batman-adv: Fix netlink dumping of all mcast_flags buckets
Subsystems (21)
Sasha Levin
maintainerPATCH 1/76 batman-adv: Fix netlink dumping of all mcast_flags buckets
From: Sven Eckelmann <[email protected]>
[ Upstream commit fa3a03da549a889fc9dbc0d3c5908eb7882cac8f ]
The bucket variable is only updated outside the loop over the mcast_flags buckets. It will only be updated during a dumping run when the dumping has to be interrupted and a new message has to be started.
This could result in repeated or missing entries when the multicast flags are dumped to userspace.
--- net/batman-adv/multicast.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/batman-adv/multicast.c +1 -1
@@ -1653,7 +1653,7 @@ __batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid,while (bucket_tmp < hash->size) {if (batadv_mcast_flags_dump_bucket (msg, portid, cb, hash, - *bucket, &idx_tmp)) + bucket_tmp, &idx_tmp))break ; bucket_tmp++;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 2/76 libbpf: fix erroneous multi-closing of BTF FD
From: Andrii Nakryiko <[email protected]>
[ Upstream commit 5d01ab7bac467edfc530e6ccf953921def935c62 ]
Libbpf stores associated BTF FD per each instance of bpf_program. When program is unloaded, that FD is closed. This is wrong, because leads to a race and possibly closing of unrelated files, if application simultaneously opens new files while bpf_programs are unloaded.
It's also unnecessary, because struct btf "owns" that FD, and btf__free(), called from bpf_object__close() will close it. Thus the fix is to never have per-program BTF FD and fetch it from obj->btf, when necessary.
--- tools/lib/bpf/libbpf.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-)
tools/lib/bpf/libbpf.c +3 -8
@@ -178,7 +178,6 @@ struct bpf_program {bpf_program_clear_priv_t clear_priv;enum bpf_attach_type expected_attach_type; -int btf_fd;void *func_info;__u32 func_info_rec_size;__u32 func_info_cnt;
@@ -305,7 +304,6 @@ void bpf_program__unload(struct bpf_program *prog) prog->instances.nr =-1 ;zfree (&prog->instances.fds); -zclose (prog->btf_fd);zfree (&prog->func_info);zfree (&prog->line_info); }
@@ -382,7 +380,6 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, prog->instances.fds =NULL ; prog->instances.nr =-1 ; prog->type =BPF_PROG_TYPE_UNSPEC ; - prog->btf_fd =-1 ;return 0 ; errout:
@@ -1883,9 +1880,6 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, prog->line_info_rec_size =btf_ext__line_info_rec_size (obj->btf_ext); } -if (!insn_offset) - prog->btf_fd =btf__fd (obj->btf); -return 0 ; }
@@ -2060,7 +2054,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,char *cp, errmsg[STRERR_BUFSIZE ];int log_buf_size =BPF_LOG_BUF_SIZE ;char *log_buf; -int ret; +int btf_fd, ret;memset (&load_attr,0 ,sizeof (struct bpf_load_program_attr )); load_attr.prog_type = prog->type;
@@ -2072,7 +2066,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.license = license; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; - load_attr.prog_btf_fd = prog->btf_fd >=0 ? prog->btf_fd :0 ; + btf_fd =bpf_object__btf_fd (prog->obj); + load_attr.prog_btf_fd = btf_fd >=0 ? btf_fd :0 ; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; load_attr.func_info_cnt = prog->func_info_cnt;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 3/76 libbpf: set BTF FD for prog only when there is supported .BTF.ext data
In reply to Sasha LevinFrom: Andrii Nakryiko <[email protected]>
[ Upstream commit 3415ec643e7bd644b03026efbe2f2b36cbe9b34b ]
5d01ab7bac46 ("libbpf: fix erroneous multi-closing of BTF FD") introduced backwards-compatibility issue, manifesting itself as -E2BIG error returned on program load due to unknown non-zero btf_fd attribute value for BPF_PROG_LOAD sys_bpf() sub-command.
This patch fixes bug by ensuring that we only ever associate BTF FD with program if there is a BTF.ext data that was successfully loaded into kernel, which automatically means kernel supports func_info/line_info and associated BTF FD for progs (checked and ensured also by BTF sanitization code).
--- tools/lib/bpf/libbpf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
tools/lib/bpf/libbpf.c +5 -1
@@ -2066,7 +2066,11 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.license = license; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; - btf_fd =bpf_object__btf_fd (prog->obj); +/* if .BTF.ext was loaded, kernel supports associated BTF for prog */ +if (prog->obj->btf_ext) + btf_fd =bpf_object__btf_fd (prog->obj); +else + btf_fd =-1 ; load_attr.prog_btf_fd = btf_fd >=0 ? btf_fd :0 ; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 4/76 netfilter: nf_flow_table: fix offload for flows that are subject to xfrm
In reply to Sasha LevinFrom: Florian Westphal <[email protected]>
[ Upstream commit 589b474a4b7ce409d6821ef17234a995841bd131 ]
This makes the previously added 'encap test' pass.
Because its possible that the xfrm dst entry becomes stale while such a flow is offloaded, we need to call dst_check() -- the notifier that handles this for non-tunneled traffic isn't sufficient, because SA or or policies might have changed.
If dst becomes stale the flow offload entry will be tagged for teardown and packets will be passed to 'classic' forwarding path.
Removing the entry right away is problematic, as this would introduce a race condition with the gc worker.
In case flow is long-lived, it could eventually be offloaded again once the gc worker removes the entry from the flow table.
--- net/netfilter/nf_flow_table_ip.c | 43 ++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+)
net/netfilter/nf_flow_table_ip.c +43 -0
@@ -214,6 +214,25 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)return true; } +static int nf_flow_offload_dst_check (struct dst_entry *dst) +{ +if (unlikely (dst_xfrm (dst))) +return dst_check (dst,0 ) ?0 :-1 ; + +return 0 ; +} + +static unsigned int nf_flow_xmit_xfrm (struct sk_buff *skb, +const struct nf_hook_state *state, +struct dst_entry *dst) +{ +skb_orphan (skb); +skb_dst_set_noref (skb, dst); + skb->tstamp =0 ; +dst_output (state->net, state->sk, skb); +return NF_STOLEN ; +} +unsigned int nf_flow_offload_ip_hook (void *priv,struct sk_buff *skb,const struct nf_hook_state *state)
@@ -254,6 +273,11 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,if (nf_flow_state_check (flow,ip_hdr (skb)->protocol, skb, thoff))return NF_ACCEPT ; +if (nf_flow_offload_dst_check (&rt->dst)) { +flow_offload_teardown (flow); +return NF_ACCEPT ; + } +if (nf_flow_nat_ip (flow, skb, thoff, dir) <0 )return NF_DROP ;
@@ -261,6 +285,13 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, iph =ip_hdr (skb);ip_decrease_ttl (iph); +if (unlikely (dst_xfrm (&rt->dst))) { +memset (skb->cb,0 ,sizeof (struct inet_skb_parm )); +IPCB (skb)->iif = skb->dev->ifindex; +IPCB (skb)->flags =IPSKB_FORWARDED ; +return nf_flow_xmit_xfrm (skb, state, &rt->dst); + } + skb->dev = outdev; nexthop =rt_nexthop (rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);skb_dst_set_noref (skb, &rt->dst);
@@ -467,6 +498,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, sizeof(*ip6h)))return NF_ACCEPT ; +if (nf_flow_offload_dst_check (&rt->dst)) { +flow_offload_teardown (flow); +return NF_ACCEPT ; + } +if (skb_try_make_writable (skb,sizeof (*ip6h)))return NF_DROP ;
@@ -477,6 +513,13 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, ip6h =ipv6_hdr (skb); ip6h->hop_limit--; +if (unlikely (dst_xfrm (&rt->dst))) { +memset (skb->cb,0 ,sizeof (struct inet6_skb_parm )); +IP6CB (skb)->iif = skb->dev->ifindex; +IP6CB (skb)->flags =IP6SKB_FORWARDED ; +return nf_flow_xmit_xfrm (skb, state, &rt->dst); + } + skb->dev = outdev; nexthop =rt6_nexthop (rt, &flow->tuplehash[!dir].tuple.src_v6);skb_dst_set_noref (skb, &rt->dst);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 5/76 net/mlx5e: Fix error flow of CQE recovery on tx reporter
In reply to Sasha LevinFrom: Aya Levin <[email protected]>
[ Upstream commit 276d197e70bcc47153592f4384675b51c7d83aba ]
CQE recovery function begins with test and set of recovery bit. Add an error flow which ensures clearing of this bit when leaving the recovery function, to allow further recoveries to take place. This allows removal of clearing recovery bit on sq activate.
--- .../net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 12 ++++++++---- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 - 2 files changed, 8 insertions(+), 5 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +8 -4
@@ -80,17 +80,17 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)if (err) {netdev_err (dev,"Failed to query SQ 0x%x state. err = %d\n" , sq->sqn, err); -return err; + goto out; }if (state !=MLX5_SQC_STATE_ERR ) -return 0 ; + goto out;mlx5e_tx_disable_queue (sq->txq); err =mlx5e_wait_for_sq_flush (sq);if (err) -return err; + goto out;/* At this point, no new packets will arrive from the stack as TXQ is * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
@@ -99,13 +99,17 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq) err =mlx5e_sq_to_ready (sq, state);if (err) -return err; + goto out;mlx5e_reset_txqsq_cc_pc (sq); sq->stats->recover++; +clear_bit (MLX5E_SQ_STATE_RECOVERING , &sq->state);mlx5e_activate_txqsq (sq);return 0 ; +out: +clear_bit (MLX5E_SQ_STATE_RECOVERING , &sq->state); +return err; } static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
drivers/net/ethernet/mellanox/mlx5/core/en_main.c +0 -1
@@ -1279,7 +1279,6 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c,void mlx5e_activate_txqsq (struct mlx5e_txqsq *sq) { sq->txq =netdev_get_tx_queue (sq->channel->netdev, sq->txq_ix); -clear_bit (MLX5E_SQ_STATE_RECOVERING , &sq->state);set_bit (MLX5E_SQ_STATE_ENABLED , &sq->state);netdev_tx_reset_queue (sq->txq);netif_tx_start_queue (sq->txq);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 6/76 clk: samsung: Change signature of exynos5_subcmus_init() function
In reply to Sasha LevinFrom: Sylwester Nawrocki <[email protected]>
[ Upstream commit bf32e7dbfce87d518c0ca77af890eae9ab8d6ab9 ]
In order to make it easier in subsequent patch to create different subcmu lists for exynos5420 and exynos5800 SoCs the code is rewritten so we pass an array of pointers to the subcmus initialization function.
--- drivers/clk/samsung/clk-exynos5-subcmu.c | 16 +++---- drivers/clk/samsung/clk-exynos5-subcmu.h | 2 +- drivers/clk/samsung/clk-exynos5250.c | 7 ++- drivers/clk/samsung/clk-exynos5420.c | 60 ++++++++++++++---------- 4 files changed, 49 insertions(+), 36 deletions(-)
drivers/clk/samsung/clk-exynos5-subcmu.c +8 -8
@@ -14,7 +14,7 @@#include "clk-exynos5-subcmu.h" static struct samsung_clk_provider *ctx; -static const struct exynos5_subcmu_info *cmu; +static const struct exynos5_subcmu_info **cmu;static int nr_cmus; static void exynos5_subcmu_clk_save(void __iomem *base,
@@ -56,17 +56,17 @@ static void exynos5_subcmu_defer_gate(struct samsung_clk_provider *ctx,* when OF-core populates all device-tree nodes. */ void exynos5_subcmus_init (struct samsung_clk_provider *_ctx,int _nr_cmus, -const struct exynos5_subcmu_info *_cmu) +const struct exynos5_subcmu_info **_cmu) { ctx = _ctx; cmu = _cmu; nr_cmus = _nr_cmus;for (; _nr_cmus--; _cmu++) { -exynos5_subcmu_defer_gate (ctx, _cmu->gate_clks, - _cmu->nr_gate_clks); -exynos5_subcmu_clk_save (ctx->reg_base, _cmu->suspend_regs, - _cmu->nr_suspend_regs); +exynos5_subcmu_defer_gate (ctx, (*_cmu)->gate_clks, + (*_cmu)->nr_gate_clks); +exynos5_subcmu_clk_save (ctx->reg_base, (*_cmu)->suspend_regs, + (*_cmu)->nr_suspend_regs); } }
@@ -163,9 +163,9 @@ static int __init exynos5_clk_probe(struct platform_device *pdev)if (of_property_read_string (np,"label" , &name) <0 )continue ;for (i =0 ; i < nr_cmus; i++) -if (strcmp (cmu[i].pd_name, name) ==0 ) +if (strcmp (cmu[i]->pd_name, name) ==0 )exynos5_clk_register_subcmu (&pdev->dev, - &cmu[i], np); + cmu[i], np); }return 0 ; }
drivers/clk/samsung/clk-exynos5-subcmu.h +1 -1
@@ -21,6 +21,6 @@ struct exynos5_subcmu_info { };void exynos5_subcmus_init (struct samsung_clk_provider *ctx,int nr_cmus, -const struct exynos5_subcmu_info *cmu); +const struct exynos5_subcmu_info **cmu);#endif
drivers/clk/samsung/clk-exynos5250.c +6 -1
@@ -681,6 +681,10 @@ static const struct exynos5_subcmu_info exynos5250_disp_subcmu = { .pd_name = "DISP1", }; +static const struct exynos5_subcmu_info *exynos5250_subcmus[] = { + &exynos5250_disp_subcmu, +}; +static const struct samsung_pll_rate_table vpll_24mhz_tbl[]__initconst = {/* sorted in descending order */ /* PLL_36XX_RATE(rate, m, p, s, k) */
@@ -843,7 +847,8 @@ static void __init exynos5250_clk_init(struct device_node *np)samsung_clk_sleep_init (reg_base, exynos5250_clk_regs,ARRAY_SIZE (exynos5250_clk_regs)); -exynos5_subcmus_init (ctx,1 , &exynos5250_disp_subcmu); +exynos5_subcmus_init (ctx,ARRAY_SIZE (exynos5250_subcmus), + exynos5250_subcmus);samsung_clk_of_add_provider (np, ctx);
drivers/clk/samsung/clk-exynos5420.c +34 -26
66 lines not on this page · raw message
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 7/76 clk: samsung: exynos5800: Move MAU subsystem clocks to MAU sub-CMU
In reply to Sasha LevinFrom: Sylwester Nawrocki <[email protected]>
[ Upstream commit b6adeb6bc61c2567b9efd815d61a61b34a2e51a6 ]
This patch fixes broken sound on Exynos5422/5800 platforms after system/suspend resume cycle in cases where the audio root clock is derived from MAU_EPLL_CLK.
In order to preserve state of the USER_MUX_MAU_EPLL_CLK clock mux during system suspend/resume cycle for Exynos5800 we group the MAU block input clocks in "MAU" sub-CMU and add the clock mux control bit to .suspend_regs. This ensures that user configuration of the mux is not lost after the PMU block changes the mux setting to OSC_DIV when switching off the MAU power domain.
Adding the SRC_TOP9 register to exynos5800_clk_regs[] array is not sufficient as at the time of the syscore_ops suspend call MAU power domain is already turned off and we already save and subsequently restore an incorrect register's value.
--- drivers/clk/samsung/clk-exynos5420.c | 54 ++++++++++++++++++++++------ 1 file changed, 43 insertions(+), 11 deletions(-)
drivers/clk/samsung/clk-exynos5420.c +43 -11
@@ -524,8 +524,6 @@ static const struct samsung_gate_clock exynos5800_gate_clks[] __initconst = { GATE_BUS_TOP, 24, 0, 0), GATE(CLK_ACLK432_SCALER, "aclk432_scaler", "mout_user_aclk432_scaler", GATE_BUS_TOP, 27, CLK_IS_CRITICAL, 0), -GATE (CLK_MAU_EPLL ,"mau_epll" ,"mout_user_mau_epll" , - SRC_MASK_TOP7, 20, CLK_SET_RATE_PARENT, 0), };static const struct samsung_mux_clock exynos5420_mux_clks[]__initconst = {
@@ -567,8 +565,13 @@ static const struct samsung_div_clock exynos5420_div_clks[] __initconst = {static const struct samsung_gate_clock exynos5420_gate_clks[]__initconst = {GATE (CLK_SECKEY ,"seckey" ,"aclk66_psgen" ,GATE_BUS_PERIS1 ,1 ,0 ,0 ), +/* Maudio Block */ GATE (CLK_MAU_EPLL ,"mau_epll" ,"mout_mau_epll_clk" ,SRC_MASK_TOP7 ,20 ,CLK_SET_RATE_PARENT ,0 ), +GATE (CLK_SCLK_MAUDIO0 ,"sclk_maudio0" ,"dout_maudio0" , +GATE_TOP_SCLK_MAU ,0 ,CLK_SET_RATE_PARENT ,0 ), +GATE (CLK_SCLK_MAUPCM0 ,"sclk_maupcm0" ,"dout_maupcm0" , +GATE_TOP_SCLK_MAU ,1 ,CLK_SET_RATE_PARENT ,0 ), };static const struct samsung_mux_clock exynos5x_mux_clks[]__initconst = {
@@ -994,12 +997,6 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = {GATE (CLK_SCLK_DP1 ,"sclk_dp1" ,"dout_dp1" ,GATE_TOP_SCLK_DISP1 ,20 ,CLK_SET_RATE_PARENT ,0 ), -/* Maudio Block */ -GATE (CLK_SCLK_MAUDIO0 ,"sclk_maudio0" ,"dout_maudio0" , -GATE_TOP_SCLK_MAU ,0 ,CLK_SET_RATE_PARENT ,0 ), -GATE (CLK_SCLK_MAUPCM0 ,"sclk_maupcm0" ,"dout_maupcm0" , -GATE_TOP_SCLK_MAU ,1 ,CLK_SET_RATE_PARENT ,0 ), -/* FSYS Block */ GATE (CLK_TSI ,"tsi" ,"aclk200_fsys" ,GATE_BUS_FSYS0 ,0 ,0 ,0 ), GATE(CLK_PDMA0, "pdma0", "aclk200_fsys", GATE_BUS_FSYS0, 1, 0, 0),
@@ -1232,6 +1229,20 @@ static struct exynos5_subcmu_reg_dump exynos5x_mfc_suspend_regs[] = { { DIV4_RATIO, 0, 0x3 }, /* DIV dout_mfc_blk */ }; + +static const struct samsung_gate_clock exynos5800_mau_gate_clks[]__initconst = { +GATE (CLK_MAU_EPLL ,"mau_epll" ,"mout_user_mau_epll" , +SRC_MASK_TOP7 ,20 ,CLK_SET_RATE_PARENT ,0 ), +GATE (CLK_SCLK_MAUDIO0 ,"sclk_maudio0" ,"dout_maudio0" , +GATE_TOP_SCLK_MAU ,0 ,CLK_SET_RATE_PARENT ,0 ), +GATE (CLK_SCLK_MAUPCM0 ,"sclk_maupcm0" ,"dout_maupcm0" , +GATE_TOP_SCLK_MAU ,1 ,CLK_SET_RATE_PARENT ,0 ), +}; + +static struct exynos5_subcmu_reg_dump exynos5800_mau_suspend_regs[] = { + {SRC_TOP9 ,0 ,BIT (8 ) },/* MUX mout_user_mau_epll */ +}; +static const struct exynos5_subcmu_info exynos5x_disp_subcmu = { .div_clks = exynos5x_disp_div_clks, .nr_div_clks = ARRAY_SIZE(exynos5x_disp_div_clks),
@@ -1262,12 +1273,27 @@ static const struct exynos5_subcmu_info exynos5x_mfc_subcmu = { .pd_name = "MFC", }; +static const struct exynos5_subcmu_info exynos5800_mau_subcmu = { + .gate_clks = exynos5800_mau_gate_clks, + .nr_gate_clks =ARRAY_SIZE (exynos5800_mau_gate_clks), + .suspend_regs = exynos5800_mau_suspend_regs, + .nr_suspend_regs =ARRAY_SIZE (exynos5800_mau_suspend_regs), + .pd_name ="MAU" , +}; +static const struct exynos5_subcmu_info *exynos5x_subcmus[] = { &exynos5x_disp_subcmu, &exynos5x_gsc_subcmu, &exynos5x_mfc_subcmu, }; +static const struct exynos5_subcmu_info *exynos5800_subcmus[] = { + &exynos5x_disp_subcmu, + &exynos5x_gsc_subcmu, + &exynos5x_mfc_subcmu, + &exynos5800_mau_subcmu, +}; +static const struct samsung_pll_rate_table exynos5420_pll2550x_24mhz_tbl[]__initconst = {PLL_35XX_RATE (24 *MHZ ,2000000000 ,250 ,3 ,0 ),PLL_35XX_RATE (24 *MHZ ,1900000000 ,475 ,6 ,0 ),
@@ -1483,11 +1509,17 @@ static void __init exynos5x_clk_init(struct device_node *np,samsung_clk_extended_sleep_init (reg_base, exynos5x_clk_regs,ARRAY_SIZE (exynos5x_clk_regs), exynos5420_set_clksrc,ARRAY_SIZE (exynos5420_set_clksrc)); -if (soc ==EXYNOS5800 ) + +if (soc ==EXYNOS5800 ) {samsung_clk_sleep_init (reg_base, exynos5800_clk_regs,ARRAY_SIZE (exynos5800_clk_regs)); -exynos5_subcmus_init (ctx,ARRAY_SIZE (exynos5x_subcmus), - exynos5x_subcmus); + +exynos5_subcmus_init (ctx,ARRAY_SIZE (exynos5800_subcmus), + exynos5800_subcmus); + }else { +exynos5_subcmus_init (ctx,ARRAY_SIZE (exynos5x_subcmus), + exynos5x_subcmus); + }samsung_clk_of_add_provider (np, ctx); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 8/76 clk: samsung: exynos542x: Move MSCL subsystem clocks to its sub-CMU
In reply to Sasha LevinFrom: Marek Szyprowski <[email protected]>
[ Upstream commit baf7b79e1ad79a41fafd8ab8597b9a96962d822d ]
M2M scaler clocks require special handling of their parent bus clock during power domain on/off sequences. MSCL clocks were not initially added to the sub-CMU handler, because that time there was no driver for the M2M scaler device and it was not possible to test it.
