Sent: Thursday, September 5, 2024 8:12 AM > To: Jones, Morgan <Morgan.Jones(a)viasat.com> > Cc: linux-pm(a)vger.kernel.org; linux-kernel(a)vger.kernel.org; David Arcari <darcari(a)redhat.com>; Dhananjay Ugwekar <Dhananjay.Ugwekar(a)amd.com>; rafael(a)kernel.org; viresh.kumar(a)linaro.org; gautham.shenoy(a)amd.com; perry.yuan(a)amd.com; skhan(a)linuxfoundation.org; li.meng(a)amd.com; ray.huang(a)amd.com > Subject: Re: [EXTERNAL] Re: [PATCH v2 2/2] cpufreq/amd-pstate: Fix the scaling_max_freq setting on shared memory CPPC systems > > Hi Morgan, > > Please apply these 3 commits: > > commit 12753d71e8c5 ("ACPI: CPPC: Add helper to get the highest performance value") commit ed429c686b79 ("cpufreq: amd-pstate: Enable amd-pstate preferred core support") commit 3d291fe47fe1 ("cpufreq: amd-pstate: fix the highest frequency issue which limits performance") > > The first two should help your system, the third will prevent introducing a regression on a different one. > > Assuming that works we should ask @stable to pull all 3 in to fix this regression. > > Thanks, > > On 9/4/2024 08:57, Mario Limonciello wrote: >> Morgan, >> >> I was referring specfiically to the version that landed in Linus' tree: >> https://urldefense.us/v3/__https://git.kernel.org/torvalds/c/8164f7433 >> 264__;!!C5Asm8uRnZQmlRln!aIZEDEbIUKD7OrxN0b0KjoqKYDL2yMkwk4EK7x_oSnyHQ >> 6MEq7yt6JHjd0TD9DgEYEWDcF58OKL8c7G11bT3dSqL8eM$ >> >> But yeah it's effectively the same thing. In any case, it's not the >> solution. >> >> We had some internal discussion and suspect this is due to missing >> prefcore patches in 6.6 as that feature landed in 6.9. We'll try to >> reproduce this on a Rome system and come back with our findings and >> suggestions what to do. >> >> Thanks, >> >

1 week, 4 days

3
3
0 0

Re: XFS mount timeout in linux-6.9.11

by David Woodhouse

On Tue, 2024-08-13 at 08:25 -0700, Darrick J. Wong wrote: > On Tue, Aug 13, 2024 at 04:59:25PM +0200, Christoph Hellwig wrote: > > On Tue, Aug 13, 2024 at 07:19:28PM +1000, Dave Chinner wrote: > > > In hindsight, this was a wholly avoidable bug - a single patch made > > > two different API modifications that only differed by a single > > > letter, and one of the 23 conversions missed a single letter. If > > > that was two patches - one for the finobt conversion, the second for > > > the inobt conversion, the bug would have been plainly obvious during > > > review.... > > > > Maybe we should avoid identifiers that close anyway :) > > > > The change looks good: > > > > Reviewed-by: Christoph Hellwig <hch(a)lst.de> > > Looks good to me too > Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Is it (now commit 95179935bea) going to -stable too?

1 week, 4 days

2
1
0 0

[PATCH][6.1][0/2] io_uring: Do not set PF_NO_SETAFFINITY on poller threads

by Felix Moessbauer

Setting the PF_NO_SETAFFINITY flag creates problems in combination with cpuset operations (see commit messages for details). To mitigate this, fixes have been written to remove the flag from the poller threads, which landed in v6.3. We need them in v6.1 as well. Best regards, Felix Moessbauer Siemens AG Jens Axboe (1): io_uring/io-wq: stop setting PF_NO_SETAFFINITY on io-wq workers Michal Koutný (1): io_uring/sqpoll: Do not set PF_NO_SETAFFINITY on sqpoll threads io_uring/io-wq.c | 16 +++++++++++----- io_uring/sqpoll.c | 1 - 2 files changed, 11 insertions(+), 6 deletions(-) -- 2.39.2