This patch fixes this issue. Parent clock for M2M scaler devices is now properly preserved during MSC power domain on/off sequence. This gives M2M scaler devices proper performance: fullHD XRGB32 image 1000 rotations test takes 3.17s instead of 45.08s.
--- drivers/clk/samsung/clk-exynos5420.c | 48 ++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 14 deletions(-)
drivers/clk/samsung/clk-exynos5420.c +34 -14
@@ -870,9 +870,6 @@ static const struct samsung_div_clock exynos5x_div_clks[] __initconst = {/* GSCL Block */ DIV (0 ,"dout_gscl_blk_333" ,"aclk333_432_gscl" ,DIV2_RATIO0 ,6 ,2 ), -/* MSCL Block */ -DIV (0 ,"dout_mscl_blk" ,"aclk400_mscl" ,DIV2_RATIO0 ,28 ,2 ), -/* PSGEN */ DIV (0 ,"dout_gen_blk" ,"mout_user_aclk266" ,DIV2_RATIO0 ,8 ,1 ), DIV(0, "dout_jpg_blk", "aclk166", DIV2_RATIO0, 20, 1),
@@ -1136,17 +1133,6 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = {GATE (CLK_FIMC_LITE3 ,"fimc_lite3" ,"aclk333_432_gscl" ,GATE_IP_GSCL1 ,17 ,0 ,0 ), -/* MSCL Block */ -GATE (CLK_MSCL0 ,"mscl0" ,"aclk400_mscl" ,GATE_IP_MSCL ,0 ,0 ,0 ), -GATE (CLK_MSCL1 ,"mscl1" ,"aclk400_mscl" ,GATE_IP_MSCL ,1 ,0 ,0 ), -GATE (CLK_MSCL2 ,"mscl2" ,"aclk400_mscl" ,GATE_IP_MSCL ,2 ,0 ,0 ), -GATE (CLK_SMMU_MSCL0 ,"smmu_mscl0" ,"dout_mscl_blk" , -GATE_IP_MSCL ,8 ,0 ,0 ), -GATE (CLK_SMMU_MSCL1 ,"smmu_mscl1" ,"dout_mscl_blk" , -GATE_IP_MSCL ,9 ,0 ,0 ), -GATE (CLK_SMMU_MSCL2 ,"smmu_mscl2" ,"dout_mscl_blk" , -GATE_IP_MSCL ,10 ,0 ,0 ), -/* ISP */ GATE (CLK_SCLK_UART_ISP ,"sclk_uart_isp" ,"dout_uart_isp" , GATE_TOP_SCLK_ISP, 0, CLK_SET_RATE_PARENT, 0),
@@ -1229,6 +1215,28 @@ static struct exynos5_subcmu_reg_dump exynos5x_mfc_suspend_regs[] = { { DIV4_RATIO, 0, 0x3 }, /* DIV dout_mfc_blk */ }; +static const struct samsung_gate_clock exynos5x_mscl_gate_clks[] __initconst = { + /* MSCL Block */ + GATE(CLK_MSCL0, "mscl0", "aclk400_mscl", GATE_IP_MSCL, 0, 0, 0), + GATE(CLK_MSCL1, "mscl1", "aclk400_mscl", GATE_IP_MSCL, 1, 0, 0), + GATE(CLK_MSCL2, "mscl2", "aclk400_mscl", GATE_IP_MSCL, 2, 0, 0), + GATE(CLK_SMMU_MSCL0, "smmu_mscl0", "dout_mscl_blk", + GATE_IP_MSCL, 8, 0, 0), + GATE(CLK_SMMU_MSCL1, "smmu_mscl1", "dout_mscl_blk", + GATE_IP_MSCL, 9, 0, 0), + GATE(CLK_SMMU_MSCL2, "smmu_mscl2", "dout_mscl_blk", + GATE_IP_MSCL, 10, 0, 0), +}; + +static const struct samsung_div_clock exynos5x_mscl_div_clks[] __initconst = { + DIV(0, "dout_mscl_blk", "aclk400_mscl", DIV2_RATIO0, 28, 2), +}; + +static struct exynos5_subcmu_reg_dump exynos5x_mscl_suspend_regs[] = { + { GATE_IP_MSCL, 0xffffffff, 0xffffffff }, /* MSCL gates */ + { SRC_TOP3, 0, BIT(4) }, /* MUX mout_user_aclk400_mscl */ + { DIV2_RATIO0, 0, 0x30000000 }, /* DIV dout_mscl_blk */ +}; static const struct samsung_gate_clock exynos5800_mau_gate_clks[] __initconst = { GATE(CLK_MAU_EPLL, "mau_epll", "mout_user_mau_epll",
@@ -1273,6 +1281,16 @@ static const struct exynos5_subcmu_info exynos5x_mfc_subcmu = { .pd_name = "MFC", }; +static const struct exynos5_subcmu_info exynos5x_mscl_subcmu = { + .div_clks = exynos5x_mscl_div_clks, + .nr_div_clks =ARRAY_SIZE (exynos5x_mscl_div_clks), + .gate_clks = exynos5x_mscl_gate_clks, + .nr_gate_clks =ARRAY_SIZE (exynos5x_mscl_gate_clks), + .suspend_regs = exynos5x_mscl_suspend_regs, + .nr_suspend_regs =ARRAY_SIZE (exynos5x_mscl_suspend_regs), + .pd_name ="MSC" , +}; +static const struct exynos5_subcmu_info exynos5800_mau_subcmu = { .gate_clks = exynos5800_mau_gate_clks, .nr_gate_clks =ARRAY_SIZE (exynos5800_mau_gate_clks),
@@ -1285,12 +1303,14 @@ static const struct exynos5_subcmu_info *exynos5x_subcmus[] = { &exynos5x_disp_subcmu, &exynos5x_gsc_subcmu, &exynos5x_mfc_subcmu, + &exynos5x_mscl_subcmu, };static const struct exynos5_subcmu_info *exynos5800_subcmus[] = { &exynos5x_disp_subcmu, &exynos5x_gsc_subcmu, &exynos5x_mfc_subcmu, + &exynos5x_mscl_subcmu, &exynos5800_mau_subcmu, };
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 9/76 net: tundra: tsi108: use spin_lock_irqsave instead of spin_lock_irq in IRQ context
In reply to Sasha LevinFrom: Fuqian Huang <[email protected]>
[ Upstream commit 8c25d0887a8bd0e1ca2074ac0c6dff173787a83b ]
As spin_unlock_irq will enable interrupts.
Function tsi108_stat_carry is called from interrupt handler tsi108_irq. Interrupts are enabled in interrupt handler.
Use spin_lock_irqsave/spin_unlock_irqrestore instead of spin_(un)lock_irq in IRQ context to avoid this.
--- drivers/net/ethernet/tundra/tsi108_eth.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/ethernet/tundra/tsi108_eth.c +3 -2
@@ -371,9 +371,10 @@ tsi108_stat_carry_one(int carry, int carry_bit, int carry_shift,static void tsi108_stat_carry (struct net_device *dev) {struct tsi108_prv_data *data =netdev_priv (dev); +unsigned long flags;u32 carry1, carry2; -spin_lock_irq (&data->misclock); +spin_lock_irqsave (&data->misclock, flags); carry1 =TSI_READ (TSI108_STAT_CARRY1 ); carry2 =TSI_READ (TSI108_STAT_CARRY2 );
@@ -441,7 +442,7 @@ static void tsi108_stat_carry(struct net_device *dev)TSI108_STAT_TXPAUSEDROP_CARRY , &data->tx_pause_drop); -spin_unlock_irq (&data->misclock); +spin_unlock_irqrestore (&data->misclock, flags); }/* Read a stat counter atomically with respect to carries.
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 10/76 netfilter: nf_tables: use-after-free in failing rule with bound set
In reply to Sasha LevinFrom: Pablo Neira Ayuso <[email protected]>
[ Upstream commit 6a0a8d10a3661a036b55af695542a714c429ab7c ]
If a rule that has already a bound anonymous set fails to be added, the preparation phase releases the rule and the bound set. However, the transaction object from the abort path still has a reference to the set object that is stale, leading to a use-after-free when checking for the set->bound field. Add a new field to the transaction that specifies if the set is bound, so the abort path can skip releasing it since the rule command owns it and it takes care of releasing it. After this update, the set->bound field is removed.
[ 24.649883] Unable to handle kernel paging request at virtual address 0000000000040434 [ 24.657858] Mem abort info: [ 24.660686] ESR = 0x96000004 [ 24.663769] Exception class = DABT (current EL), IL = 32 bits [ 24.669725] SET = 0, FnV = 0 [ 24.672804] EA = 0, S1PTW = 0 [ 24.675975] Data abort info: [ 24.678880] ISV = 0, ISS = 0x00000004 [ 24.682743] CM = 0, WnR = 0 [ 24.685723] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000428952000 [ 24.692207] [0000000000040434] pgd=0000000000000000 [ 24.697119] Internal error: Oops: 96000004 [#1] SMP [...] [ 24.889414] Call trace: [ 24.891870] __nf_tables_abort+0x3f0/0x7a0 [ 24.895984] nf_tables_abort+0x20/0x40 [ 24.899750] nfnetlink_rcv_batch+0x17c/0x588 [ 24.904037] nfnetlink_rcv+0x13c/0x190 [ 24.907803] netlink_unicast+0x18c/0x208 [ 24.911742] netlink_sendmsg+0x1b0/0x350 [ 24.915682] sock_sendmsg+0x4c/0x68 [ 24.919185] ___sys_sendmsg+0x288/0x2c8 [ 24.923037] __sys_sendmsg+0x7c/0xd0 [ 24.926628] __arm64_sys_sendmsg+0x2c/0x38 [ 24.930744] el0_svc_common.constprop.0+0x94/0x158 [ 24.935556] el0_svc_handler+0x34/0x90 [ 24.939322] el0_svc+0x8/0xc [ 24.942216] Code: 37280300 f9404023 91014262 aa1703e0 (f9401863) [ 24.948336] ---[ end trace cebbb9dcbed3b56f ]---
--- include/net/netfilter/nf_tables.h | 9 +++++++-- net/netfilter/nf_tables_api.c | 15 ++++++++++----- 2 files changed, 17 insertions(+), 7 deletions(-)
include/net/netfilter/nf_tables.h +7 -2
@@ -419,8 +419,7 @@ struct nft_set {unsigned char *udata;/* runtime data below here */ const struct nft_set_ops *ops____cacheline_aligned ; - u16 flags:13, - bound:1, + u16 flags:14, genmask:2;u8 klen;u8 dlen;
@@ -1333,12 +1332,15 @@ struct nft_trans_rule {struct nft_trans_set {struct nft_set *set;u32 set_id; +bool bound; };#define nft_trans_set (trans) \ (((struct nft_trans_set *)trans->data)->set)#define nft_trans_set_id (trans) \ (((struct nft_trans_set *)trans->data)->set_id) +#define nft_trans_set_bound (trans) \ + (((struct nft_trans_set *)trans->data)->bound)struct nft_trans_chain {bool update;
@@ -1369,12 +1371,15 @@ struct nft_trans_table {struct nft_trans_elem {struct nft_set *set;struct nft_set_elem elem; +bool bound; };#define nft_trans_elem_set (trans) \ (((struct nft_trans_elem *)trans->data)->set)#define nft_trans_elem (trans) \ (((struct nft_trans_elem *)trans->data)->elem) +#define nft_trans_elem_set_bound (trans) \ + (((struct nft_trans_elem *)trans->data)->bound)struct nft_trans_obj {struct nft_object *obj;
net/netfilter/nf_tables_api.c +10 -5
@@ -136,9 +136,14 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)return ;list_for_each_entry_reverse (trans, &net->nft.commit_list, list) { -if (trans->msg_type ==NFT_MSG_NEWSET && -nft_trans_set (trans) == set) { - set->bound = true; +switch (trans->msg_type) { +case NFT_MSG_NEWSET : +if (nft_trans_set (trans) == set) +nft_trans_set_bound (trans) = true; +break ; +case NFT_MSG_NEWSETELEM : +if (nft_trans_elem_set (trans) == set) +nft_trans_elem_set_bound (trans) = true;break ; } }
@@ -6849,7 +6854,7 @@ static int __nf_tables_abort(struct net *net)break ;case NFT_MSG_NEWSET : trans->ctx.table->use--; -if (nft_trans_set (trans)->bound) { +if (nft_trans_set_bound (trans)) {nft_trans_destroy (trans);break ; }
@@ -6861,7 +6866,7 @@ static int __nf_tables_abort(struct net *net)nft_trans_destroy (trans);break ;case NFT_MSG_NEWSETELEM : -if (nft_trans_elem_set (trans)->bound) { +if (nft_trans_elem_set_bound (trans)) {nft_trans_destroy (trans);break ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 11/76 netfilter: nf_flow_table: conntrack picks up expired flows
In reply to Sasha LevinFrom: Pablo Neira Ayuso <[email protected]>
[ Upstream commit 3e68db2f6422d711550a32cbc87abd97bb6efab3 ]
Update conntrack entry to pick up expired flows, otherwise the conntrack entry gets stuck with the internal offload timeout (one day). The TCP state also needs to be adjusted to ESTABLISHED state and tracking is set to liberal mode in order to give conntrack a chance to pick up the expired flow.
--- net/netfilter/nf_flow_table_core.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-)
net/netfilter/nf_flow_table_core.c +10 -7
@@ -112,7 +112,7 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ)#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ) -static void flow_offload_fixup_ct_state (struct nf_conn *ct) +static void flow_offload_fixup_ct (struct nf_conn *ct) {const struct nf_conntrack_l4proto *l4proto;unsigned int timeout;
@@ -209,6 +209,11 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) }EXPORT_SYMBOL_GPL (flow_offload_add); +static inline bool nf_flow_has_expired (const struct flow_offload *flow) +{ +return (__s32)(flow->timeout - (u32 )jiffies) <=0 ; +} +static void flow_offload_del (struct nf_flowtable *flow_table,struct flow_offload *flow) {
@@ -224,6 +229,9 @@ static void flow_offload_del(struct nf_flowtable *flow_table, e = container_of(flow, struct flow_offload_entry, flow);clear_bit (IPS_OFFLOAD_BIT , &e->ct->status); +if (nf_flow_has_expired (flow)) +flow_offload_fixup_ct (e->ct); +flow_offload_free (flow); }
@@ -234,7 +242,7 @@ void flow_offload_teardown(struct flow_offload *flow) flow->flags |=FLOW_OFFLOAD_TEARDOWN ; e = container_of(flow, struct flow_offload_entry, flow); -flow_offload_fixup_ct_state (e->ct); +flow_offload_fixup_ct (e->ct); }EXPORT_SYMBOL_GPL (flow_offload_teardown);
@@ -299,11 +307,6 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table,return err; } -static inline bool nf_flow_has_expired (const struct flow_offload *flow) -{ -return (__s32)(flow->timeout - (u32 )jiffies) <=0 ; -} -static void nf_flow_offload_gc_step (struct flow_offload *flow,void *data) {struct nf_flowtable *flow_table = data;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 12/76 netfilter: nf_flow_table: teardown flow timeout race
In reply to Sasha LevinFrom: Pablo Neira Ayuso <[email protected]>
[ Upstream commit 1e5b2471bcc4838df298080ae1ec042c2cbc9ce9 ]
Flows that are in teardown state (due to RST / FIN TCP packet) still have their offload flag set on. Hence, the conntrack garbage collector may race to undo the timeout adjustment that the fixup routine performs, leaving the conntrack entry in place with the internal offload timeout (one day).
Update teardown flow state to ESTABLISHED and set tracking to liberal, then once the offload bit is cleared, adjust timeout if it is more than the default fixup timeout (conntrack might already have set a lower timeout from the packet path).
--- net/netfilter/nf_flow_table_core.c | 34 ++++++++++++++++++++++-------- 1 file changed, 25 insertions(+), 9 deletions(-)
net/netfilter/nf_flow_table_core.c +25 -9
@@ -112,15 +112,16 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ)#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ) -static void flow_offload_fixup_ct (struct nf_conn *ct) +static inline __s32 nf_flow_timeout_delta (unsigned int timeout) +{ +return (__s32)(timeout - (u32 )jiffies); +} + +static void flow_offload_fixup_ct_timeout (struct nf_conn *ct) {const struct nf_conntrack_l4proto *l4proto; +int l4num =nf_ct_protonum (ct);unsigned int timeout; -int l4num; - - l4num =nf_ct_protonum (ct); -if (l4num ==IPPROTO_TCP ) -flow_offload_fixup_tcp (&ct->proto.tcp); l4proto =nf_ct_l4proto_find (l4num);if (!l4proto)
@@ -133,7 +134,20 @@ static void flow_offload_fixup_ct(struct nf_conn *ct)else return ; - ct->timeout = nfct_time_stamp + timeout; +if (nf_flow_timeout_delta (ct->timeout) > (__s32 )timeout) + ct->timeout = nfct_time_stamp + timeout; +} + +static void flow_offload_fixup_ct_state (struct nf_conn *ct) +{ +if (nf_ct_protonum (ct) ==IPPROTO_TCP ) +flow_offload_fixup_tcp (&ct->proto.tcp); +} + +static void flow_offload_fixup_ct (struct nf_conn *ct) +{ +flow_offload_fixup_ct_state (ct); +flow_offload_fixup_ct_timeout (ct); }void flow_offload_free (struct flow_offload *flow)
@@ -211,7 +225,7 @@ EXPORT_SYMBOL_GPL(flow_offload_add);static inline bool nf_flow_has_expired (const struct flow_offload *flow) { -return (__s32)(flow->timeout - (u32 )jiffies) <=0 ; +return nf_flow_timeout_delta (flow->timeout) <=0 ; } static void flow_offload_del(struct nf_flowtable *flow_table,
@@ -231,6 +245,8 @@ static void flow_offload_del(struct nf_flowtable *flow_table,if (nf_flow_has_expired (flow))flow_offload_fixup_ct (e->ct); +else if (flow->flags &FLOW_OFFLOAD_TEARDOWN ) +flow_offload_fixup_ct_timeout (e->ct);flow_offload_free (flow); }
@@ -242,7 +258,7 @@ void flow_offload_teardown(struct flow_offload *flow) flow->flags |=FLOW_OFFLOAD_TEARDOWN ; e = container_of(flow, struct flow_offload_entry, flow); -flow_offload_fixup_ct (e->ct); +flow_offload_fixup_ct_state (e->ct); }EXPORT_SYMBOL_GPL (flow_offload_teardown);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 13/76 rxrpc: Fix local endpoint refcounting
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit 730c5fd42c1e3652a065448fd235cb9fafb2bd10 ]
The object lifetime management on the rxrpc_local struct is broken in that the rxrpc_local_processor() function is expected to clean up and remove an object - but it may get requeued by packets coming in on the backing UDP socket once it starts running.
This may result in the assertion in rxrpc_local_rcu() firing because the memory has been scheduled for RCU destruction whilst still queued:
rxrpc: Assertion failed ------------[ cut here ]------------ kernel BUG at net/rxrpc/local_object.c:468!
Note that if the processor comes around before the RCU free function, it will just do nothing because ->dead is true.
Fix this by adding a separate refcount to count active users of the endpoint that causes the endpoint to be destroyed when it reaches 0.
The original refcount can then be used to refcount objects through the work processor and cause the memory to be rcu freed when that reaches 0.
--- net/rxrpc/af_rxrpc.c | 4 +- net/rxrpc/ar-internal.h | 5 ++- net/rxrpc/input.c | 16 ++++++-- net/rxrpc/local_object.c | 86 +++++++++++++++++++++++++--------------- 4 files changed, 72 insertions(+), 39 deletions(-)
net/rxrpc/af_rxrpc.c +2 -2
@@ -193,7 +193,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) service_in_use:write_unlock (&local->services_lock); -rxrpc_put_local (local); +rxrpc_unuse_local (local); ret = -EADDRINUSE ; error_unlock:release_sock (&rx->sk);
@@ -901,7 +901,7 @@ static int rxrpc_release_sock(struct sock *sk)rxrpc_queue_work (&rxnet->service_conn_reaper);rxrpc_queue_work (&rxnet->client_conn_reaper); -rxrpc_put_local (rx->local); +rxrpc_unuse_local (rx->local); rx->local =NULL ;key_put (rx->key); rx->key =NULL ;
net/rxrpc/ar-internal.h +4 -1
@@ -254,7 +254,8 @@ struct rxrpc_security {*/ struct rxrpc_local {struct rcu_head rcu; -atomic_t usage; +atomic_t active_users;/* Number of users of the local endpoint */ +atomic_t usage;/* Number of references to the structure */ struct rxrpc_net *rxnet;/* The network ns in which this resides */ struct list_head link;struct socket *socket;/* my UDP socket */
@@ -1002,6 +1003,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpcstruct rxrpc_local *rxrpc_get_local (struct rxrpc_local *);struct rxrpc_local *rxrpc_get_local_maybe (struct rxrpc_local *);void rxrpc_put_local (struct rxrpc_local *); +struct rxrpc_local *rxrpc_use_local (struct rxrpc_local *); +void rxrpc_unuse_local (struct rxrpc_local *);void rxrpc_queue_local (struct rxrpc_local *);void rxrpc_destroy_all_locals (struct rxrpc_net *);
net/rxrpc/input.c +12 -4
@@ -1108,8 +1108,12 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, {_enter ("%p,%p" , local, skb); -skb_queue_tail (&local->event_queue, skb); -rxrpc_queue_local (local); +if (rxrpc_get_local_maybe (local)) { +skb_queue_tail (&local->event_queue, skb); +rxrpc_queue_local (local); + }else { +rxrpc_free_skb (skb, rxrpc_skb_rx_freed); + } }/*
@@ -1119,8 +1123,12 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) {CHECK_SLAB_OKAY (&local->usage); -skb_queue_tail (&local->reject_queue, skb); -rxrpc_queue_local (local); +if (rxrpc_get_local_maybe (local)) { +skb_queue_tail (&local->reject_queue, skb); +rxrpc_queue_local (local); + }else { +rxrpc_free_skb (skb, rxrpc_skb_rx_freed); + } }/*
net/rxrpc/local_object.c +54 -32
153 lines not on this page · raw message
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 14/76 tools: bpftool: fix error message (prog -> object)
In reply to Sasha LevinFrom: Jakub Kicinski <[email protected]>
[ Upstream commit b3e78adcbf991a4e8b2ebb23c9889e968ec76c5f ]
Change an error message to work for any object being pinned not just programs.
--- tools/bpf/bpftool/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/bpf/bpftool/common.c +1 -1
@@ -236,7 +236,7 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) fd =get_fd_by_id (id);if (fd <0 ) { -p_err ("can't get prog by id (%u): %s" , id,strerror (errno)); +p_err ("can't open object by id (%u): %s" , id,strerror (errno));return -1 ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 15/76 ixgbe: fix possible deadlock in ixgbe_service_task()
In reply to Sasha LevinFrom: Taehee Yoo <[email protected]>
[ Upstream commit 8b6381600d59871fbe44d36522272f961ab42410 ]
ixgbe_service_task() calls unregister_netdev() under rtnl_lock(). But unregister_netdev() internally calls rtnl_lock(). So deadlock would occur.
--- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +1 -4
@@ -7893,11 +7893,8 @@ static void ixgbe_service_task(struct work_struct *work)return ; }if (ixgbe_check_fw_error (adapter)) { -if (!test_bit (__IXGBE_DOWN, &adapter->state)) { -rtnl_lock (); +if (!test_bit (__IXGBE_DOWN, &adapter->state))unregister_netdev (adapter->netdev); -rtnl_unlock (); - }ixgbe_service_event_complete (adapter);return ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 16/76 hv_netvsc: Fix a warning of suspicious RCU usage
In reply to Sasha LevinFrom: Dexuan Cui <[email protected]>
[ Upstream commit 6d0d779dca73cd5acb649c54f81401f93098b298 ]
This fixes a warning of "suspicious rcu_dereference_check() usage" when nload runs.
--- drivers/net/hyperv/netvsc_drv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/net/hyperv/netvsc_drv.c +7 -2
@@ -1239,12 +1239,15 @@ static void netvsc_get_stats64(struct net_device *net, struct rtnl_link_stats64 *t) {struct net_device_context *ndev_ctx =netdev_priv (net); -struct netvsc_device *nvdev =rcu_dereference_rtnl (ndev_ctx->nvdev); +struct netvsc_device *nvdev;struct netvsc_vf_pcpu_stats vf_tot;int i; +rcu_read_lock (); + + nvdev =rcu_dereference (ndev_ctx->nvdev);if (!nvdev) -return ; + goto out;netdev_stats_to_stats64 (t, &net->stats);
@@ -1283,6 +1286,8 @@ static void netvsc_get_stats64(struct net_device *net, t->rx_packets += packets; t->multicast += multicast; } +out: +rcu_read_unlock (); }static int netvsc_set_mac_addr (struct net_device *ndev,void *p)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 17/76 net: tc35815: Explicitly check NET_IP_ALIGN is not zero in tc35815_rx
In reply to Sasha LevinFrom: Nathan Chancellor <[email protected]>
[ Upstream commit 125b7e0949d4e72b15c2b1a1590f8cece985a918 ]
clang warns:
drivers/net/ethernet/toshiba/tc35815.c:1507:30: warning: use of logical '&&' with constant operand [-Wconstant-logical-operand]
if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN)
^ ~~~~~~~~~~~~
drivers/net/ethernet/toshiba/tc35815.c:1507:30: note: use '&' for a
bitwise operation
if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN)
^~
&
drivers/net/ethernet/toshiba/tc35815.c:1507:30: note: remove constant to
silence this warning
if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN)
~^~~~~~~~~~~~~~~1 warning generated.
Explicitly check that NET_IP_ALIGN is not zero, which matches how this is checked in other parts of the tree. Because NET_IP_ALIGN is a build time constant, this check will be constant folded away during optimization.
--- drivers/net/ethernet/toshiba/tc35815.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/toshiba/tc35815.c +1 -1
@@ -1504,7 +1504,7 @@ tc35815_rx(struct net_device *dev, int limit)pci_unmap_single (lp->pci_dev, lp->rx_skbs[cur_bd].skb_dma,RX_BUF_SIZE ,PCI_DMA_FROMDEVICE ); -if (!HAVE_DMA_RXALIGN (lp) &&NET_IP_ALIGN ) +if (!HAVE_DMA_RXALIGN (lp) &&NET_IP_ALIGN !=0 )memmove (skb->data, skb->data -NET_IP_ALIGN , pkt_len); data =skb_put (skb, pkt_len);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 18/76 Bluetooth: btqca: Add a short delay before downloading the NVM
In reply to Sasha LevinFrom: Matthias Kaehlcke <[email protected]>
[ Upstream commit 8059ba0bd0e4694e51c2ee6438a77b325f06c0d5 ]
On WCN3990 downloading the NVM sometimes fails with a "TLV response size mismatch" error:
[ 174.949955] Bluetooth: btqca.c:qca_download_firmware() hci0: QCA Downloading qca/crnv21.bin [ 174.958718] Bluetooth: btqca.c:qca_tlv_send_segment() hci0: QCA TLV response size mismatch
It seems the controller needs a short time after downloading the firmware before it is ready for the NVM. A delay as short as 1 ms seems sufficient, make it 10 ms just in case. No event is received during the delay, hence we don't just silently drop an extra event.
--- drivers/bluetooth/btqca.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/bluetooth/btqca.c +3 -0
@@ -350,6 +350,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,return err; } +/* Give the controller some time to get ready to receive the NVM */ +msleep (10 ); +/* Download NVM configuration */ config.type =TLV_TYPE_NVM ;if (qca_is_wcn399x (soc_type))
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 19/76 Bluetooth: hci_qca: Send VS pre shutdown command.
In reply to Sasha LevinFrom: Harish Bandi <[email protected]>
[ Upstream commit a2780889e247561744dd8efbd3478a1999b72ae3 ]
WCN399x chips are coex chips, it needs a VS pre shutdown command while turning off the BT. So that chip can inform BT is OFF to other active clients.
--- drivers/bluetooth/btqca.c | 21 +++++++++++++++++++++ drivers/bluetooth/btqca.h | 7 +++++++ drivers/bluetooth/hci_qca.c | 3 +++ 3 files changed, 31 insertions(+)
drivers/bluetooth/btqca.c +21 -0
@@ -99,6 +99,27 @@ static int qca_send_reset(struct hci_dev *hdev)return 0 ; } +int qca_send_pre_shutdown_cmd (struct hci_dev *hdev) +{ +struct sk_buff *skb; +int err; + +bt_dev_dbg (hdev,"QCA pre shutdown cmd" ); + + skb =__hci_cmd_sync (hdev,QCA_PRE_SHUTDOWN_CMD ,0 , +NULL ,HCI_INIT_TIMEOUT ); +if (IS_ERR (skb)) { + err =PTR_ERR (skb); +bt_dev_err (hdev,"QCA preshutdown_cmd failed (%d)" , err); +return err; + } + +kfree_skb (skb); + +return 0 ; +} +EXPORT_SYMBOL_GPL (qca_send_pre_shutdown_cmd); +static void qca_tlv_check_data (struct rome_config *config,const struct firmware *fw) {
drivers/bluetooth/btqca.h +7 -0
@@ -13,6 +13,7 @@#define EDL_PATCH_TLV_REQ_CMD (0x1E)#define EDL_NVM_ACCESS_SET_REQ_CMD (0x01)#define MAX_SIZE_PER_TLV_SEGMENT (243) +#define QCA_PRE_SHUTDOWN_CMD (0xFC08)#define EDL_CMD_REQ_RES_EVT (0x00)#define EDL_PATCH_VER_RES_EVT (0x19)
@@ -130,6 +131,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, u32 soc_ver);int qca_read_soc_version (struct hci_dev *hdev,u32 *soc_version);int qca_set_bdaddr (struct hci_dev *hdev,const bdaddr_t *bdaddr); +int qca_send_pre_shutdown_cmd (struct hci_dev *hdev);static inline bool qca_is_wcn399x (enum qca_btsoc_type soc_type) {return soc_type ==QCA_WCN3990 || soc_type ==QCA_WCN3998 ;
@@ -161,4 +163,9 @@ static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) {return false; } + +static inline int qca_send_pre_shutdown_cmd (struct hci_dev *hdev) +{ +return -EOPNOTSUPP ; +}#endif
drivers/bluetooth/hci_qca.c +3 -0
@@ -1319,6 +1319,9 @@ static int qca_power_off(struct hci_dev *hdev) {struct hci_uart *hu =hci_get_drvdata (hdev); +/* Perform pre shutdown command */ +qca_send_pre_shutdown_cmd (hdev); +qca_power_shutdown (hu);return 0 ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 20/76 Bluetooth: hidp: Let hidp_send_message return number of queued bytes
In reply to Sasha LevinFrom: Fabian Henneke <[email protected]>
[ Upstream commit 48d9cc9d85dde37c87abb7ac9bbec6598ba44b56 ]
Let hidp_send_message return the number of successfully queued bytes instead of an unconditional 0.
With the return value fixed to 0, other drivers relying on hidp, such as hidraw, can not return meaningful values from their respective implementations of write(). In particular, with the current behavior, a hidraw device's write() will have different return values depending on whether the device is connected via USB or Bluetooth, which makes it harder to abstract away the transport layer.
--- net/bluetooth/hidp/core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
net/bluetooth/hidp/core.c +7 -2
@@ -101,6 +101,7 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock, {struct sk_buff *skb;struct sock *sk = sock->sk; +int ret;BT_DBG ("session %p data %p size %d" , session, data, size);
@@ -114,13 +115,17 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock, }skb_put_u8 (skb, hdr); -if (data && size >0 ) +if (data && size >0 ) {skb_put_data (skb, data, size); + ret = size; + }else { + ret =0 ; + }skb_queue_tail (transmit, skb);wake_up_interruptible (sk_sleep (sk)); -return 0 ; +return ret; } static int hidp_send_ctrl_message(struct hidp_session *session,
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 21/76 s390/qeth: serialize cmd reply with concurrent timeout
In reply to Sasha LevinFrom: Julian Wiedmann <[email protected]>
[ Upstream commit 072f79400032f74917726cf76f4248367ea2b5b8 ]
Callbacks for a cmd reply run outside the protection of card->lock, to allow for additional cmds to be issued & enqueued in parallel.
When qeth_send_control_data() bails out for a cmd without having received a reply (eg. due to timeout), its callback may concurrently be processing a reply that just arrived. In this case, the callback potentially accesses a stale reply->reply_param area that eg. was on-stack and has already been released.
To avoid this race, add some locking so that qeth_send_control_data() can (1) wait for a concurrently running callback, and (2) zap any pending callback that still wants to run.
--- drivers/s390/net/qeth_core.h | 1 + drivers/s390/net/qeth_core_main.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+)
drivers/s390/net/qeth_core.h +1 -0
@@ -640,6 +640,7 @@ struct qeth_seqno {struct qeth_reply {struct list_head list;struct completion received; +spinlock_t lock;int (*callback)(struct qeth_card *,struct qeth_reply *,unsigned long );u32 seqno;
drivers/s390/net/qeth_core_main.c +20 -0
@@ -548,6 +548,7 @@ static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card)if (reply) {refcount_set (&reply->refcnt,1 );init_completion (&reply->received); +spin_lock_init (&reply->lock); }return reply; }
@@ -832,6 +833,13 @@ static void qeth_issue_next_read_cb(struct qeth_card *card,if (!reply->callback) { rc =0 ; + goto no_callback; + } + +spin_lock_irqsave (&reply->lock, flags); +if (reply->rc) { +/* Bail out when the requestor has already left: */ + rc = reply->rc; }else {if (cmd) { reply->offset = (u16)((char *)cmd - (char *)iob->data);
@@ -840,7 +848,9 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, rc = reply->callback (card, reply, (unsigned long )iob); } } +spin_unlock_irqrestore (&reply->lock, flags); +no_callback:if (rc <=0 )qeth_notify_reply (reply, rc);qeth_put_reply (reply);
@@ -1880,6 +1890,16 @@ static int qeth_send_control_data(struct qeth_card *card, int len, rc = (timeout == -ERESTARTSYS ) ? -EINTR : -ETIME ;qeth_dequeue_reply (card, reply); + +if (reply_cb) { +/* Wait until the callback for a late reply has completed: */ +spin_lock_irq (&reply->lock); +if (rc) +/* Zap any callback that's still pending: */ + reply->rc = rc; +spin_unlock_irq (&reply->lock); + } +if (!rc) rc = reply->rc;qeth_put_reply (reply);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 22/76 ibmveth: Convert multicast list size for little-endian system
In reply to Sasha LevinFrom: Thomas Falcon <[email protected]>
[ Upstream commit 66cf4710b23ab2adda11155684a2c8826f4fe732 ]
The ibm,mac-address-filters property defines the maximum number of addresses the hypervisor's multicast filter list can support. It is encoded as a big-endian integer in the OF device tree, but the virtual ethernet driver does not convert it for use by little-endian systems. As a result, the driver is not behaving as it should on affected systems when a large number of multicast addresses are assigned to the device.
--- drivers/net/ethernet/ibm/ibmveth.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/net/ethernet/ibm/ibmveth.c +5 -4
@@ -1605,7 +1605,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)struct net_device *netdev;struct ibmveth_adapter *adapter;unsigned char *mac_addr_p; -unsigned int *mcastFilterSize_p; +__be32 *mcastFilterSize_p;long ret;unsigned long ret_attr;
@@ -1627,8 +1627,9 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)return -EINVAL ; } - mcastFilterSize_p = (unsigned int *)vio_get_attribute (dev, -VETH_MCAST_FILTER_SIZE ,NULL ); + mcastFilterSize_p = (__be32 *)vio_get_attribute (dev, +VETH_MCAST_FILTER_SIZE , +NULL );if (!mcastFilterSize_p) {dev_err (&dev->dev,"Can't find VETH_MCAST_FILTER_SIZE " "attribute\n" );
@@ -1645,7 +1646,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->vdev = dev; adapter->netdev = netdev; - adapter->mcastFilterSize = *mcastFilterSize_p; + adapter->mcastFilterSize =be32_to_cpu (*mcastFilterSize_p); adapter->pool_config =0 ;netif_napi_add (netdev, &adapter->napi, ibmveth_poll,16 );
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 23/76 gpio: Fix build error of function redefinition
In reply to Sasha LevinFrom: YueHaibing <[email protected]>
[ Upstream commit 68e03b85474a51ec1921b4d13204782594ef7223 ]
when do randbuilding, I got this error:
In file included from drivers/hwmon/pmbus/ucd9000.c:19:0:./include/linux/gpio/driver.h:576:1: error: redefinition of gpiochip_add_pin_range
gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, ^~~~~~~~~~~~~~~~~~~~~~
In file included from drivers/hwmon/pmbus/ucd9000.c:18:0:./include/linux/gpio.h:245:1: note: previous definition of gpiochip_add_pin_range was here
gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, ^~~~~~~~~~~~~~~~~~~~~~
--- include/linux/gpio.h | 24 ------------------------ 1 file changed, 24 deletions(-)
include/linux/gpio.h +0 -24
@@ -240,30 +240,6 @@ static inline int irq_to_gpio(unsigned irq)return -EINVAL ; } -static inline int -gpiochip_add_pin_range (struct gpio_chip *chip,const char *pinctl_name, -unsigned int gpio_offset,unsigned int pin_offset, -unsigned int npins) -{ -WARN_ON (1 ); -return -EINVAL ; -} - -static inline int -gpiochip_add_pingroup_range (struct gpio_chip *chip, -struct pinctrl_dev *pctldev, -unsigned int gpio_offset,const char *pin_group) -{ -WARN_ON (1 ); -return -EINVAL ; -} - -static inline void -gpiochip_remove_pin_ranges (struct gpio_chip *chip) -{ -WARN_ON (1 ); -} -static inline int devm_gpio_request (struct device *dev,unsigned gpio,const char *label) {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 24/76 netfilter: nft_flow_offload: skip tcp rst and fin packets
In reply to Sasha LevinFrom: Pablo Neira Ayuso <[email protected]>
[ Upstream commit dfe42be15fde16232340b8b2a57c359f51cc10d9 ]
TCP rst and fin packets do not qualify to place a flow into the flowtable. Most likely there will be no more packets after connection closure. Without this patch, this flow entry expires and connection tracking picks up the entry in ESTABLISHED state using the fixup timeout, which makes this look inconsistent to the user for a connection that is actually already closed.