1 week, 4 days

3
4
0 0

[PATCH 6.6 4/4] riscv: Use accessors to page table entries instead of direct dereference

by WangYuli

From: Alexandre Ghiti <alexghiti(a)rivosinc.com> [ Upstream commit edf955647269422e387732870d04fc15933a25ea ] As very well explained in commit 20a004e7b017 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing page tables"), an architecture whose page table walker can modify the PTE in parallel must use READ_ONCE()/WRITE_ONCE() macro to avoid any compiler transformation. So apply that to riscv which is such architecture. Signed-off-by: Alexandre Ghiti <alexghiti(a)rivosinc.com> Acked-by: Anup Patel <anup(a)brainfault.org> Link: https://lore.kernel.org/r/20231213203001.179237-5-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt <palmer(a)rivosinc.com> Signed-off-by: WangYuli <wangyuli(a)uniontech.com> --- arch/riscv/include/asm/kfence.h | 4 +-- arch/riscv/include/asm/pgtable-64.h | 16 ++------- arch/riscv/include/asm/pgtable.h | 29 ++++------------ arch/riscv/kernel/efi.c | 2 +- arch/riscv/kvm/mmu.c | 22 ++++++------- arch/riscv/mm/fault.c | 16 ++++----- arch/riscv/mm/hugetlbpage.c | 12 +++---- arch/riscv/mm/kasan_init.c | 45 +++++++++++++------------ arch/riscv/mm/pageattr.c | 44 ++++++++++++------------- arch/riscv/mm/pgtable.c | 51 ++++++++++++++++++++++++++--- 10 files changed, 128 insertions(+), 113 deletions(-) diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index 0bbffd528096..7388edd88986 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -18,9 +18,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) pte_t *pte = virt_to_kpte(addr); if (protect) - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); + set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT)); else - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); + set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index a65a352dcfbf..3272ca7a5270 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -336,13 +336,7 @@ static inline struct page *p4d_page(p4d_t p4d) #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) #define pud_offset pud_offset -static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) -{ - if (pgtable_l4_enabled) - return p4d_pgtable(*p4d) + pud_index(address); - - return (pud_t *)p4d; -} +pud_t *pud_offset(p4d_t *p4d, unsigned long address); static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { @@ -400,12 +394,6 @@ static inline struct page *pgd_page(pgd_t pgd) #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) #define p4d_offset p4d_offset -static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) -{ - if (pgtable_l5_enabled) - return pgd_pgtable(*pgd) + p4d_index(address); - - return (p4d_t *)pgd; -} +p4d_t *p4d_offset(pgd_t *pgd, unsigned long address); #endif /* _ASM_RISCV_PGTABLE_64_H */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index f8e72df4113a..37829dab4a0a 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -549,19 +549,12 @@ static inline void pte_clear(struct mm_struct *mm, __set_pte_at(ptep, __pte(0)); } -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -static inline int ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, - pte_t entry, int dirty) -{ - if (!pte_same(*ptep, entry)) - __set_pte_at(ptep, entry); - /* - * update_mmu_cache will unconditionally execute, handling both - * the case that the PTE changed and the spurious fault case. - */ - return true; -} +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* defined in mm/pgtable.c */ +extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG /* defined in mm/pgtable.c */ +extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, @@ -574,16 +567,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, return pte; } -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, - pte_t *ptep) -{ - if (!pte_young(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep)); -} - #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c index aa6209a74c83..b64bf1624a05 100644 --- a/arch/riscv/kernel/efi.c +++ b/arch/riscv/kernel/efi.c @@ -60,7 +60,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { efi_memory_desc_t *md = data; - pte_t pte = READ_ONCE(*ptep); + pte_t pte = ptep_get(ptep); unsigned long val; if (md->attribute & EFI_MEMORY_RO) { diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 068c74593871..a9e2fd7245e1 