--- net/netfilter/nft_flow_offload.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
net/netfilter/nft_flow_offload.c +6 -3
@@ -72,11 +72,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, {struct nft_flow_offload *priv =nft_expr_priv (expr);struct nf_flowtable *flowtable = &priv->flowtable->data; +struct tcphdr _tcph, *tcph =NULL ;enum ip_conntrack_info ctinfo;struct nf_flow_route route;struct flow_offload *flow;enum ip_conntrack_dir dir; -bool is_tcp = false;struct nf_conn *ct;int ret;
@@ -89,7 +89,10 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,switch (ct->tuplehash[IP_CT_DIR_ORIGINAL ].tuple.dst.protonum) {case IPPROTO_TCP : - is_tcp = true; + tcph =skb_header_pointer (pkt->skb, pkt->xt.thoff, +sizeof (_tcph), &_tcph); +if (unlikely (!tcph || tcph->fin || tcph->rst)) + goto out;break ;case IPPROTO_UDP :break ;
@@ -115,7 +118,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,if (!flow) goto err_flow_alloc; -if (is_tcp) { +if (tcph) { ct->proto.tcp.seen[0 ].flags |=IP_CT_TCP_FLAG_BE_LIBERAL ; ct->proto.tcp.seen[1 ].flags |=IP_CT_TCP_FLAG_BE_LIBERAL ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 25/76 rxrpc: Fix local endpoint replacement
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit b00df840fb4004b7087940ac5f68801562d0d2de ]
When a local endpoint (struct rxrpc_local) ceases to be in use by any AF_RXRPC sockets, it starts the process of being destroyed, but this doesn't cause it to be removed from the namespace endpoint list immediately as tearing it down isn't trivial and can't be done in softirq context, so it gets deferred.
If a new socket comes along that wants to bind to the same endpoint, a new rxrpc_local object will be allocated and rxrpc_lookup_local() will use list_replace() to substitute the new one for the old.
Then, when the dying object gets to rxrpc_local_destroyer(), it is removed unconditionally from whatever list it is on by calling list_del_init().
However, list_replace() doesn't reset the pointers in the replaced list_head and so the list_del_init() will likely corrupt the local endpoints list.
Fix this by using list_replace_init() instead.
--- net/rxrpc/local_object.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/rxrpc/local_object.c +1 -1
@@ -283,7 +283,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, goto sock_error;if (cursor != &rxnet->local_endpoints) -list_replace (cursor, &local->link); +list_replace_init (cursor, &local->link);else list_add_tail (&local->link, cursor); age ="new" ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 26/76 rxrpc: Fix read-after-free in rxrpc_queue_local()
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit 06d9532fa6b34f12a6d75711162d47c17c1add72 ]
rxrpc_queue_local() attempts to queue the local endpoint it is given and then, if successful, prints a trace line. The trace line includes the current usage count - but we're not allowed to look at the local endpoint at this point as we passed our ref on it to the workqueue.
Fix this by reading the usage count before queuing the work item.
Also fix the reading of local->debug_id for trace lines, which must be done with the same consideration as reading the usage count.
--- include/trace/events/rxrpc.h | 6 +++--- net/rxrpc/local_object.c | 19 ++++++++++--------- 2 files changed, 13 insertions(+), 12 deletions(-)
include/trace/events/rxrpc.h +3 -3
@@ -498,10 +498,10 @@ rxrpc_tx_points;#define E_ (a, b) { a, b } TRACE_EVENT(rxrpc_local, - TP_PROTO(struct rxrpc_local *local, enum rxrpc_local_trace op, + TP_PROTO(unsigned int local_debug_id, enum rxrpc_local_trace op, int usage, const void *where), - TP_ARGS(local, op, usage, where), + TP_ARGS(local_debug_id, op, usage, where), TP_STRUCT__entry( __field(unsigned int, local )
@@ -511,7 +511,7 @@ TRACE_EVENT(rxrpc_local, ), TP_fast_assign( - __entry->local = local->debug_id; + __entry->local = local_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where;
net/rxrpc/local_object.c +10 -9
@@ -93,7 +93,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->debug_id =atomic_inc_return (&rxrpc_debug_id);memcpy (&local->srx, srx,sizeof (*srx)); local->srx.srx_service =0 ; -trace_rxrpc_local (local, rxrpc_local_new,1 ,NULL ); +trace_rxrpc_local (local->debug_id, rxrpc_local_new,1 ,NULL ); }_leave (" = %p" , local);
@@ -321,7 +321,7 @@ struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local)int n; n =atomic_inc_return (&local->usage); -trace_rxrpc_local (local, rxrpc_local_got, n, here); +trace_rxrpc_local (local->debug_id, rxrpc_local_got, n, here);return local; }
@@ -335,7 +335,8 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)if (local) {int n =atomic_fetch_add_unless (&local->usage,1 ,0 );if (n >0 ) -trace_rxrpc_local (local, rxrpc_local_got, n +1 , here); +trace_rxrpc_local (local->debug_id, rxrpc_local_got, + n +1 , here);else local =NULL ; }
@@ -343,16 +344,16 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) }/* -* Queue a local endpoint unless it has become unreferenced and pass the -* caller's reference to the work item. +* Queue a local endpoint and pass the caller's reference to the work item. */ void rxrpc_queue_local (struct rxrpc_local *local) {const void *here =__builtin_return_address (0 ); +unsigned int debug_id = local->debug_id; +int n =atomic_read (&local->usage);if (rxrpc_queue_work (&local->processor)) -trace_rxrpc_local (local, rxrpc_local_queued, -atomic_read (&local->usage), here); +trace_rxrpc_local (debug_id, rxrpc_local_queued, n, here);else rxrpc_put_local (local); }
@@ -367,7 +368,7 @@ void rxrpc_put_local(struct rxrpc_local *local)if (local) { n =atomic_dec_return (&local->usage); -trace_rxrpc_local (local, rxrpc_local_put, n, here); +trace_rxrpc_local (local->debug_id, rxrpc_local_put, n, here);if (n ==0 )call_rcu (&local->rcu, rxrpc_local_rcu);
@@ -454,7 +455,7 @@ static void rxrpc_local_processor(struct work_struct *work) container_of(work, struct rxrpc_local, processor);bool again; -trace_rxrpc_local (local, rxrpc_local_processing, +trace_rxrpc_local (local->debug_id, rxrpc_local_processing,atomic_read (&local->usage),NULL ); do {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 27/76 drm/mediatek: use correct device to import PRIME buffers
In reply to Sasha LevinFrom: Alexandre Courbot <[email protected]>
[ Upstream commit 4c6f3196e6ea111c456c6086dc3f57d4706b0b2d ]
PRIME buffers should be imported using the DMA device. To this end, use a custom import function that mimics drm_gem_prime_import_dev(), but passes the correct device.
--- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)
drivers/gpu/drm/mediatek/mtk_drm_drv.c +13 -1
@@ -320,6 +320,18 @@ static const struct file_operations mtk_drm_fops = { .compat_ioctl = drm_compat_ioctl, }; +/* +* We need to override this because the device used to import the memory is +* not dev->dev, as drm_gem_prime_import() expects. +*/ +struct drm_gem_object *mtk_drm_gem_prime_import (struct drm_device *dev, +struct dma_buf *dma_buf) +{ +struct mtk_drm_private *private = dev->dev_private; + +return drm_gem_prime_import_dev (dev, dma_buf, private->dma_dev); +} +static struct drm_driver mtk_drm_driver = { .driver_features =DRIVER_MODESET |DRIVER_GEM |DRIVER_PRIME |DRIVER_ATOMIC ,
@@ -331,7 +343,7 @@ static struct drm_driver mtk_drm_driver = { .prime_handle_to_fd = drm_gem_prime_handle_to_fd, .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, - .gem_prime_import = drm_gem_prime_import, + .gem_prime_import = mtk_drm_gem_prime_import, .gem_prime_get_sg_table = mtk_gem_prime_get_sg_table, .gem_prime_import_sg_table = mtk_gem_prime_import_sg_table, .gem_prime_mmap = mtk_drm_gem_mmap_buf,
Signature · 6 lines
2.20.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 28/76 drm/mediatek: set DMA max segment size
In reply to Sasha LevinFrom: Alexandre Courbot <[email protected]>
[ Upstream commit 070955558e820b9a89c570b91b1f21762f62b288 ]
This driver requires imported PRIME buffers to appear contiguously in its IO address space. Make sure this is the case by setting the maximum DMA segment size to a more suitable value than the default 64KB.
--- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 35 ++++++++++++++++++++++++-- drivers/gpu/drm/mediatek/mtk_drm_drv.h | 2 ++ 2 files changed, 35 insertions(+), 2 deletions(-)
drivers/gpu/drm/mediatek/mtk_drm_drv.c +33 -2
@@ -213,6 +213,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)struct mtk_drm_private *private = drm->dev_private;struct platform_device *pdev;struct device_node *np; +struct device *dma_dev;int ret;if (!iommu_present (&platform_bus_type))
@@ -275,7 +276,29 @@ static int mtk_drm_kms_init(struct drm_device *drm) goto err_component_unbind; } - private->dma_dev = &pdev->dev; + dma_dev = &pdev->dev; + private->dma_dev = dma_dev; + +/* +* Configure the DMA segment size to make sure we get contiguous IOVA +* when importing PRIME buffers. +*/ +if (!dma_dev->dma_parms) { + private->dma_parms_allocated = true; + dma_dev->dma_parms = +devm_kzalloc (drm->dev,sizeof (*dma_dev->dma_parms), +GFP_KERNEL ); + } +if (!dma_dev->dma_parms) { + ret = -ENOMEM ; + goto err_component_unbind; + } + + ret =dma_set_max_seg_size (dma_dev, (unsigned int )DMA_BIT_MASK (32 )); +if (ret) { +dev_err (dma_dev,"Failed to set DMA segment size\n" ); + goto err_unset_dma_parms; + }/* * We don't use the drm_irq_install() helpers provided by the DRM
@@ -285,13 +308,16 @@ static int mtk_drm_kms_init(struct drm_device *drm) drm->irq_enabled = true; ret =drm_vblank_init (drm,MAX_CRTC );if (ret <0 ) - goto err_component_unbind; + goto err_unset_dma_parms;drm_kms_helper_poll_init (drm);drm_mode_config_reset (drm);return 0 ; +err_unset_dma_parms: +if (private->dma_parms_allocated) + dma_dev->dma_parms =NULL ; err_component_unbind:component_unbind_all (drm->dev, drm); err_config_cleanup:
@@ -302,9 +328,14 @@ static int mtk_drm_kms_init(struct drm_device *drm)static void mtk_drm_kms_deinit (struct drm_device *drm) { +struct mtk_drm_private *private = drm->dev_private; +drm_kms_helper_poll_fini (drm);drm_atomic_helper_shutdown (drm); +if (private->dma_parms_allocated) + private->dma_dev->dma_parms =NULL ; +component_unbind_all (drm->dev, drm);drm_mode_config_cleanup (drm); }
drivers/gpu/drm/mediatek/mtk_drm_drv.h +2 -0
@@ -51,6 +51,8 @@ struct mtk_drm_private { } commit;struct drm_atomic_state *suspend_state; + +bool dma_parms_allocated; };extern struct platform_driver mtk_ddp_driver;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 29/76 scsi: qla2xxx: Fix gnl.l memory leak on adapter init failure
In reply to Sasha LevinFrom: Bill Kuzeja <[email protected]>
[ Upstream commit 26fa656e9a0cbccddf7db132ea020d2169dbe46e ]
If HBA initialization fails unexpectedly (exiting via probe_failed:), we may fail to free vha->gnl.l. So that we don't attempt to double free, set this pointer to NULL after a free and check for NULL at probe_failed: so we know whether or not to call dma_free_coherent.
--- drivers/scsi/qla2xxx/qla_attr.c | 2 ++ drivers/scsi/qla2xxx/qla_os.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-)
drivers/scsi/qla2xxx/qla_attr.c +2 -0
@@ -2956,6 +2956,8 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)dma_free_coherent (&ha->pdev->dev, vha->gnl.size, vha->gnl.l, vha->gnl.ldma); + vha->gnl.l =NULL ; +vfree (vha->scan.l);if (vha->qpair && vha->qpair->vp_idx == vha->vp_idx) {
drivers/scsi/qla2xxx/qla_os.c +10 -1
@@ -3440,6 +3440,12 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)return 0 ; probe_failed: +if (base_vha->gnl.l) { +dma_free_coherent (&ha->pdev->dev, base_vha->gnl.size, + base_vha->gnl.l, base_vha->gnl.ldma); + base_vha->gnl.l =NULL ; + } +if (base_vha->timer_active)qla2x00_stop_timer (base_vha); base_vha->flags.online =0 ;
@@ -3673,7 +3679,7 @@ qla2x00_remove_one(struct pci_dev *pdev)if (!atomic_read (&pdev->enable_cnt)) {dma_free_coherent (&ha->pdev->dev, base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); - + base_vha->gnl.l =NULL ;scsi_host_put (base_vha->host);kfree (ha);pci_set_drvdata (pdev,NULL );
@@ -3713,6 +3719,8 @@ qla2x00_remove_one(struct pci_dev *pdev)dma_free_coherent (&ha->pdev->dev, base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); + base_vha->gnl.l =NULL ; +vfree (base_vha->scan.l);if (IS_QLAFX00 (ha))
@@ -4817,6 +4825,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, "Alloc failed for scan database.\n");dma_free_coherent (&ha->pdev->dev, vha->gnl.size, vha->gnl.l, vha->gnl.ldma); + vha->gnl.l =NULL ;scsi_remove_host (vha->host);return NULL ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 30/76 scsi: target: tcmu: avoid use-after-free after command timeout
In reply to Sasha LevinFrom: Dmitry Fomichev <[email protected]>
[ Upstream commit a86a75865ff4d8c05f355d1750a5250aec89ab15 ]
In tcmu_handle_completion() function, the variable called read_len is always initialized with a value taken from se_cmd structure. If this function is called to complete an expired (timed out) out command, the session command pointed by se_cmd is likely to be already deallocated by the target core at that moment. As the result, this access triggers a use-after-free warning from KASAN.
This patch fixes the code not to touch se_cmd when completing timed out TCMU commands. It also resets the pointer to se_cmd at the time when the TCMU_CMD_BIT_EXPIRED flag is set because it is going to become invalid after calling target_complete_cmd() later in the same function, tcmu_check_expired_cmd().
--- drivers/target/target_core_user.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/target/target_core_user.c +7 -2
@@ -1132,14 +1132,16 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *struct se_cmd *se_cmd = cmd->se_cmd;struct tcmu_dev *udev = cmd->tcmu_dev;bool read_len_valid = false; -uint32_t read_len = se_cmd->data_length; +uint32_t read_len;/* * cmd has been completed already from timeout, just reclaim * data area space and free cmd */ -if (test_bit (TCMU_CMD_BIT_EXPIRED , &cmd->flags)) +if (test_bit (TCMU_CMD_BIT_EXPIRED , &cmd->flags)) { +WARN_ON_ONCE (se_cmd); goto out; + }list_del_init (&cmd->queue_entry);
@@ -1152,6 +1154,7 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * goto done; } + read_len = se_cmd->data_length;if (se_cmd->data_direction =DMA_FROM_DEVICE && (entry->hdr.uflags &TCMU_UFLAG_READ_LEN ) && entry->rsp.read_len) { read_len_valid = true;
@@ -1307,6 +1310,7 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data)*/ scsi_status =SAM_STAT_CHECK_CONDITION ;list_del_init (&cmd->queue_entry); + cmd->se_cmd =NULL ; }else {list_del_init (&cmd->queue_entry);idr_remove (&udev->commands, id);
@@ -2024,6 +2028,7 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level)idr_remove (&udev->commands, i);if (!test_bit (TCMU_CMD_BIT_EXPIRED , &cmd->flags)) { +WARN_ON (!cmd->se_cmd);list_del_init (&cmd->queue_entry);if (err_level =1 ) {/*
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 31/76 cxgb4: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit c554336efa9bbc28d6ec14efbee3c7d63c61a34f ]
In blocked_fl_write(), 't' is not deallocated if bitmap_parse_user() fails, leading to a memory leak bug. To fix this issue, free t before returning the error.
--- drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +3 -1
@@ -3236,8 +3236,10 @@ static ssize_t blocked_fl_write(struct file *filp, const char __user *ubuf,return -ENOMEM ; err =bitmap_parse_user (ubuf, count, t, adap->sge.egr_sz); -if (err) +if (err) { +kvfree (t);return err; + }bitmap_copy (adap->sge.blocked_fl, t, adap->sge.egr_sz);kvfree (t);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 32/76 selftests: kvm: do not try running the VM in vmx_set_nested_state_test
In reply to Sasha LevinFrom: Paolo Bonzini <[email protected]>
[ Upstream commit 92cd0f0be3d7adb63611c28693ec0399beded837 ]
This test is only covering various edge cases of the KVM_SET_NESTED_STATE ioctl. Running the VM does not really add anything.
--- .../kvm/x86_64/vmx_set_nested_state_test.c | 15 --------------- 1 file changed, 15 deletions(-)
tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +0 -15
@@ -27,22 +27,13 @@void test_nested_state (struct kvm_vm *vm,struct kvm_nested_state *state) { -volatile struct kvm_run *run; -vcpu_nested_state_set (vm,VCPU_ID , state, false); - run =vcpu_state (vm,VCPU_ID ); -vcpu_run (vm,VCPU_ID ); -TEST_ASSERT (run->exit_reason ==KVM_EXIT_SHUTDOWN , -"Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n" , - run->exit_reason, -exit_reason_str (run->exit_reason)); }void test_nested_state_expect_errno (struct kvm_vm *vm,struct kvm_nested_state *state,int expected_errno) { -volatile struct kvm_run *run;int rv; rv =vcpu_nested_state_set (vm,VCPU_ID , state, true);
@@ -50,12 +41,6 @@ void test_nested_state_expect_errno(struct kvm_vm *vm,"Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)" ,strerror (expected_errno), expected_errno, rv,strerror (errno), errno); - run =vcpu_state (vm,VCPU_ID ); -vcpu_run (vm,VCPU_ID ); -TEST_ASSERT (run->exit_reason ==KVM_EXIT_SHUTDOWN , -"Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n" , - run->exit_reason, -exit_reason_str (run->exit_reason)); } void test_nested_state_expect_einval(struct kvm_vm *vm,
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 33/76 selftests: kvm: provide common function to enable eVMCS
In reply to Sasha LevinFrom: Paolo Bonzini <[email protected]>
[ Upstream commit 65efa61dc0d536d5f0602c33ee805a57cc07e9dc ]
There are two tests already enabling eVMCS and a third is coming. Add a function that enables the capability and tests the result.
--- tools/testing/selftests/kvm/include/evmcs.h | 2 ++ tools/testing/selftests/kvm/lib/x86_64/vmx.c | 20 +++++++++++++++++++ .../testing/selftests/kvm/x86_64/evmcs_test.c | 15 ++------------ .../selftests/kvm/x86_64/hyperv_cpuid.c | 12 ++++------- 4 files changed, 28 insertions(+), 21 deletions(-)
tools/testing/selftests/kvm/include/evmcs.h +2 -0
@@ -220,6 +220,8 @@ struct hv_enlightened_vmcs {struct hv_enlightened_vmcs *current_evmcs;struct hv_vp_assist_page *current_vp_assist; +int vcpu_enable_evmcs (struct kvm_vm *vm,int vcpu_id); +static inline int enable_vp_assist (uint64_t vp_assist_pa,void *vp_assist) { u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) |
tools/testing/selftests/kvm/lib/x86_64/vmx.c +20 -0
@@ -14,6 +14,26 @@bool enable_evmcs; +int vcpu_enable_evmcs (struct kvm_vm *vm,int vcpu_id) +{ +uint16_t evmcs_ver; + +struct kvm_enable_cap enable_evmcs_cap = { + .cap =KVM_CAP_HYPERV_ENLIGHTENED_VMCS , + .args[0 ] = (unsigned long )&evmcs_ver + }; + +vcpu_ioctl (vm, vcpu_id,KVM_ENABLE_CAP , &enable_evmcs_cap); + +/* KVM should return supported EVMCS version range */ +TEST_ASSERT (((evmcs_ver >>8 ) >= (evmcs_ver &0xff )) && + (evmcs_ver &0xff ) >0 , +"Incorrect EVMCS version range: %x:%x\n" , + evmcs_ver &0xff , evmcs_ver >>8 ); + +return evmcs_ver; +} +/* Allocate memory regions for nested VMX tests. * * Input Args:
tools/testing/selftests/kvm/x86_64/evmcs_test.c +2 -13
@@ -79,11 +79,6 @@ int main(int argc, char *argv[])struct kvm_x86_state *state;struct ucall uc;int stage; -uint16_t evmcs_ver; -struct kvm_enable_cap enable_evmcs_cap = { - .cap =KVM_CAP_HYPERV_ENLIGHTENED_VMCS , - .args[0 ] = (unsigned long )&evmcs_ver - };/* Create VM */ vm =vm_create_default (VCPU_ID ,0 , guest_code);
@@ -96,13 +91,7 @@ int main(int argc, char *argv[])exit (KSFT_SKIP ); } -vcpu_ioctl (vm,VCPU_ID ,KVM_ENABLE_CAP , &enable_evmcs_cap); - -/* KVM should return supported EVMCS version range */ -TEST_ASSERT (((evmcs_ver >>8 ) >= (evmcs_ver &0xff )) && - (evmcs_ver &0xff ) >0 , -"Incorrect EVMCS version range: %x:%x\n" , - evmcs_ver &0xff , evmcs_ver >>8 ); +vcpu_enable_evmcs (vm,VCPU_ID ); run =vcpu_state (vm,VCPU_ID );
@@ -146,7 +135,7 @@ int main(int argc, char *argv[])kvm_vm_restart (vm,O_RDWR );vm_vcpu_add (vm,VCPU_ID ,0 ,0 );vcpu_set_cpuid (vm,VCPU_ID ,kvm_get_supported_cpuid ()); -vcpu_ioctl (vm,VCPU_ID ,KVM_ENABLE_CAP , &enable_evmcs_cap); +vcpu_enable_evmcs (vm,VCPU_ID );vcpu_load_state (vm,VCPU_ID , state); run =vcpu_state (vm,VCPU_ID );free (state);
tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +4 -8
@@ -18,6 +18,7 @@#include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "vmx.h" #define VCPU_ID 0
@@ -106,12 +107,7 @@ int main(int argc, char *argv[]) {struct kvm_vm *vm;int rv; -uint16_t evmcs_ver;struct kvm_cpuid2 *hv_cpuid_entries; -struct kvm_enable_cap enable_evmcs_cap = { - .cap =KVM_CAP_HYPERV_ENLIGHTENED_VMCS , - .args[0 ] = (unsigned long )&evmcs_ver - };/* Tell stdout not to buffer its content */ setbuf (stdout,NULL );
@@ -136,14 +132,14 @@ int main(int argc, char *argv[])free (hv_cpuid_entries); - rv =_vcpu_ioctl (vm,VCPU_ID ,KVM_ENABLE_CAP , &enable_evmcs_cap); - -if (rv) { +if (!kvm_check_cap (KVM_CAP_HYPERV_ENLIGHTENED_VMCS )) {fprintf (stderr,"Enlightened VMCS is unsupported, skip related test\n" ); goto vm_free; } +vcpu_enable_evmcs (vm,VCPU_ID ); + hv_cpuid_entries =kvm_get_supported_hv_cpuid (vm);if (!hv_cpuid_entries)return 1 ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 34/76 selftests: kvm: fix vmx_set_nested_state_test
In reply to Sasha LevinFrom: Paolo Bonzini <[email protected]>
[ Upstream commit c930e19790bbbff31c018009907c813fa0925f63 ]
vmx_set_nested_state_test is trying to use the KVM_STATE_NESTED_EVMCS without enabling enlightened VMCS first. Correct the outcome of the test, and actually test that it succeeds after the capability is enabled.
--- .../kvm/x86_64/vmx_set_nested_state_test.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-)
tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +14 -3
@@ -25,6 +25,8 @@#define VMCS12_REVISION 0x11e57ed0#define VCPU_ID 5 +bool have_evmcs; +void test_nested_state (struct kvm_vm *vm,struct kvm_nested_state *state) {vcpu_nested_state_set (vm,VCPU_ID , state, false);
@@ -75,8 +77,9 @@ void set_default_vmx_state(struct kvm_nested_state *state, int size) {memset (state,0 , size); state->flags =KVM_STATE_NESTED_GUEST_MODE | -KVM_STATE_NESTED_RUN_PENDING | -KVM_STATE_NESTED_EVMCS ; +KVM_STATE_NESTED_RUN_PENDING ; +if (have_evmcs) + state->flags |=KVM_STATE_NESTED_EVMCS ; state->format =0 ; state->size = size; state->hdr.vmx.vmxon_pa =0x1000 ;
@@ -126,13 +129,19 @@ void test_vmx_nested_state(struct kvm_vm *vm)/* * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without * setting the nested state but flags other than eVMCS must be clear. +* The eVMCS flag can be set if the enlightened VMCS capability has +* been enabled. */ set_default_vmx_state (state, state_sz); state->hdr.vmx.vmxon_pa =-1ull ; state->hdr.vmx.vmcs12_pa =-1ull ;test_nested_state_expect_einval (vm, state); - state->flags =KVM_STATE_NESTED_EVMCS ; + state->flags &=KVM_STATE_NESTED_EVMCS ; +if (have_evmcs) { +test_nested_state_expect_einval (vm, state); +vcpu_enable_evmcs (vm,VCPU_ID ); + }test_nested_state (vm, state);/* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */
@@ -217,6 +226,8 @@ int main(int argc, char *argv[])struct kvm_nested_state state;struct kvm_cpuid_entry2 *entry =kvm_get_supported_cpuid_entry (1 ); + have_evmcs =kvm_check_cap (KVM_CAP_HYPERV_ENLIGHTENED_VMCS ); +if (!kvm_check_cap (KVM_CAP_NESTED_STATE )) {printf ("KVM_CAP_NESTED_STATE not available, skipping test\n" );exit (KSFT_SKIP );
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 35/76 liquidio: add cleanup in octeon_setup_iq()
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 6f967f8b1be7001b31c46429f2ee7d275af2190f ]
If oct->fn_list.enable_io_queues() fails, no cleanup is executed, leading to memory/resource leaks. To fix this issue, invoke octeon_delete_instr_queue() before returning from the function.
--- drivers/net/ethernet/cavium/liquidio/request_manager.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/cavium/liquidio/request_manager.c +3 -1
@@ -239,8 +239,10 @@ int octeon_setup_iq(struct octeon_device *oct, } oct->num_iqs++; -if (oct->fn_list.enable_io_queues (oct)) +if (oct->fn_list.enable_io_queues (oct)) { +octeon_delete_instr_queue (oct, iq_no);return 1 ; + }return 0 ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 36/76 net: myri10ge: fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 20fb7c7a39b5c719e2e619673b5f5729ee7d2306 ]
In myri10ge_probe(), myri10ge_alloc_slices() is invoked to allocate slices related structures. Later on, myri10ge_request_irq() is used to get an irq. However, if this process fails, the allocated slices related structures are not deallocated, leading to memory leaks. To fix this issue, revise the target label of the goto statement to 'abort_with_slices'.
--- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/myricom/myri10ge/myri10ge.c +1 -1
@@ -3919,7 +3919,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)* setup (if available). */ status =myri10ge_request_irq (mgp);if (status !=0 ) - goto abort_with_firmware; + goto abort_with_slices;myri10ge_free_irq (mgp);/* Save configuration space to be restored if the
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 37/76 clk: Fix falling back to legacy parent string matching
In reply to Sasha LevinFrom: Stephen Boyd <[email protected]>
[ Upstream commit 4f8c6aba37da199155a121c6cdc38505a9eb0259 ]
Calls to clk_core_get() will return ERR_PTR(-EINVAL) if we've started migrating a clk driver to use the DT based style of specifying parents but we haven't made any DT updates yet. This happens when we pass a non-NULL value as the 'name' argument of of_parse_clkspec(). That function returns -EINVAL in such a situation, instead of -ENOENT like we expected. The return value comes back up to clk_core_fill_parent_index() which proceeds to skip calling clk_core_lookup() because the error pointer isn't equal to -ENOENT, it's -EINVAL.
Furthermore, we blindly overwrite the error pointer returned by clk_core_get() with NULL when there isn't a legacy .name member specified in the parent map. This isn't too bad right now because we don't really care to differentiate NULL from an error, but in the future we should only try to do a legacy lookup if we know we might find something. This way DT lookups that fail don't try to lookup based on strings when there isn't any string to match, hiding the error from DT parsing.
Fix both these problems so that clk provider drivers can use the new style of parent mapping without having to also update their DT at the same time. This patch is based on an earlier patch from Taniya Das which checked for -EINVAL in addition to -ENOENT return values from clk_core_get().
--- drivers/clk/clk.c | 46 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 34 insertions(+), 12 deletions(-)
drivers/clk/clk.c +34 -12
@@ -324,6 +324,25 @@ static struct clk_core *clk_core_lookup(const char *name)return NULL ; } +#ifdef CONFIG_OF +static int of_parse_clkspec (const struct device_node *np,int index, +const char *name,struct of_phandle_args *out_args); +static struct clk_hw * +of_clk_get_hw_from_clkspec (struct of_phandle_args *clkspec); +#else +static inline int of_parse_clkspec (const struct device_node *np,int index, +const char *name, +struct of_phandle_args *out_args) +{ +return -ENOENT ; +} +static inline struct clk_hw * +of_clk_get_hw_from_clkspec (struct of_phandle_args *clkspec) +{ +return ERR_PTR (-ENOENT ); +} +#endif +/** * clk_core_get - Find the clk_core parent of a clk * @core: clk to find parent of
@@ -355,8 +374,9 @@ static struct clk_core *clk_core_lookup(const char *name)* }; * * Returns: -ENOENT when the provider can't be found or the clk doesn't -* exist in the provider. -EINVAL when the name can't be found. NULL when the -* provider knows about the clk but it isn't provided on this system. +* exist in the provider or the name can't be found in the DT node or +* in a clkdev lookup. NULL when the provider knows about the clk but it +* isn't provided on this system. * A valid clk_core pointer when the clk can be found in the provider. */ static struct clk_core *clk_core_get (struct clk_core *core,u8 p_index)
@@ -367,17 +387,19 @@ static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index)struct device *dev = core->dev;const char *dev_id = dev ?dev_name (dev) :NULL ;struct device_node *np = core->of_node; +struct of_phandle_args clkspec; -if (np && (name || index >=0 )) - hw =of_clk_get_hw (np, index, name); - -/* -* If the DT search above couldn't find the provider or the provider -* didn't know about this clk, fallback to looking up via clkdev based -* clk_lookups -*/ -if (PTR_ERR (hw) == -ENOENT && name) +if (np && (name || index >=0 ) && + !of_parse_clkspec (np, index, name, &clkspec)) { + hw =of_clk_get_hw_from_clkspec (&clkspec); +of_node_put (clkspec.np); + }else if (name) { +/* +* If the DT search above couldn't find the provider fallback to +* looking up via clkdev based clk_lookups. +*/ hw =clk_find_hw (dev_id, name); + }if (IS_ERR (hw))return ERR_CAST (hw);
@@ -401,7 +423,7 @@ static void clk_core_fill_parent_index(struct clk_core *core, u8 index) parent =ERR_PTR (-EPROBE_DEFER ); }else { parent =clk_core_get (core, index); -if (IS_ERR (parent) &&PTR_ERR (parent) == -ENOENT ) +if (IS_ERR (parent) &&PTR_ERR (parent) == -ENOENT && entry->name) parent =clk_core_lookup (entry->name); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 38/76 clk: Fix potential NULL dereference in clk_fetch_parent_index()
In reply to Sasha LevinFrom: Martin Blumenstingl <[email protected]>
[ Upstream commit 24876f09a7dfe36a82f53d304d8c1bceb3257a0f ]
Don't compare the parent clock name with a NULL name in the clk_parent_map. This prevents a kernel crash when passing NULL core->parents[i].name to strcmp().
An example which triggered this is a mux clock with four parents when each of them is referenced in the clock driver using clk_parent_data.fw_name and then calling clk_set_parent(clk, 3rd_parent) on this mux.
In this case the first parent is also the HW default so core->parents[i].hw is populated when the clock is registered. Calling clk_set_parent(clk, 3rd_parent) will then go through all parents and skip the first parent because it's hw pointer doesn't match. For the second parent no hw pointer is cached yet and clk_core_get(core, 1) returns a non-matching pointer (which is correct because we are comparing the second with the third parent). Comparing the result of clk_core_get(core, 2) with the requested parent gives a match. However we don't reach this point because right after the clk_core_get(core, 1) mismatch the old code tried to !strcmp(parent->name, NULL) (where the second argument is actually core->parents[i].name, but that was never populated by the clock driver).
--- drivers/clk/clk.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/clk/clk.c +2 -1
@@ -1657,7 +1657,8 @@ static int clk_fetch_parent_index(struct clk_core *core,break ;/* Fallback to comparing globally unique names */ -if (!strcmp (parent->name, core->parents[i].name)) +if (core->parents[i].name && + !strcmp (parent->name, core->parents[i].name))break ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 39/76 lan78xx: Fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit b9cbf8a64865b50fd0f4a3915fa00ac7365cdf8f ]
In lan78xx_probe(), a new urb is allocated through usb_alloc_urb() and saved to 'dev->urb_intr'. However, in the following execution, if an error occurs, 'dev->urb_intr' is not deallocated, leading to memory leaks. To fix this issue, invoke usb_free_urb() to free the allocated urb before returning from the function.
--- drivers/net/usb/lan78xx.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/net/usb/lan78xx.c +5 -3
@@ -3792,7 +3792,7 @@ static int lan78xx_probe(struct usb_interface *intf, ret =register_netdev (netdev);if (ret !=0 ) {netif_err (dev, probe, netdev,"couldn't register the device\n" ); - goto out3; + goto out4; }usb_set_intfdata (intf, dev);
@@ -3807,12 +3807,14 @@ static int lan78xx_probe(struct usb_interface *intf, ret =lan78xx_phy_init (dev);if (ret <0 ) - goto out4; + goto out5;return 0 ; -out4: +out5:unregister_netdev (netdev); +out4: +usb_free_urb (dev->urb_intr); out3:lan78xx_unbind (dev, intf); out2:
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 40/76 vfs: fix page locking deadlocks when deduping files
In reply to Sasha LevinFrom: "Darrick J. Wong" <[email protected]>
[ Upstream commit edc58dd0123b552453a74369bd0c8d890b497b4b ]
When dedupe wants to use the page cache to compare parts of two files for dedupe, we must be very careful to handle locking correctly. The current code doesn't do this. It must lock and unlock the page only once if the two pages are the same, since the overlapping range check doesn't catch this when blocksize < pagesize. If the pages are distinct but from the same file, we must observe page locking order and lock them in order of increasing offset to avoid clashing with writeback locking.
--- fs/read_write.c | 49 +++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 41 insertions(+), 8 deletions(-)
fs/read_write.c +41 -8
@@ -1776,10 +1776,7 @@ static int generic_remap_check_len(struct inode *inode_in,return (remap_flags &REMAP_FILE_DEDUP ) ? -EBADE : -EINVAL ; } -/* -* Read a page's worth of file data into the page cache. Return the page -* locked. -*/ +/* Read a page's worth of file data into the page cache. */ static struct page *vfs_dedupe_get_page (struct inode *inode,loff_t offset) {struct page *page;
@@ -1791,10 +1788,32 @@ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)put_page (page);return ERR_PTR (-EIO ); } -lock_page (page);return page; } +/* +* Lock two pages, ensuring that we lock in offset order if the pages are from +* the same file. +*/ +static void vfs_lock_two_pages (struct page *page1,struct page *page2) +{ +/* Always lock in order of increasing index. */ +if (page1->index > page2->index) +swap (page1, page2); + +lock_page (page1); +if (page1 != page2) +lock_page (page2); +} + +/* Unlock two pages, being careful not to unlock the same page twice. */ +static void vfs_unlock_two_pages (struct page *page1,struct page *page2) +{ +unlock_page (page1); +if (page1 != page2) +unlock_page (page2); +} +/* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races.
@@ -1832,10 +1851,24 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, dest_page =vfs_dedupe_get_page (dest, destoff);if (IS_ERR (dest_page)) { error =PTR_ERR (dest_page); -unlock_page (src_page);put_page (src_page); goto out_error; } + +vfs_lock_two_pages (src_page, dest_page); + +/* +* Now that we've locked both pages, make sure they're still +* mapped to the file data we're interested in. If not, +* someone is invalidating pages on us and we lose. +*/ +if (!PageUptodate (src_page) || !PageUptodate (dest_page) || + src_page->mapping != src->i_mapping || + dest_page->mapping != dest->i_mapping) { + same = false; + goto unlock; + } + src_addr =kmap_atomic (src_page); dest_addr =kmap_atomic (dest_page);
@@ -1847,8 +1880,8 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,kunmap_atomic (dest_addr);kunmap_atomic (src_addr); -unlock_page (dest_page); -unlock_page (src_page); +unlock: +vfs_unlock_two_pages (src_page, dest_page);put_page (dest_page);put_page (src_page);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 41/76 cx82310_eth: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 1eca92eef18719027d394bf1a2d276f43e7cf886 ]
In cx82310_bind(), 'dev->partial_data' is allocated through kmalloc(). Then, the execution waits for the firmware to become ready. If the firmware is not ready in time, the execution is terminated. However, the allocated 'dev->partial_data' is not deallocated on this path, leading to a memory leak bug. To fix this issue, free 'dev->partial_data' before returning the error.
--- drivers/net/usb/cx82310_eth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/usb/cx82310_eth.c +2 -1
@@ -163,7 +163,8 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) }if (!timeout) {dev_err (&udev->dev,"firmware not ready in time\n" ); -return -ETIMEDOUT ; + ret = -ETIMEDOUT ; + goto err; }/* enable ethernet mode (?) */
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 42/76 net: kalmia: fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit f1472cb09f11ddb41d4be84f0650835cb65a9073 ]
In kalmia_init_and_get_ethernet_addr(), 'usb_buf' is allocated through kmalloc(). In the following execution, if the 'status' returned by kalmia_send_init_packet() is not 0, 'usb_buf' is not deallocated, leading to memory leaks. To fix this issue, add the 'out' label to free 'usb_buf'.
--- drivers/net/usb/kalmia.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/net/usb/kalmia.c +3 -3
@@ -113,16 +113,16 @@ kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr) status =kalmia_send_init_packet (dev, usb_buf,ARRAY_SIZE (init_msg_1), usb_buf,24 );if (status !=0 ) -return status; + goto out;memcpy (usb_buf, init_msg_2,12 ); status =kalmia_send_init_packet (dev, usb_buf,ARRAY_SIZE (init_msg_2), usb_buf,28 );if (status !=0 ) -return status; + goto out;memcpy (ethernet_addr, usb_buf +10 ,ETH_ALEN ); - +out:kfree (usb_buf);return status; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 43/76 ibmvnic: Unmap DMA address of TX descriptor buffers after use
In reply to Sasha LevinFrom: Thomas Falcon <[email protected]>
[ Upstream commit 80f0fe0934cd3daa13a5e4d48a103f469115b160 ]
There's no need to wait until a completion is received to unmap TX descriptor buffers that have been passed to the hypervisor. Instead unmap it when the hypervisor call has completed. This patch avoids the possibility that a buffer will not be unmapped because a TX completion is lost or mishandled.