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -103,7 +103,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr, *ptep_level = current_level; ptep = (pte_t *)kvm->arch.pgd; ptep = &ptep[gstage_pte_index(addr, current_level)]; - while (ptep && pte_val(*ptep)) { + while (ptep && pte_val(ptep_get(ptep))) { if (gstage_pte_leaf(ptep)) { *ptep_level = current_level; *ptepp = ptep; @@ -113,7 +113,7 @@ static bool gstage_get_leaf_entry(struct kvm *kvm, gpa_t addr, if (current_level) { current_level--; *ptep_level = current_level; - ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); + ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); ptep = &ptep[gstage_pte_index(addr, current_level)]; } else { ptep = NULL; @@ -149,25 +149,25 @@ static int gstage_set_pte(struct kvm *kvm, u32 level, if (gstage_pte_leaf(ptep)) return -EEXIST; - if (!pte_val(*ptep)) { + if (!pte_val(ptep_get(ptep))) { if (!pcache) return -ENOMEM; next_ptep = kvm_mmu_memory_cache_alloc(pcache); if (!next_ptep) return -ENOMEM; - *ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)), - __pgprot(_PAGE_TABLE)); + set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)), + __pgprot(_PAGE_TABLE))); } else { if (gstage_pte_leaf(ptep)) return -EEXIST; - next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); } current_level--; ptep = &next_ptep[gstage_pte_index(addr, current_level)]; } - *ptep = *new_pte; + set_pte(ptep, *new_pte); if (gstage_pte_leaf(ptep)) gstage_remote_tlb_flush(kvm, current_level, addr); @@ -239,11 +239,11 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr, BUG_ON(addr & (page_size - 1)); - if (!pte_val(*ptep)) + if (!pte_val(ptep_get(ptep))) return; if (ptep_level && !gstage_pte_leaf(ptep)) { - next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep); + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); next_ptep_level = ptep_level - 1; ret = gstage_level_to_page_size(next_ptep_level, &next_page_size); @@ -261,7 +261,7 @@ static void gstage_op_pte(struct kvm *kvm, gpa_t addr, if (op == GSTAGE_OP_CLEAR) set_pte(ptep, __pte(0)); else if (op == GSTAGE_OP_WP) - set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE)); + set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE)); gstage_remote_tlb_flush(kvm, ptep_level, addr); } } @@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) &ptep, &ptep_level)) return false; - return pte_young(*ptep); + return pte_young(ptep_get(ptep)); } int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 655b2b1bb529..8960f4c84497 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -137,24 +137,24 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a pgd = (pgd_t *)pfn_to_virt(pfn) + index; pgd_k = init_mm.pgd + index; - if (!pgd_present(*pgd_k)) { + if (!pgd_present(pgdp_get(pgd_k))) { no_context(regs, addr); return; } - set_pgd(pgd, *pgd_k); + set_pgd(pgd, pgdp_get(pgd_k)); p4d_k = p4d_offset(pgd_k, addr); - if (!p4d_present(*p4d_k)) { + if (!p4d_present(p4dp_get(p4d_k))) { no_context(regs, addr); return; } pud_k = pud_offset(p4d_k, addr); - if (!pud_present(*pud_k)) { + if (!pud_present(pudp_get(pud_k))) { no_context(regs, addr); return; } - if (pud_leaf(*pud_k)) + if (pud_leaf(pudp_get(pud_k))) goto flush_tlb; /* @@ -162,11 +162,11 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * to copy individual PTEs */ pmd_k = pmd_offset(pud_k, addr); - if (!pmd_present(*pmd_k)) { + if (!pmd_present(pmdp_get(pmd_k))) { no_context(regs, addr); return; } - if (pmd_leaf(*pmd_k)) + if (pmd_leaf(pmdp_get(pmd_k))) goto flush_tlb; /* @@ -176,7 +176,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * silently loop forever. */ pte_k = pte_offset_kernel(pmd_k, addr); - if (!pte_present(*pte_k)) { + if (!pte_present(ptep_get(pte_k))) { no_context(regs, addr); return; } diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index fbe918801667..5ef2a6891158 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, } if (sz == PMD_SIZE) { - if (want_pmd_share(vma, addr) && pud_none(*pud)) + if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud))) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, pmd_t *pmd; pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) + if (!pgd_present(pgdp_get(pgd))) return NULL; p4d = p4d_offset(pgd, addr); - if (!p4d_present(*p4d)) + if (!p4d_present(p4dp_get(p4d))) return