--- drivers/net/ethernet/ibm/ibmvnic.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-)
drivers/net/ethernet/ibm/ibmvnic.c +2 -9
@@ -1568,6 +1568,8 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) lpar_rc =send_subcrq_indirect (adapter, handle_array[queue_num], (u64 )tx_buff->indir_dma, (u64 )num_entries); +dma_unmap_single (dev, tx_buff->indir_dma, +sizeof (tx_buff->indir_arr),DMA_TO_DEVICE ); }else { tx_buff->num_entries = num_entries; lpar_rc = send_subcrq(adapter, handle_array[queue_num],
@@ -2788,7 +2790,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,union sub_crq *next;int index;int i, j; -u8 *first; restart_loop:while (pending_scrq (adapter, scrq)) {
@@ -2818,14 +2819,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, txbuff->data_dma[j] =0 ; } -/* if sub_crq was sent indirectly */ - first = &txbuff->indir_arr[0 ].generic.first; -if (*first ==IBMVNIC_CRQ_CMD ) { -dma_unmap_single (dev, txbuff->indir_dma, -sizeof (txbuff->indir_arr), -DMA_TO_DEVICE ); - *first =0 ; - }if (txbuff->last_frag) {dev_kfree_skb_any (txbuff->skb);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 44/76 net: cavium: fix driver name
In reply to Sasha LevinFrom: Stephen Hemminger <[email protected]>
[ Upstream commit 3434341004a380f4e47c3a03d4320d43982162a0 ]
The driver name gets exposed in sysfs under /sys/bus/pci/drivers so it should look like other devices. Change it to be common format (instead of "Cavium PTP").
This is a trivial fix that was observed by accident because Debian kernels were building this driver into kernel (bug).
--- drivers/net/ethernet/cavium/common/cavium_ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/cavium/common/cavium_ptp.c +1 -1
@@ -10,7 +10,7 @@#include "cavium_ptp.h" -#define DRV_NAME "Cavium PTP Driver" +#define DRV_NAME "cavium_ptp"#define PCI_DEVICE_ID_CAVIUM_PTP 0xA00C#define PCI_DEVICE_ID_CAVIUM_RST 0xA00E
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 45/76 wimax/i2400m: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 44ef3a03252844a8753479b0cea7f29e4a804bdc ]
In i2400m_barker_db_init(), 'options_orig' is allocated through kstrdup() to hold the original command line options. Then, the options are parsed. However, if an error occurs during the parsing process, 'options_orig' is not deallocated, leading to a memory leak bug. To fix this issue, free 'options_orig' before returning the error.
--- drivers/net/wimax/i2400m/fw.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/wimax/i2400m/fw.c +3 -1
@@ -351,13 +351,15 @@ int i2400m_barker_db_init(const char *_options) } result =i2400m_barker_db_add (barker);if (result <0 ) - goto error_add; + goto error_parse_add; }kfree (options_orig); }return 0 ; +error_parse_add: error_parse: +kfree (options_orig); error_add:kfree (i2400m_barker_db);return result;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 46/76 ravb: Fix use-after-free ravb_tstamp_skb
In reply to Sasha LevinFrom: Tho Vu <[email protected]>
[ Upstream commit cfef46d692efd852a0da6803f920cc756eea2855 ]
When a Tx timestamp is requested, a pointer to the skb is stored in the ravb_tstamp_skb struct. This was done without an skb_get. There exists the possibility that the skb could be freed by ravb_tx_free (when ravb_tx_free is called from ravb_start_xmit) before the timestamp was processed, leading to a use-after-free bug.
Use skb_get when filling a ravb_tstamp_skb struct, and add appropriate frees/consumes when a ravb_tstamp_skb struct is freed.
--- drivers/net/ethernet/renesas/ravb_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/net/ethernet/renesas/ravb_main.c +6 -2
@@ -1,7 +1,7 @@// SPDX-License-Identifier: GPL-2.0 /* Renesas Ethernet AVB device driver * -* Copyright (C) 2014-2015 Renesas Electronics Corporation +* Copyright (C) 2014-2019 Renesas Electronics Corporation * Copyright (C) 2015 Renesas Solutions Corp. * Copyright (C) 2015-2016 Cogent Embedded, Inc. <[email protected]> *
@@ -513,7 +513,10 @@ static void ravb_get_tx_tstamp(struct net_device *ndev)kfree (ts_skb);if (tag == tfa_tag) {skb_tstamp_tx (skb, &shhwtstamps); +dev_consume_skb_any (skb);break ; + }else { +dev_kfree_skb_any (skb); } }ravb_modify (ndev,TCCR ,TCCR_TFR ,TCCR_TFR );
@@ -1564,7 +1567,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) } goto unmap; } - ts_skb->skb = skb; + ts_skb->skb =skb_get (skb); ts_skb->tag = priv->ts_skb_tag++; priv->ts_skb_tag &=0x3ff ;list_add_tail (&ts_skb->list, &priv->ts_skb_list);
@@ -1693,6 +1696,7 @@ static int ravb_close(struct net_device *ndev)/* Clear the timestamp list */ list_for_each_entry_safe (ts_skb, ts_skb2, &priv->ts_skb_list, list) {list_del (&ts_skb->list); +kfree_skb (ts_skb->skb);kfree (ts_skb); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 47/76 sched/core: Schedule new worker even if PI-blocked
In reply to Sasha LevinFrom: Sebastian Andrzej Siewior <[email protected]>
[ Upstream commit b0fdc01354f45d43f082025636ef808968a27b36 ]
If a task is PI-blocked (blocking on sleeping spinlock) then we don't want to schedule a new kworker if we schedule out due to lock contention because !RT does not do that as well. A spinning spinlock disables preemption and a worker does not schedule out on lock contention (but spin).
On RT the RW-semaphore implementation uses an rtmutex so tsk_is_pi_blocked() will return true if a task blocks on it. In this case we will now start a new worker which may deadlock if one worker is waiting on progress from another worker. Since a RW-semaphore starts a new worker on !RT, we should do the same on RT.
XFS is able to trigger this deadlock.
Allow to schedule new worker if the current worker is PI-blocked.
--- kernel/sched/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
kernel/sched/core.c +4 -1
@@ -3469,7 +3469,7 @@ void __noreturn do_task_dead(void)static inline void sched_submit_work (struct task_struct *tsk) { -if (!tsk->state ||tsk_is_pi_blocked (tsk)) +if (!tsk->state)return ;/*
@@ -3485,6 +3485,9 @@ static inline void sched_submit_work(struct task_struct *tsk)preempt_enable_no_resched (); } +if (tsk_is_pi_blocked (tsk)) +return ; +/* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks.
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 48/76 kprobes: Fix potential deadlock in kprobe_optimizer()
In reply to Sasha LevinFrom: Andrea Righi <[email protected]>
[ Upstream commit f1c6ece23729257fb46562ff9224cf5f61b818da ]
lockdep reports the following deadlock scenario:
WARNING: possible circular locking dependency detected
kworker/1:1/48 is trying to acquire lock:
000000008d7a62b2 (text_mutex){+.+.}, at: kprobe_optimizer+0x163/0x290
but task is already holding lock:
00000000850b5e2d (module_mutex){+.+.}, at: kprobe_optimizer+0x31/0x290
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (module_mutex){+.+.}:
__mutex_lock+0xac/0x9f0
mutex_lock_nested+0x1b/0x20
set_all_modules_text_rw+0x22/0x90
ftrace_arch_code_modify_prepare+0x1c/0x20
ftrace_run_update_code+0xe/0x30
ftrace_startup_enable+0x2e/0x50
ftrace_startup+0xa7/0x100
register_ftrace_function+0x27/0x70
arm_kprobe+0xb3/0x130
enable_kprobe+0x83/0xa0
enable_trace_kprobe.part.0+0x2e/0x80
kprobe_register+0x6f/0xc0
perf_trace_event_init+0x16b/0x270
perf_kprobe_init+0xa7/0xe0
perf_kprobe_event_init+0x3e/0x70
perf_try_init_event+0x4a/0x140
perf_event_alloc+0x93a/0xde0
__do_sys_perf_event_open+0x19f/0xf30
__x64_sys_perf_event_open+0x20/0x30
do_syscall_64+0x65/0x1d0
entry_SYSCALL_64_after_hwframe+0x49/0xbe-> #0 (text_mutex){+.+.}:
__lock_acquire+0xfcb/0x1b60
lock_acquire+0xca/0x1d0
__mutex_lock+0xac/0x9f0
mutex_lock_nested+0x1b/0x20
kprobe_optimizer+0x163/0x290
process_one_work+0x22b/0x560
worker_thread+0x50/0x3c0
kthread+0x112/0x150
ret_from_fork+0x3a/0x50other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(module_mutex);
lock(text_mutex);
lock(module_mutex); lock(text_mutex);
*** DEADLOCK ***
As a reproducer I've been using bcc's funccount.py
(https://github.com/iovisor/bcc/blob/master/tools/funccount.py),
for example:
# ./funccount.py '*interrupt*'
That immediately triggers the lockdep splat.
Fix by acquiring text_mutex before module_mutex in kprobe_optimizer().
--- kernel/kprobes.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
kernel/kprobes.c +4 -4
@@ -470,6 +470,7 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);*/ static void do_optimize_kprobes (void ) { +lockdep_assert_held (&text_mutex);/* * The optimization/unoptimization refers online_cpus via * stop_machine() and cpu-hotplug modifies online_cpus.
@@ -487,9 +488,7 @@ static void do_optimize_kprobes(void) list_empty(&optimizing_list))return ; -mutex_lock (&text_mutex);arch_optimize_kprobes (&optimizing_list); -mutex_unlock (&text_mutex); }/*
@@ -500,6 +499,7 @@ static void do_unoptimize_kprobes(void) {struct optimized_kprobe *op, *tmp; +lockdep_assert_held (&text_mutex);/* See comment in do_optimize_kprobes() */ lockdep_assert_cpus_held ();
@@ -507,7 +507,6 @@ static void do_unoptimize_kprobes(void)if (list_empty (&unoptimizing_list))return ; -mutex_lock (&text_mutex);arch_unoptimize_kprobes (&unoptimizing_list, &freeing_list);/* Loop free_list for disarming */ list_for_each_entry_safe (op, tmp, &freeing_list, list) {
@@ -524,7 +523,6 @@ static void do_unoptimize_kprobes(void) }else list_del_init (&op->list); } -mutex_unlock (&text_mutex); }/* Reclaim all kprobes on the free_list */
@@ -556,6 +554,7 @@ static void kprobe_optimizer(struct work_struct *work) {mutex_lock (&kprobe_mutex);cpus_read_lock (); +mutex_lock (&text_mutex);/* Lock modules while optimizing kprobes */ mutex_lock (&module_mutex);
@@ -583,6 +582,7 @@ static void kprobe_optimizer(struct work_struct *work)do_free_cleaned_kprobes ();mutex_unlock (&module_mutex); +mutex_unlock (&text_mutex);cpus_read_unlock ();mutex_unlock (&kprobe_mutex);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 49/76 HID: intel-ish-hid: ipc: add EHL device id
In reply to Sasha LevinFrom: Even Xu <[email protected]>
[ Upstream commit b640be5bc8e4673dc8049cf74176ddedecea5597 ]
EHL is a new platform using ishtp solution, add its device id to support list.
--- drivers/hid/intel-ish-hid/ipc/hw-ish.h | 1 + drivers/hid/intel-ish-hid/ipc/pci-ish.c | 1 + 2 files changed, 2 insertions(+)
drivers/hid/intel-ish-hid/ipc/hw-ish.h +1 -0
@@ -24,6 +24,7 @@#define ICL_MOBILE_DEVICE_ID 0x34FC#define SPT_H_DEVICE_ID 0xA135#define CML_LP_DEVICE_ID 0x02FC +#define EHL_Ax_DEVICE_ID 0x4BB3#define REVISION_ID_CHT_A0 0x6#define REVISION_ID_CHT_Ax_SI 0x0
drivers/hid/intel-ish-hid/ipc/pci-ish.c +1 -0
@@ -33,6 +33,7 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ICL_MOBILE_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CML_LP_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, EHL_Ax_DEVICE_ID)}, {0, } };MODULE_DEVICE_TABLE (pci, ish_pci_tbl);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 50/76 HID: cp2112: prevent sleeping function called from invalid context
In reply to Sasha LevinFrom: Benjamin Tissoires <[email protected]>
[ Upstream commit 2d05dba2b25ecb0f8fc3a0b4eb2232da6454a47b ]
When calling request_threaded_irq() with a CP2112, the function cp2112_gpio_irq_startup() is called in a IRQ context.
Therefore we can not sleep, and we can not callcp2112_gpio_direction_input() there.
Move the call to cp2112_gpio_direction_input() earlier to have a working driver.
--- drivers/hid/hid-cp2112.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/hid/hid-cp2112.c +6 -2
@@ -1152,8 +1152,6 @@ static unsigned int cp2112_gpio_irq_startup(struct irq_data *d)INIT_DELAYED_WORK (&dev->gpio_poll_worker, cp2112_gpio_poll_callback); -cp2112_gpio_direction_input (gc, d->hwirq); -if (!dev->gpio_poll) { dev->gpio_poll = true;schedule_delayed_work (&dev->gpio_poll_worker,0 );
@@ -1201,6 +1199,12 @@ static int __maybe_unused cp2112_allocate_irq(struct cp2112_device *dev,return PTR_ERR (dev->desc[pin]); } + ret =cp2112_gpio_direction_input (&dev->gc, pin); +if (ret <0 ) { +dev_err (dev->gc.parent,"Failed to set GPIO to input dir\n" ); + goto err_desc; + } + ret =gpiochip_lock_as_irq (&dev->gc, pin);if (ret) {dev_err (dev->gc.parent,"Failed to lock GPIO as interrupt\n" );
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 51/76 x86/boot/compressed/64: Fix boot on machines with broken E820 table
In reply to Sasha LevinFrom: "Kirill A. Shutemov" <[email protected]>
[ Upstream commit 0a46fff2f9108c2c44218380a43a736cf4612541 ]
BIOS on Samsung 500C Chromebook reports very rudimentary E820 table that consists of 2 entries:
BIOS-e820: [mem 0x0000000000000000-0x0000000000000fff] usable
BIOS-e820: [mem 0x00000000fffff000-0x00000000ffffffff] reserved
It breaks logic in find_trampoline_placement(): bios_start lands on the end of the first 4k page and trampoline start gets placed below 0.
Detect underflow and don't touch bios_start for such cases. It makes kernel ignore E820 table on machines that doesn't have two usable pages below BIOS_START_MAX.
--- arch/x86/boot/compressed/pgtable_64.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
arch/x86/boot/compressed/pgtable_64.c +10 -3
@@ -73,6 +73,8 @@ static unsigned long find_trampoline_placement(void)/* Find the first usable memory region under bios_start. */ for (i = boot_params->e820_entries -1 ; i >=0 ; i--) { +unsigned long new; + entry = &boot_params->e820_table[i];/* Skip all entries above bios_start. */
@@ -85,15 +87,20 @@ static unsigned long find_trampoline_placement(void)/* Adjust bios_start to the end of the entry if needed. */ if (bios_start > entry->addr + entry->size) - bios_start = entry->addr + entry->size; + new = entry->addr + entry->size;/* Keep bios_start page-aligned. */ - bios_start =round_down (bios_start,PAGE_SIZE ); + new =round_down (new,PAGE_SIZE );/* Skip the entry if it's too small. */ -if (bios_start -TRAMPOLINE_32BIT_SIZE < entry->addr) +if (new -TRAMPOLINE_32BIT_SIZE < entry->addr)continue ; +/* Protect against underflow. */ +if (new -TRAMPOLINE_32BIT_SIZE > bios_start) +break ; + + bios_start = new;break ; }
Signature · 1 line
2.20.1
Re: [PATCH AUTOSEL 5.2 51/76] x86/boot/compressed/64: Fix boot on machines with broken E820 table
Quoted 17 lines · Sasha Levin
From: "Kirill A. Shutemov" <[email protected]>
[ Upstream commit
0a46fff2f9108c2c44218380a43a736cf4612541]BIOS on Samsung 500C Chromebook reports very rudimentary E820 table that consists of 2 entries:
BIOS-e820: [mem 0x0000000000000000-0x0000000000000fff] usable
BIOS-e820: [mem 0x00000000fffff000-0x00000000ffffffff] reservedIt breaks logic in
find_trampoline_placement():bios_startlands on the end of the first 4k page and trampoline start gets placed below 0.Detect underflow and don't touch
bios_startfor such cases. It makes kernel ignore E820 table on machines that doesn't have two usable pages belowBIOS_START_MAX.
Quoted 10 lines
Fixes 1b3a62643660 ("x86/boot/compressed/64: Validate trampoline placement against E820")Signed-off-by Kirill A. Shutemov <[email protected]>Signed-off-by Borislav Petkov <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc Ingo Molnar <[email protected]>Cc Thomas Gleixner <[email protected]>Cc x86-ml <[email protected]>Signed-off-by Sasha Levin <[email protected]>
Please postpone backporting the patch (and into other trees). There's a fixup for it:
http://lore.kernel.org/r/20190826133326.7cxb4vbmiawffv2r@box
Signature · 1 line
Kirill A. Shutemov
Sasha Levin
maintainerRe: [PATCH AUTOSEL 5.2 51/76] x86/boot/compressed/64: Fix boot on machines with broken E820 table
Quoted 29 lines · Kirill A. Shutemov
Quoted 17 lines · Sasha Levin
From: "Kirill A. Shutemov" <[email protected]>
[ Upstream commit
0a46fff2f9108c2c44218380a43a736cf4612541]BIOS on Samsung 500C Chromebook reports very rudimentary E820 table that consists of 2 entries:
BIOS-e820: [mem 0x0000000000000000-0x0000000000000fff] usable
BIOS-e820: [mem 0x00000000fffff000-0x00000000ffffffff] reservedIt breaks logic in
find_trampoline_placement():bios_startlands on the end of the first 4k page and trampoline start gets placed below 0.Detect underflow and don't touch
bios_startfor such cases. It makes kernel ignore E820 table on machines that doesn't have two usable pages belowBIOS_START_MAX.Quoted 10 lines
Fixes 1b3a62643660 ("x86/boot/compressed/64: Validate trampoline placement against E820")Signed-off-by Kirill A. Shutemov <[email protected]>Signed-off-by Borislav Petkov <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc Ingo Molnar <[email protected]>Cc Thomas Gleixner <[email protected]>Cc x86-ml <[email protected]>Signed-off-by Sasha Levin <[email protected]>
Quoted 4 lines
Please postpone backporting the patch (and into other trees). There's a fixup for it:
http://lore.kernel.org/r/20190826133326.7cxb4vbmiawffv2r@box
Sure. Should I just queue it up for a week or two later (along with the fixes), or do you want to let me know when?
--
Thanks,
Sasha
Re: [PATCH AUTOSEL 5.2 51/76] x86/boot/compressed/64: Fix boot on machines with broken E820 table
Quoted 30 lines · Sasha Levin
Quoted 29 lines · Kirill A. Shutemov
Quoted 27 lines · Sasha Levin
From: "Kirill A. Shutemov" <[email protected]>
[ Upstream commit
0a46fff2f9108c2c44218380a43a736cf4612541]BIOS on Samsung 500C Chromebook reports very rudimentary E820 table that consists of 2 entries:
BIOS-e820: [mem 0x0000000000000000-0x0000000000000fff] usable
BIOS-e820: [mem 0x00000000fffff000-0x00000000ffffffff] reservedIt breaks logic in
find_trampoline_placement():bios_startlands on the end of the first 4k page and trampoline start gets placed below 0.Detect underflow and don't touch
bios_startfor such cases. It makes kernel ignore E820 table on machines that doesn't have two usable pages belowBIOS_START_MAX.Fixes 1b3a62643660 ("x86/boot/compressed/64: Validate trampoline placement against E820")Signed-off-by Kirill A. Shutemov <[email protected]>Signed-off-by Borislav Petkov <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc Ingo Molnar <[email protected]>Cc Thomas Gleixner <[email protected]>Cc x86-ml <[email protected]>Signed-off-by Sasha Levin <[email protected]>
Quoted 7 lines
Quoted 4 lines
Please postpone backporting the patch (and into other trees). There's a fixup for it:
http://lore.kernel.org/r/20190826133326.7cxb4vbmiawffv2r@box
Sure. Should I just queue it up for a week or two later (along with the fixes), or do you want to let me know when?
You can queue it up later (two weeks is fine) once the fixup hit Linus' tree.
Signature · 1 line
Kirill A. Shutemov
Sasha Levin
maintainerPATCH 52/76 scsi: lpfc: Mitigate high memory pre-allocation by SCSI-MQ
In reply to Sasha LevinFrom: James Smart <[email protected]>
[ Upstream commit 77ffd3465ba837e9dc714e17b014e77b2eae765a ]
When SCSI-MQ is enabled, the SCSI-MQ layers will do pre-allocation of MQ resources based on shost values set by the driver. In newer cases of the driver, which attempts to set nr_hw_queues to the cpu count, the multipliers become excessive, with a single shost having SCSI-MQ pre-allocation reaching into the multiple GBytes range. NPIV, which creates additional shosts, only multiply this overhead. On lower-memory systems, this can exhaust system memory very quickly, resulting in a system crash or failures in the driver or elsewhere due to low memory conditions.
After testing several scenarios, the situation can be mitigated by limiting the value set in shost->nr_hw_queues to 4. Although the shost values were changed, the driver still had per-cpu hardware queues of its own that allowed parallelization per-cpu. Testing revealed that even with the smallish number for nr_hw_queues for SCSI-MQ, performance levels remained near maximum with the within-driver affiinitization.
A module parameter was created to allow the value set for the nr_hw_queues to be tunable.
--- drivers/scsi/lpfc/lpfc.h | 1 + drivers/scsi/lpfc/lpfc_attr.c | 15 +++++++++++++++ drivers/scsi/lpfc/lpfc_init.c | 10 ++++++---- drivers/scsi/lpfc/lpfc_sli4.h | 5 +++++ 4 files changed, 27 insertions(+), 4 deletions(-)
drivers/scsi/lpfc/lpfc.h +1 -0
@@ -822,6 +822,7 @@ struct lpfc_hba {uint32_t cfg_cq_poll_threshold;uint32_t cfg_cq_max_proc_limit;uint32_t cfg_fcp_cpu_map; +uint32_t cfg_fcp_mq_threshold;uint32_t cfg_hdw_queue;uint32_t cfg_irq_chann;uint32_t cfg_suppress_rsp;
drivers/scsi/lpfc/lpfc_attr.c +15 -0
@@ -5640,6 +5640,19 @@ LPFC_ATTR_RW(nvme_oas, 0, 0, 1,LPFC_ATTR_RW (nvme_embed_cmd,1 ,0 ,2 ,"Embed NVME Command in WQE" ); +/* +* lpfc_fcp_mq_threshold: Set the maximum number of Hardware Queues +* the driver will advertise it supports to the SCSI layer. +* +* 0 = Set nr_hw_queues by the number of CPUs or HW queues. +* 1,128 = Manually specify the maximum nr_hw_queue value to be set, +* +* Value range is [0,128]. Default value is 8. +*/ +LPFC_ATTR_R (fcp_mq_threshold,LPFC_FCP_MQ_THRESHOLD_DEF , +LPFC_FCP_MQ_THRESHOLD_MIN ,LPFC_FCP_MQ_THRESHOLD_MAX , +"Set the number of SCSI Queues advertised" ); +/* * lpfc_hdw_queue: Set the number of Hardware Queues the driver * will advertise it supports to the NVME and SCSI layers. This also
@@ -5961,6 +5974,7 @@ struct device_attribute *lpfc_hba_attrs[] = { &dev_attr_lpfc_cq_poll_threshold, &dev_attr_lpfc_cq_max_proc_limit, &dev_attr_lpfc_fcp_cpu_map, + &dev_attr_lpfc_fcp_mq_threshold, &dev_attr_lpfc_hdw_queue, &dev_attr_lpfc_irq_chann, &dev_attr_lpfc_suppress_rsp,
@@ -7042,6 +7056,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)/* Initialize first burst. Target vs Initiator are different. */ lpfc_nvme_enable_fb_init (phba, lpfc_nvme_enable_fb);lpfc_nvmet_fb_size_init (phba, lpfc_nvmet_fb_size); +lpfc_fcp_mq_threshold_init (phba, lpfc_fcp_mq_threshold);lpfc_hdw_queue_init (phba, lpfc_hdw_queue);lpfc_irq_chann_init (phba, lpfc_irq_chann);lpfc_enable_bbcr_init (phba, lpfc_enable_bbcr);
drivers/scsi/lpfc/lpfc_init.c +6 -4
@@ -4308,10 +4308,12 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) shost->max_cmd_len =16 ;if (phba->sli_rev ==LPFC_SLI_REV4 ) { -if (phba->cfg_fcp_io_sched ==LPFC_FCP_SCHED_BY_HDWQ ) - shost->nr_hw_queues = phba->cfg_hdw_queue; -else - shost->nr_hw_queues = phba->sli4_hba.num_present_cpu; +if (!phba->cfg_fcp_mq_threshold || + phba->cfg_fcp_mq_threshold > phba->cfg_hdw_queue) + phba->cfg_fcp_mq_threshold = phba->cfg_hdw_queue; + + shost->nr_hw_queues =min_t (int,2 *num_possible_nodes (), + phba->cfg_fcp_mq_threshold); shost->dma_boundary = phba->sli4_hba.pc_sli4_params.sge_supp_len-1 ;
drivers/scsi/lpfc/lpfc_sli4.h +5 -0
@@ -44,6 +44,11 @@#define LPFC_HBA_HDWQ_MAX 128#define LPFC_HBA_HDWQ_DEF 0 +/* FCP MQ queue count limiting */ +#define LPFC_FCP_MQ_THRESHOLD_MIN 0 +#define LPFC_FCP_MQ_THRESHOLD_MAX 128 +#define LPFC_FCP_MQ_THRESHOLD_DEF 8 +/* Common buffer size to accomidate SCSI and NVME IO buffers */ #define LPFC_COMMON_IO_BUF_SZ 768
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 53/76 Input: hyperv-keyboard: Use in-place iterator API in the channel callback
In reply to Sasha LevinFrom: Dexuan Cui <[email protected]>
[ Upstream commit d09bc83640d524b8467a660db7b1d15e6562a1de ]
Simplify the ring buffer handling with the in-place API.
Also avoid the dynamic allocation and the memory leak in the channel callback function.
--- drivers/input/serio/hyperv-keyboard.c | 35 +++++---------------------- 1 file changed, 6 insertions(+), 29 deletions(-)
drivers/input/serio/hyperv-keyboard.c +6 -29
@@ -237,40 +237,17 @@ static void hv_kbd_handle_received_packet(struct hv_device *hv_dev,static void hv_kbd_on_channel_callback (void *context) { +struct vmpacket_descriptor *desc;struct hv_device *hv_dev = context; -void *buffer; -int bufferlen =0x100 ;/* Start with sensible size */ u32 bytes_recvd;u64 req_id; -int error; - buffer =kmalloc (bufferlen,GFP_ATOMIC ); -if (!buffer) -return ; - -while (1 ) { - error =vmbus_recvpacket_raw (hv_dev->channel, buffer, bufferlen, - &bytes_recvd, &req_id); -switch (error) { -case 0 : -if (bytes_recvd ==0 ) { -kfree (buffer); -return ; - } - -hv_kbd_handle_received_packet (hv_dev, buffer, - bytes_recvd, req_id); -break ; + foreach_vmbus_pkt(desc, hv_dev->channel) { + bytes_recvd = desc->len8 *8 ; + req_id = desc->trans_id; -case -ENOBUFS : -kfree (buffer); -/* Handle large packet */ - bufferlen = bytes_recvd; - buffer =kmalloc (bytes_recvd,GFP_ATOMIC ); -if (!buffer) -return ; -break ; - } +hv_kbd_handle_received_packet (hv_dev, desc, bytes_recvd, + req_id); } }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 54/76 Tools: hv: kvp: eliminate 'may be used uninitialized' warning
In reply to Sasha LevinFrom: Vitaly Kuznetsov <[email protected]>
[ Upstream commit 89eb4d8d25722a0a0194cf7fa47ba602e32a6da7 ]
When building hv_kvp_daemon GCC-8.3 complains:
hv_kvp_daemon.c: In function ‘kvp_get_ip_info.constprop’:
hv_kvp_daemon.c:812:30: warning: ‘ip_buffer’ may be used uninitialized in this function [-Wmaybe-uninitialized]
struct hv_kvp_ipaddr_value *ip_buffer;
this seems to be a false positive: we only use ip_buffer when op == KVP_OP_GET_IP_INFO and it is only unset when op == KVP_OP_ENUMERATE.
Silence the warning by initializing ip_buffer to NULL.
--- tools/hv/hv_kvp_daemon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/hv/hv_kvp_daemon.c +1 -1
@@ -809,7 +809,7 @@ kvp_get_ip_info(int family, char *if_name, int op,int sn_offset =0 ;int error =0 ;char *buffer; -struct hv_kvp_ipaddr_value *ip_buffer; +struct hv_kvp_ipaddr_value *ip_buffer =NULL ;char cidr_mask[5 ];/* /xyz */ int weight;int i;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 55/76 io_uring: fix potential hang with polled IO
In reply to Sasha LevinFrom: Jens Axboe <[email protected]>
[ Upstream commit 500f9fbadef86466a435726192f4ca4df7d94236 ]
If a request issue ends up being punted to async context to avoid blocking, we can get into a situation where the original application enters the poll loop for that very request before it has been issued. This should not be an issue, except that the polling will hold the io_uring uring_ctx mutex for the duration of the poll. When the async worker has actually issued the request, it needs to acquire this mutex to add the request to the poll issued list. Since the application polling is already holding this mutex, the workqueue sleeps on the mutex forever, and the application thus never gets a chance to poll for the very request it was interested in.
Fix this by ensuring that the polling drops the uring_ctx occasionally if it's not making any progress.
--- fs/io_uring.c | 36 +++++++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 11 deletions(-)
fs/io_uring.c +25 -11
@@ -743,11 +743,34 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)static int io_iopoll_check (struct io_ring_ctx *ctx,unsigned *nr_events,long min) { -int ret =0 ; +int iters, ret =0 ; + +/* +* We disallow the app entering submit/complete with polling, but we +* still need to lock the ring to prevent racing with polled issue +* that got punted to a workqueue. +*/ +mutex_lock (&ctx->uring_lock); + iters =0 ; do { int tmin = 0; + /* + * If a submit got punted to a workqueue, we can have the + * application entering polling for a command before it gets + * issued. That app will hold the uring_lock for the duration + * of the poll right here, so we need to take a breather every + * now and then to ensure that the issue has a chance to add + * the poll to the issued list. Otherwise we can spin here + * forever, while the workqueue is stuck trying to acquire the + * very same mutex. + */ + if (!(++iters & 7)) { + mutex_unlock(&ctx->uring_lock); + mutex_lock(&ctx->uring_lock); + } + if (*nr_events < min) tmin = min - *nr_events;
@@ -757,6 +780,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, ret =0 ; }while (min && !*nr_events && !need_resched ()); +mutex_unlock (&ctx->uring_lock);return ret; }
@@ -2073,15 +2097,7 @@ static int io_sq_thread(void *data)unsigned nr_events =0 ;if (ctx->flags &IORING_SETUP_IOPOLL ) { -/* -* We disallow the app entering submit/complete -* with polling, but we still need to lock the -* ring to prevent racing with polled issue -* that got punted to a workqueue. -*/ -mutex_lock (&ctx->uring_lock);io_iopoll_check (ctx, &nr_events,0 ); -mutex_unlock (&ctx->uring_lock); }else {/* * Normal IO, just pretend everything completed.
@@ -2978,9 +2994,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, min_complete =min (min_complete, ctx->cq_entries);if (ctx->flags &IORING_SETUP_IOPOLL ) { -mutex_lock (&ctx->uring_lock); ret =io_iopoll_check (ctx, &nr_events, min_complete); -mutex_unlock (&ctx->uring_lock); }else { ret =io_cqring_wait (ctx, min_complete, sig, sigsz); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 56/76 nvme-multipath: fix possible I/O hang when paths are updated
In reply to Sasha LevinFrom: Anton Eidelman <[email protected]>
[ Upstream commit 504db087aaccdb32af61539916409f7dca31ceb5 ]
nvme_state_set_live() making a path available triggers requeue_work in order to resubmit requests that ended up on requeue_list when no paths were available.
This requeue_work may race with concurrent nvme_ns_head_make_request() that do not observe the live path yet.
Such concurrent requests may by made by either:
- New IO submission.
- Requeue_work triggered by nvme_failover_req() or another ana_work.
A race may cause requeue_work capture the state of requeue_list before more requests get onto the list. These requests will stay on the list forever unless requeue_work is triggered again.
In order to prevent such race, nvme_state_set_live() should synchronize_srcu(&head->srcu) before triggering the requeue_work and prevent nvme_ns_head_make_request referencing an old snapshot of the path list.
--- drivers/nvme/host/multipath.c | 1 + 1 file changed, 1 insertion(+)
drivers/nvme/host/multipath.c +1 -0
@@ -356,6 +356,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)srcu_read_unlock (&head->srcu, srcu_idx); } +synchronize_srcu (&ns->head->srcu);kblockd_schedule_work (&ns->head->requeue_work); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 57/76 nvme: Fix cntlid validation when not using NVMEoF
In reply to Sasha LevinFrom: "Guilherme G. Piccoli" <[email protected]>
[ Upstream commit a89fcca8185633993018dc081d6b021d005e6d0b ]
Commit 1b1031ca63b2 ("nvme: validate cntlid during controller initialisation") introduced a validation for controllers with duplicate cntlid that runs on nvme_init_subsystem(). The problem is that the validation relies on ctrl->cntlid, and this value is assigned (from id_ctrl value) after the call for nvme_init_subsystem() in nvme_init_identify() for non-fabrics scenario. That leads to ctrl->cntlid always being 0 in case we have a physical set of controllers in the same subsystem.
This patch fixes that by loading the discovered cntlid id_ctrl value into ctrl->cntlid before the subsystem initialization, only for the non-fabrics case. The patch was tested with emulated nvme devices (qemu) having two controllers in a single subsystem. Without the patch, we couldn't make it work failing in the duplicate check; when running with the patch, we could see the subsystem holding both controllers.
For the fabrics case we see ctrl->cntlid has a more intricate relation with the admin connect, so we didn't change that.
--- drivers/nvme/host/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/nvme/host/core.c +3 -1
@@ -2543,6 +2543,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) goto out_free; } +if (!(ctrl->ops->flags &NVME_F_FABRICS )) + ctrl->cntlid =le16_to_cpu (id->cntlid); +if (!ctrl->identified) {int i;
@@ -2643,7 +2646,6 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) goto out_free; } }else { - ctrl->cntlid =le16_to_cpu (id->cntlid); ctrl->hmpre =le32_to_cpu (id->hmpre); ctrl->hmmin =le32_to_cpu (id->hmmin); ctrl->hmminds =le32_to_cpu (id->hmminds);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 58/76 io_uring: don't enter poll loop if we have CQEs pending
In reply to Sasha LevinFrom: Jens Axboe <[email protected]>
[ Upstream commit a3a0e43fd77013819e4b6f55e37e0efe8e35d805 ]
We need to check if we have CQEs pending before starting a poll loop, as those could be the events we will be spinning for (and hence we'll find none). This can happen if a CQE triggers an error, or if it is found by eg an IRQ before we get a chance to find it through polling.
--- fs/io_uring.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-)
fs/io_uring.c +15 -7
@@ -618,6 +618,13 @@ static void io_put_req(struct io_kiocb *req)io_free_req (req); } +static unsigned io_cqring_events (struct io_cq_ring *ring) +{ +/* See comment at the top of this file */ +smp_rmb (); +return READ_ONCE (ring->r.tail) -READ_ONCE (ring->r.head); +} +/* * Find and free completed poll iocbs */
@@ -756,6 +763,14 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events, do { int tmin = 0; + /* + * Don't enter poll loop if we already have events pending. + * If we do, we can potentially be spinning for commands that + * already triggered a CQE (eg in error). + */ + if (io_cqring_events(ctx->cq_ring)) + break; + /* * If a submit got punted to a workqueue, we can have the * application entering polling for a command before it gets
@@ -2232,13 +2247,6 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)return submit; } -static unsigned io_cqring_events (struct io_cq_ring *ring) -{ -/* See comment at the top of this file */ -smp_rmb (); -return READ_ONCE (ring->r.tail) -READ_ONCE (ring->r.head); -} -/* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring.
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 59/76 RDMA/cma: fix null-ptr-deref Read in cma_cleanup
In reply to Sasha LevinFrom: zhengbin <[email protected]>
[ Upstream commit a7bfb93f0211b4a2f1ffeeb259ed6206bac30460 ]
In cma_init, if cma_configfs_init fails, need to free the previously memory and return fail, otherwise will trigger null-ptr-deref Read in cma_cleanup.
cma_cleanup
cma_configfs_exit
configfs_unregister_subsystem
--- drivers/infiniband/core/cma.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/infiniband/core/cma.c +5 -1
@@ -4724,10 +4724,14 @@ static int __init cma_init(void)if (ret) goto err; -cma_configfs_init (); + ret =cma_configfs_init (); +if (ret) + goto err_ib;return 0 ; +err_ib: +ib_unregister_client (&cma_client); err:unregister_netdevice_notifier (&cma_nb);ib_sa_unregister_client (&sa_client);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 60/76 IB/mlx4: Fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 5c1baaa82cea2c815a5180ded402a7cd455d1810 ]
In mlx4_ib_alloc_pv_bufs(), 'tun_qp->tx_ring' is allocated through kcalloc(). However, it is not always deallocated in the following execution if an error occurs, leading to memory leaks. To fix this issue, free 'tun_qp->tx_ring' whenever an error occurs.
--- drivers/infiniband/hw/mlx4/mad.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/infiniband/hw/mlx4/mad.c +2 -2
@@ -1677,8 +1677,6 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, tx_buf_size, DMA_TO_DEVICE);kfree (tun_qp->tx_ring[i].buf.addr); } -kfree (tun_qp->tx_ring); - tun_qp->tx_ring =NULL ; i =MLX4_NUM_TUNNEL_BUFS ; err:while (i >0 ) {
@@ -1687,6 +1685,8 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, rx_buf_size, DMA_FROM_DEVICE);kfree (tun_qp->ring[i].addr); } +kfree (tun_qp->tx_ring); + tun_qp->tx_ring =NULL ;kfree (tun_qp->ring); tun_qp->ring =NULL ;return -ENOMEM ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 61/76 infiniband: hfi1: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit b08afa064c320e5d85cdc27228426b696c4c8dae ]
In fault_opcodes_read(), 'data' is not deallocated if debugfs_file_get() fails, leading to a memory leak. To fix this bug, introduce the 'free_data' label to free 'data' before returning the error.
--- drivers/infiniband/hw/hfi1/fault.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/infiniband/hw/hfi1/fault.c +2 -1
@@ -214,7 +214,7 @@ static ssize_t fault_opcodes_read(struct file *file, char __user *buf,return -ENOMEM ; ret =debugfs_file_get (file->f_path.dentry);if (unlikely (ret)) -return ret; + goto free_data; bit =find_first_bit (fault->opcodes, bitsize);while (bit < bitsize) { zero =find_next_zero_bit (fault->opcodes, bitsize, bit);
@@ -232,6 +232,7 @@ static ssize_t fault_opcodes_read(struct file *file, char __user *buf, data[size -1 ] ='\n' ; data[size] ='\0' ; ret =simple_read_from_buffer (buf, len, pos, data, size); +free_data:kfree (data);return ret; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 62/76 infiniband: hfi1: fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 2323d7baab2b18d87d9bc267452e387aa9f0060a ]
In fault_opcodes_write(), 'data' is allocated through kcalloc(). However, it is not deallocated in the following execution if an error occurs, leading to memory leaks. To fix this issue, introduce the 'free_data' label to free 'data' before returning the error.
--- drivers/infiniband/hw/hfi1/fault.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/infiniband/hw/hfi1/fault.c +6 -3
@@ -141,12 +141,14 @@ static ssize_t fault_opcodes_write(struct file *file, const char __user *buf,if (!data)return -ENOMEM ; copy =min (len, datalen -1 ); -if (copy_from_user (data, buf, copy)) -return -EFAULT ; +if (copy_from_user (data, buf, copy)) { + ret = -EFAULT ; + goto free_data; + } ret =debugfs_file_get (file->f_path.dentry);if (unlikely (ret)) -return ret; + goto free_data; ptr = data; token = ptr;for (ptr = data; *ptr; ptr = end +1 , token = ptr) {
@@ -195,6 +197,7 @@ static ssize_t fault_opcodes_write(struct file *file, const char __user *buf, ret = len;debugfs_file_put (file->f_path.dentry); +free_data:kfree (data);return ret; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 63/76 selftests: kvm: fix state save/load on processors without XSAVE
In reply to Sasha LevinFrom: Paolo Bonzini <[email protected]>
[ Upstream commit 54577e5018a8c0cb79c9a0fa118a55c68715d398 ]
state_test and smm_test are failing on older processors that do not have xcr0. This is because on those processor KVM does provide support for KVM_GET/SET_XSAVE (to avoid having to rely on the older KVM_GET/SET_FPU) but not for KVM_GET/SET_XCRS.