NULL; pud = pud_offset(p4d, addr); @@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, /* must be pud huge, non-present or none */ return (pte_t *)pud; - if (!pud_present(*pud)) + if (!pud_present(pudp_get(pud))) return NULL; pmd = pmd_offset(pud, addr); @@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, /* must be pmd huge, non-present or none */ return (pte_t *)pmd; - if (!pmd_present(*pmd)) + if (!pmd_present(pmdp_get(pmd))) return NULL; for_each_napot_order(order) { @@ -351,7 +351,7 @@ void huge_pte_clear(struct mm_struct *mm, pte_t *ptep, unsigned long sz) { - pte_t pte = READ_ONCE(*ptep); + pte_t pte = ptep_get(ptep); int i, pte_num; if (!pte_napot(pte)) { diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 5e39dcf23fdb..e96251853037 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -31,7 +31,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned phys_addr_t phys_addr; pte_t *ptep, *p; - if (pmd_none(*pmd)) { + if (pmd_none(pmdp_get(pmd))) { p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -39,7 +39,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned ptep = pte_offset_kernel(pmd, vaddr); do { - if (pte_none(*ptep)) { + if (pte_none(ptep_get(ptep))) { phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL)); memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE); @@ -53,7 +53,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned pmd_t *pmdp, *p; unsigned long next; - if (pud_none(*pud)) { + if (pud_none(pudp_get(pud))) { p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -63,7 +63,8 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned do { next = pmd_addr_end(vaddr, end); - if (pmd_none(*pmdp) && IS_ALIGNED(vaddr, PMD_SIZE) && (next - vaddr) >= PMD_SIZE) { + if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) && + (next - vaddr) >= PMD_SIZE) { phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE); if (phys_addr) { set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL)); @@ -83,7 +84,7 @@ static void __init kasan_populate_pud(p4d_t *p4d, pud_t *pudp, *p; unsigned long next; - if (p4d_none(*p4d)) { + if (p4d_none(p4dp_get(p4d))) { p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -93,7 +94,8 @@ static void __init kasan_populate_pud(p4d_t *p4d, do { next = pud_addr_end(vaddr, end); - if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) { + if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) && + (next - vaddr) >= PUD_SIZE) { phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE); if (phys_addr) { set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL)); @@ -113,7 +115,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd, p4d_t *p4dp, *p; unsigned long next; - if (pgd_none(*pgd)) { + if (pgd_none(pgdp_get(pgd))) { p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } @@ -123,7 +125,8 @@ static void __init kasan_populate_p4d(pgd_t *pgd, do { next = p4d_addr_end(vaddr, end); - if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) { + if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) && + (next - vaddr) >= P4D_SIZE) { phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE); if (phys_addr) { set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL)); @@ -145,7 +148,7 @@ static void __init kasan_populate_pgd(pgd_t *pgdp, do { next = pgd_addr_end(vaddr, end); - if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) { phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE); if (phys_addr) { @@ -168,7 +171,7 @@ static void __init kasan_early_clear_pud(p4d_t *p4dp, if (!pgtable_l4_enabled) { pudp = (pud_t *)p4dp; } else { - base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp))); + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp)))); pudp = base_pud + pud_index(vaddr); } @@ -193,7 +196,7 @@ static void __init kasan_early_clear_p4d(pgd_t *pgdp, if (!pgtable_l5_enabled) { p4dp = (p4d_t *)pgdp; } else { - base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp))); + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp)))); p4dp = base_p4d + p4d_index(vaddr); } @@ -239,14 +242,14 @@ static void __init kasan_early_populate_pud(p4d_t *p4dp, if (!pgtable_l4_enabled) { pudp = (pud_t *)p4dp; } else { - base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp))); + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp)))); pudp = base_pud + pud_index(vaddr); } do { next = pud_addr_end(vaddr, end); - if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && + if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) { phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd); set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE)); @@ -277,14 +280,14 @@ static void __init kasan_early_populate_p4d(pgd_t *pgdp, if (!pgtable_l5_enabled) { p4dp = (p4d_t *)pgdp; } else { - base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp))); + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp)))); p4dp = base_p4d + p4d_index(vaddr); } do { next = p4d_addr_end(vaddr, end); - if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && + if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) { phys_addr = __pa((uintptr_t)kasan_early_shadow_pud); set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE)); @@ -305,7 +308,7 @@ static void __init kasan_early_populate_pgd(pgd_t *pgdp, do { next = pgd_addr_end(vaddr, end); - if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) { phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d); set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE)); @@ -381,7 +384,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d, do { next = pud_addr_end(vaddr, end); - if (pud_none(*pud_k)) { + if (pud_none(pudp_get(pud_k))) { p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; @@ -401,7 +404,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd, do { next = p4d_addr_end(vaddr, end); - if (p4d_none(*p4d_k)) { + if (p4d_none(p4dp_get(p4d_k))) { p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; @@ -420,7 +423,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long do { next = pgd_addr_end(vaddr, end); - if (pgd_none(*pgd_k)) { + if (pgd_none(pgdp_get(pgd_k))) { p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; @@ -451,7 +454,7 @@ static void __init create_tmp_mapping(void) /* Copy the last p4d since it is shared with the kernel mapping. */ if (pgtable_l5_enabled) { - ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END)); + ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END))); memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D); set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)], pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE)); @@ -462,7 +465,7 @@ static void __init create_tmp_mapping(void) /* Copy the last pud since it is shared with the kernel mapping. */ if (pgtable_l4_enabled) { - ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END))); + ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END))); memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD); set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)], pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE)); diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index f61b2f8291e3..271d01a5ba4d 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -29,7 +29,7 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk) static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, unsigned long next, struct mm_walk *walk) { - p4d_t val = READ_ONCE(*p4d); + p4d_t val = p4dp_get(p4d); if (p4d_leaf(val)) { val = __p4d(set_pageattr_masks(p4d_val(val), walk)); @@ -42,7 +42,7 @@ static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, static int pageattr_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk) { - pud_t val = READ_ONCE(*pud); + pud_t val = pudp_get(pud); if (pud_leaf(val)) { val = __pud(set_pageattr_masks(pud_val(val), walk)); @@ -55,7 +55,7 @@ static int pageattr_pud_entry(pud_t *pud, unsigned long addr, static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { - pmd_t val = READ_ONCE(*pmd); + pmd_t val = pmdp_get(pmd); if (pmd_leaf(val)) { val = __pmd(set_pageattr_masks(pmd_val(val), walk)); @@ -68,7 +68,7 @@ static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr, static int pageattr_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { - pte_t val = READ_ONCE(*pte); + pte_t val = ptep_get(pte); val = __pte(set_pageattr_masks(pte_val(val), walk)); set_pte(pte, val); @@ -108,10 +108,10 @@ static int __split_linear_mapping_pmd(pud_t *pudp, vaddr <= (vaddr & PMD_MASK) && end >= next) continue; - if (pmd_leaf(*pmdp)) { + if (pmd_leaf(pmdp_get(pmdp))) { struct page *pte_page; - unsigned long pfn = _pmd_pfn(*pmdp); - pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK); + unsigned long pfn = _pmd_pfn(pmdp_get(pmdp)); + pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK); pte_t *ptep_new; int i; @@ -148,10 +148,10 @@ static int __split_linear_mapping_pud(p4d_t *p4dp, vaddr <= (vaddr & PUD_MASK) && end >= next) continue; - if (pud_leaf(*pudp)) { + if (pud_leaf(pudp_get(pudp))) { struct page *pmd_page; - unsigned long pfn = _pud_pfn(*pudp); - pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK); + unsigned long pfn = _pud_pfn(pudp_get(pudp)); + pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK); pmd_t *pmdp_new; int i; @@ -197,10 +197,10 @@ static int __split_linear_mapping_p4d(pgd_t *pgdp, vaddr <= (vaddr & P4D_MASK) && end >= next) continue; - if (p4d_leaf(*p4dp)) { + if (p4d_leaf(p4dp_get(p4dp))) { struct page *pud_page; - unsigned long pfn = _p4d_pfn(*p4dp); - pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK); + unsigned long pfn = _p4d_pfn(p4dp_get(p4dp)); + pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK); pud_t *pudp_new; int i; @@ -427,29 +427,29 @@ bool kernel_page_present(struct page *page) pte_t *pte; pgd = pgd_offset_k(addr); - if (!pgd_present(*pgd)) + if (!pgd_present(pgdp_get(pgd))) return false; - if (pgd_leaf(*pgd)) + if (pgd_leaf(pgdp_get(pgd))) return true; p4d = p4d_offset(pgd, addr); - if (!p4d_present(*p4d)) + if (!p4d_present(p4dp_get(p4d))) return false; - if (p4d_leaf(*p4d)) + if (p4d_leaf(p4dp_get(p4d))) return true; pud = pud_offset(p4d, addr); - if (!pud_present(*pud)) + if (!pud_present(pudp_get(pud))) return false; - if (pud_leaf(*pud)) + if (pud_leaf(pudp_get(pud))) return true; pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) + if (!pmd_present(pmdp_get(pmd))) return false; - if (pmd_leaf(*pmd)) + if (pmd_leaf(pmdp_get(pmd))) return true; pte = pte_offset_kernel(pmd, addr); - return pte_present(*pte); + return pte_present(ptep_get(pte)); } diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c index fef4e7328e49..ef887efcb679 100644 --- a/arch/riscv/mm/pgtable.c +++ b/arch/riscv/mm/pgtable.c @@ -5,6 +5,47 @@ #include <linux/kernel.h> #include <linux/pgtable.h> +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + if (!pte_same(ptep_get(ptep), entry)) + __set_pte_at(ptep, entry); + /* + * update_mmu_cache will unconditionally execute, handling both + * the case that the PTE changed and the spurious fault case. + */ + return true; +} + +int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + if (!pte_young(ptep_get(ptep))) + return 0; + return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep)); +} +EXPORT_SYMBOL_GPL(ptep_test_and_clear_young); + +#ifdef CONFIG_64BIT +pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + if (pgtable_l4_enabled) + return p4d_pgtable(p4dp_get(p4d)) + pud_index(address); + + return (pud_t *)p4d; +} + +p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +{ + if (pgtable_l5_enabled) + return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address); + + return (p4d_t *)pgd; +} +#endif + #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { @@ -25,7 +66,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) int pud_clear_huge(pud_t *pud) { - if (!pud_leaf(READ_ONCE(*pud))) + if (!pud_leaf(pudp_get(pud))) return 0; pud_clear(pud); return 1; @@ -33,7 +74,7 @@ int pud_clear_huge(pud_t *pud) int pud_free_pmd_page(pud_t *pud, unsigned long addr) { - pmd_t *pmd = pud_pgtable(*pud); + pmd_t *pmd = pud_pgtable(pudp_get(pud)); int i; pud_clear(pud); @@ -63,7 +104,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) int pmd_clear_huge(pmd_t *pmd) { - if (!pmd_leaf(READ_ONCE(*pmd))) + if (!pmd_leaf(pmdp_get(pmd))) return 0; pmd_clear(pmd); return 1; @@ -71,7 +112,7 @@ int pmd_clear_huge(pmd_t *pmd) int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { - pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd); + pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd)); pmd_clear(pmd); @@ -88,7 +129,7 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON(pmd_trans_huge(*pmdp)); + VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp))); /* * When leaf PTE entries (regular pages) are collapsed into a leaf * PMD entry (huge page), a valid non-leaf PTE is converted into a -- 2.43.4

1 week, 4 days

2
1
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2024