--- .../testing/selftests/kvm/lib/x86_64/processor.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
tools/testing/selftests/kvm/lib/x86_64/processor.c +10 -6
@@ -1059,9 +1059,11 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)TEST_ASSERT (r ==0 ,"Unexpected result from KVM_GET_XSAVE, r: %i" , r); - r =ioctl (vcpu->fd,KVM_GET_XCRS , &state->xcrs); -TEST_ASSERT (r ==0 ,"Unexpected result from KVM_GET_XCRS, r: %i" , - r); +if (kvm_check_cap (KVM_CAP_XCRS )) { + r =ioctl (vcpu->fd,KVM_GET_XCRS , &state->xcrs); +TEST_ASSERT (r ==0 ,"Unexpected result from KVM_GET_XCRS, r: %i" , + r); + } r =ioctl (vcpu->fd,KVM_GET_SREGS , &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
@@ -1102,9 +1104,11 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *sTEST_ASSERT (r ==0 ,"Unexpected result from KVM_SET_XSAVE, r: %i" , r); - r =ioctl (vcpu->fd,KVM_SET_XCRS , &state->xcrs); -TEST_ASSERT (r ==0 ,"Unexpected result from KVM_SET_XCRS, r: %i" , - r); +if (kvm_check_cap (KVM_CAP_XCRS )) { + r =ioctl (vcpu->fd,KVM_SET_XCRS , &state->xcrs); +TEST_ASSERT (r ==0 ,"Unexpected result from KVM_SET_XCRS, r: %i" , + r); + } r =ioctl (vcpu->fd,KVM_SET_SREGS , &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 64/76 selftests/kvm: make platform_info_test pass on AMD
In reply to Sasha LevinFrom: Vitaly Kuznetsov <[email protected]>
[ Upstream commit e4427372398c31f57450565de277f861a4db5b3b ]
test_msr_platform_info_disabled() generates EXIT_SHUTDOWN but VMCB state is undefined after that so an attempt to launch this guest again from test_msr_platform_info_enabled() fails. Reorder the tests to make test pass.
--- tools/testing/selftests/kvm/x86_64/platform_info_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/kvm/x86_64/platform_info_test.c +1 -1
@@ -99,8 +99,8 @@ int main(int argc, char *argv[]) msr_platform_info =vcpu_get_msr (vm,VCPU_ID ,MSR_PLATFORM_INFO );vcpu_set_msr (vm,VCPU_ID ,MSR_PLATFORM_INFO , msr_platform_info |MSR_PLATFORM_INFO_MAX_TURBO_RATIO ); -test_msr_platform_info_disabled (vm);test_msr_platform_info_enabled (vm); +test_msr_platform_info_disabled (vm);vcpu_set_msr (vm,VCPU_ID ,MSR_PLATFORM_INFO , msr_platform_info);kvm_vm_free (vm);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 65/76 drm/amdgpu: prevent memory leaks in AMDGPU_CS ioctl
In reply to Sasha LevinFrom: Nicolai Hähnle <[email protected]>
[ Upstream commit 1a701ea924815b0518733aa8d5d05c1f6fa87062 ]
Error out if the AMDGPU_CS ioctl is called with multiple SYNCOBJ_OUT and/or TIMELINE_SIGNAL chunks, since otherwise the last chunk wins while the allocated array as well as the reference counts of sync objects are leaked.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +7 -2
@@ -1192,6 +1192,9 @@ static int amdgpu_cs_process_syncobj_out_dep(struct amdgpu_cs_parser *p, num_deps = chunk->length_dw *4 /sizeof (struct drm_amdgpu_cs_chunk_sem ); +if (p->post_deps) +return -EINVAL ; + p->post_deps =kmalloc_array (num_deps,sizeof (*p->post_deps),GFP_KERNEL ); p->num_post_deps =0 ;
@@ -1215,8 +1218,7 @@ static int amdgpu_cs_process_syncobj_out_dep(struct amdgpu_cs_parser *p,static int amdgpu_cs_process_syncobj_timeline_out_dep (struct amdgpu_cs_parser *p, -struct amdgpu_cs_chunk - *chunk) +struct amdgpu_cs_chunk *chunk) {struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;unsigned num_deps;
@@ -1226,6 +1228,9 @@ static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p num_deps = chunk->length_dw *4 /sizeof (struct drm_amdgpu_cs_chunk_syncobj ); +if (p->post_deps) +return -EINVAL ; + p->post_deps =kmalloc_array (num_deps,sizeof (*p->post_deps),GFP_KERNEL ); p->num_post_deps =0 ;
Signature · 6 lines
2.20.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Sasha Levin
maintainerPATCH 66/76 ceph: fix buffer free while holding i_ceph_lock in __ceph_setxattr()
In reply to Sasha LevinFrom: Luis Henriques <[email protected]>
[ Upstream commit 86968ef21596515958d5f0a40233d02be78ecec0 ]
Calling ceph_buffer_put() in __ceph_setxattr() may end up freeing the i_xattrs.prealloc_blob buffer while holding the i_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.
The following backtrace was triggered by fstests generic/117.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
in_atomic(): 1, irqs_disabled(): 0, pid: 650, name: fsstress
3 locks held by fsstress/650:
#0: 00000000870a0fe8 (sb_writers#8){.+.+}, at: mnt_want_write+0x20/0x50
#1: 00000000ba0c4c74 (&type->i_mutex_dir_key#6){++++}, at: vfs_setxattr+0x55/0xa0
#2: 000000008dfbb3f2 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: __ceph_setxattr+0x297/0x810
CPU: 1 PID: 650 Comm: fsstress Not tainted 5.2.0+ #437
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
Call Trace:
dump_stack+0x67/0x90
___might_sleep.cold+0x9f/0xb1
vfree+0x4b/0x60
ceph_buffer_release+0x1b/0x60
__ceph_setxattr+0x2b4/0x810
__vfs_setxattr+0x66/0x80
__vfs_setxattr_noperm+0x59/0xf0
vfs_setxattr+0x81/0xa0
setxattr+0x115/0x230
? filename_lookup+0xc9/0x140
? rcu_read_lock_sched_held+0x74/0x80
? rcu_sync_lockdep_assert+0x2e/0x60
? __sb_start_write+0x142/0x1a0
? mnt_want_write+0x20/0x50
path_setxattr+0xba/0xd0
__x64_sys_lsetxattr+0x24/0x30
do_syscall_64+0x50/0x1c0
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7ff23514359a--- fs/ceph/xattr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
fs/ceph/xattr.c +6 -2
@@ -1028,6 +1028,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_inode_info *ci =ceph_inode (inode);struct ceph_mds_client *mdsc =ceph_sb_to_client (inode->i_sb)->mdsc;struct ceph_cap_flush *prealloc_cf =NULL ; +struct ceph_buffer *old_blob =NULL ;int issued;int err;int dirty =0 ;
@@ -1101,13 +1102,15 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_buffer *blob;spin_unlock (&ci->i_ceph_lock); -dout (" preaallocating new blob size=%d\n" , required_blob_size); +ceph_buffer_put (old_blob);/* Shouldn't be required */ +dout (" pre-allocating new blob size=%d\n" , required_blob_size); blob =ceph_buffer_new (required_blob_size,GFP_NOFS );if (!blob) goto do_sync_unlocked;spin_lock (&ci->i_ceph_lock); +/* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) -ceph_buffer_put (ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; }
@@ -1123,6 +1126,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, }spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob);if (lock_snap_rwsem)up_read (&mdsc->snap_rwsem);if (dirty)
Signature · 1 line
2.20.1
Re: [PATCH AUTOSEL 5.2 66/76] ceph: fix buffer free while holding i_ceph_lock in __ceph_setxattr()
Quoted 79 lines · Sasha Levin
From: Luis Henriques <[email protected]>
[ Upstream commit
86968ef21596515958d5f0a40233d02be78ecec0]Calling
ceph_buffer_put()in__ceph_setxattr()may end up freeing the i_xattrs.prealloc_blob buffer while holding thei_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.The following backtrace was triggered by fstests generic/117.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283 in_atomic(): 1, irqs_disabled(): 0, pid: 650, name: fsstress 3 locks held by fsstress/650: #0: 00000000870a0fe8 (sb_writers#8){.+.+}, at: mnt_want_write+0x20/0x50 #1: 00000000ba0c4c74 (&type->i_mutex_dir_key#6){++++}, at: vfs_setxattr+0x55/0xa0 #2: 000000008dfbb3f2 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: __ceph_setxattr+0x297/0x810 CPU: 1 PID: 650 Comm: fsstress Not tainted 5.2.0+ #437 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x67/0x90 ___might_sleep.cold+0x9f/0xb1 vfree+0x4b/0x60 ceph_buffer_release+0x1b/0x60 __ceph_setxattr+0x2b4/0x810 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x59/0xf0 vfs_setxattr+0x81/0xa0 setxattr+0x115/0x230 ? filename_lookup+0xc9/0x140 ? rcu_read_lock_sched_held+0x74/0x80 ? rcu_sync_lockdep_assert+0x2e/0x60 ? __sb_start_write+0x142/0x1a0 ? mnt_want_write+0x20/0x50 path_setxattr+0xba/0xd0 __x64_sys_lsetxattr+0x24/0x30 do_syscall_64+0x50/0x1c0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7ff23514359aSigned-off-by Luis Henriques <[email protected]>Reviewed-by Jeff Layton <[email protected]>Signed-off-by Ilya Dryomov <[email protected]>Signed-off-by Sasha Levin <[email protected]>--- fs/ceph/xattr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)fs/ceph/xattr.c +5
-2@@ -1028,6 +1028,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_inode_info *ci =ceph_inode (inode);struct ceph_mds_client *mdsc =ceph_sb_to_client (inode->i_sb)->mdsc;struct ceph_cap_flush *prealloc_cf =NULL ; +struct ceph_buffer *old_blob =NULL ;int issued;int err;int dirty =0 ;@@ -1101,13 +1102,15 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_buffer *blob;spin_unlock (&ci->i_ceph_lock); -dout (" preaallocating new blob size=%d\n" , required_blob_size); +ceph_buffer_put (old_blob);/* Shouldn't be required */ +dout (" pre-allocating new blob size=%d\n" , required_blob_size); blob =ceph_buffer_new (required_blob_size,GFP_NOFS );if (!blob) goto do_sync_unlocked;spin_lock (&ci->i_ceph_lock); +/* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) -ceph_buffer_put (ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; }
fs/ceph/xattr.c int __ceph_setxattr(struct inode *inode, const char *name, · line 1132
Quoted 7 lines
fs/ceph/xattr.c +1
-0@@ -1123,6 +1126,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, }spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob);if (lock_snap_rwsem)up_read (&mdsc->snap_rwsem);if (dirty)
Hi Sasha,
I didn't tag i_ceph_lock series for stable because this is a very old bug which no one ever hit in real life, at least to my knowledge.
Please note that each of these patches requires 5c498950f730 ("libceph:
allow ceph_buffer_put() to receive a NULL ceph_buffer").
Thanks,
Ilya
Sasha Levin
maintainerRe: [PATCH AUTOSEL 5.2 66/76] ceph: fix buffer free while holding i_ceph_lock in __ceph_setxattr()
Quoted 90 lines · Ilya Dryomov
Quoted 79 lines · Sasha Levin
From: Luis Henriques <[email protected]>
[ Upstream commit
86968ef21596515958d5f0a40233d02be78ecec0]Calling
ceph_buffer_put()in__ceph_setxattr()may end up freeing the i_xattrs.prealloc_blob buffer while holding thei_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.The following backtrace was triggered by fstests generic/117.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283 in_atomic(): 1, irqs_disabled(): 0, pid: 650, name: fsstress 3 locks held by fsstress/650: #0: 00000000870a0fe8 (sb_writers#8){.+.+}, at: mnt_want_write+0x20/0x50 #1: 00000000ba0c4c74 (&type->i_mutex_dir_key#6){++++}, at: vfs_setxattr+0x55/0xa0 #2: 000000008dfbb3f2 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: __ceph_setxattr+0x297/0x810 CPU: 1 PID: 650 Comm: fsstress Not tainted 5.2.0+ #437 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x67/0x90 ___might_sleep.cold+0x9f/0xb1 vfree+0x4b/0x60 ceph_buffer_release+0x1b/0x60 __ceph_setxattr+0x2b4/0x810 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x59/0xf0 vfs_setxattr+0x81/0xa0 setxattr+0x115/0x230 ? filename_lookup+0xc9/0x140 ? rcu_read_lock_sched_held+0x74/0x80 ? rcu_sync_lockdep_assert+0x2e/0x60 ? __sb_start_write+0x142/0x1a0 ? mnt_want_write+0x20/0x50 path_setxattr+0xba/0xd0 __x64_sys_lsetxattr+0x24/0x30 do_syscall_64+0x50/0x1c0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7ff23514359aSigned-off-by Luis Henriques <[email protected]>Reviewed-by Jeff Layton <[email protected]>Signed-off-by Ilya Dryomov <[email protected]>Signed-off-by Sasha Levin <[email protected]>--- fs/ceph/xattr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)fs/ceph/xattr.c +5
-2@@ -1028,6 +1028,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_inode_info *ci =ceph_inode (inode);struct ceph_mds_client *mdsc =ceph_sb_to_client (inode->i_sb)->mdsc;struct ceph_cap_flush *prealloc_cf =NULL ; +struct ceph_buffer *old_blob =NULL ;int issued;int err;int dirty =0 ;@@ -1101,13 +1102,15 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_buffer *blob;spin_unlock (&ci->i_ceph_lock); -dout (" preaallocating new blob size=%d\n" , required_blob_size); +ceph_buffer_put (old_blob);/* Shouldn't be required */ +dout (" pre-allocating new blob size=%d\n" , required_blob_size); blob =ceph_buffer_new (required_blob_size,GFP_NOFS );if (!blob) goto do_sync_unlocked;spin_lock (&ci->i_ceph_lock); +/* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) -ceph_buffer_put (ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; }fs/ceph/xattr.c int __ceph_setxattr(struct inode *inode, const char *name, · line 1132
Quoted 7 lines
fs/ceph/xattr.c +1
-0@@ -1123,6 +1126,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, }spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob);if (lock_snap_rwsem)up_read (&mdsc->snap_rwsem);if (dirty)Hi Sasha,
Quoted 2 lines
I didn't tag
i_ceph_lockseries for stable because this is a very old bug which no one ever hit in real life, at least to my knowledge.
I can drop it if you prefer.
Re: [PATCH AUTOSEL 5.2 66/76] ceph: fix buffer free while holding i_ceph_lock in __ceph_setxattr()
Quoted 92 lines · Sasha Levin
Quoted 90 lines · Ilya Dryomov
Quoted 79 lines · Sasha Levin
From: Luis Henriques <[email protected]>
[ Upstream commit
86968ef21596515958d5f0a40233d02be78ecec0]Calling
ceph_buffer_put()in__ceph_setxattr()may end up freeing the i_xattrs.prealloc_blob buffer while holding thei_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.The following backtrace was triggered by fstests generic/117.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283 in_atomic(): 1, irqs_disabled(): 0, pid: 650, name: fsstress 3 locks held by fsstress/650: #0: 00000000870a0fe8 (sb_writers#8){.+.+}, at: mnt_want_write+0x20/0x50 #1: 00000000ba0c4c74 (&type->i_mutex_dir_key#6){++++}, at: vfs_setxattr+0x55/0xa0 #2: 000000008dfbb3f2 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: __ceph_setxattr+0x297/0x810 CPU: 1 PID: 650 Comm: fsstress Not tainted 5.2.0+ #437 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x67/0x90 ___might_sleep.cold+0x9f/0xb1 vfree+0x4b/0x60 ceph_buffer_release+0x1b/0x60 __ceph_setxattr+0x2b4/0x810 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x59/0xf0 vfs_setxattr+0x81/0xa0 setxattr+0x115/0x230 ? filename_lookup+0xc9/0x140 ? rcu_read_lock_sched_held+0x74/0x80 ? rcu_sync_lockdep_assert+0x2e/0x60 ? __sb_start_write+0x142/0x1a0 ? mnt_want_write+0x20/0x50 path_setxattr+0xba/0xd0 __x64_sys_lsetxattr+0x24/0x30 do_syscall_64+0x50/0x1c0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7ff23514359aSigned-off-by Luis Henriques <[email protected]>Reviewed-by Jeff Layton <[email protected]>Signed-off-by Ilya Dryomov <[email protected]>Signed-off-by Sasha Levin <[email protected]>--- fs/ceph/xattr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)fs/ceph/xattr.c +5
-2@@ -1028,6 +1028,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_inode_info *ci =ceph_inode (inode);struct ceph_mds_client *mdsc =ceph_sb_to_client (inode->i_sb)->mdsc;struct ceph_cap_flush *prealloc_cf =NULL ; +struct ceph_buffer *old_blob =NULL ;int issued;int err;int dirty =0 ;@@ -1101,13 +1102,15 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_buffer *blob;spin_unlock (&ci->i_ceph_lock); -dout (" preaallocating new blob size=%d\n" , required_blob_size); +ceph_buffer_put (old_blob);/* Shouldn't be required */ +dout (" pre-allocating new blob size=%d\n" , required_blob_size); blob =ceph_buffer_new (required_blob_size,GFP_NOFS );if (!blob) goto do_sync_unlocked;spin_lock (&ci->i_ceph_lock); +/* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) -ceph_buffer_put (ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; }fs/ceph/xattr.c int __ceph_setxattr(struct inode *inode, const char *name, · line 1132
Quoted 7 lines
fs/ceph/xattr.c +1
-0@@ -1123,6 +1126,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, }spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob);if (lock_snap_rwsem)up_read (&mdsc->snap_rwsem);if (dirty)Hi Sasha,
Quoted 4 lines
Quoted 2 lines
I didn't tag
i_ceph_lockseries for stable because this is a very old bug which no one ever hit in real life, at least to my knowledge.I can drop it if you prefer.
Either is fine with me. I just wanted to explain my rationale for not tagging them for stable in the first place and point out that there is a prerequisite.
Thanks,
Ilya
Sasha Levin
maintainerPATCH 67/76 ceph: fix buffer free while holding i_ceph_lock in __ceph_build_xattrs_blob()
In reply to Sasha LevinFrom: Luis Henriques <[email protected]>
[ Upstream commit 12fe3dda7ed89c95cc0ef7abc001ad1ad3e092f8 ]
Calling ceph_buffer_put() in __ceph_build_xattrs_blob() may result in freeing the i_xattrs.blob buffer while holding the i_ceph_lock. This can be fixed by having this function returning the old blob buffer and have the callers of this function freeing it when the lock is released.
The following backtrace was triggered by fstests generic/117.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
in_atomic(): 1, irqs_disabled(): 0, pid: 649, name: fsstress
4 locks held by fsstress/649:
#0: 00000000a7478e7e (&type->s_umount_key#19){++++}, at: iterate_supers+0x77/0xf0
#1: 00000000f8de1423 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: ceph_check_caps+0x7b/0xc60
#2: 00000000562f2b27 (&s->s_mutex){+.+.}, at: ceph_check_caps+0x3bd/0xc60
#3: 00000000f83ce16a (&mdsc->snap_rwsem){++++}, at: ceph_check_caps+0x3ed/0xc60
CPU: 1 PID: 649 Comm: fsstress Not tainted 5.2.0+ #439
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
Call Trace:
dump_stack+0x67/0x90
___might_sleep.cold+0x9f/0xb1
vfree+0x4b/0x60
ceph_buffer_release+0x1b/0x60
__ceph_build_xattrs_blob+0x12b/0x170
__send_cap+0x302/0x540
? __lock_acquire+0x23c/0x1e40
? __mark_caps_flushing+0x15c/0x280
? _raw_spin_unlock+0x24/0x30
ceph_check_caps+0x5f0/0xc60
ceph_flush_dirty_caps+0x7c/0x150
? __ia32_sys_fdatasync+0x20/0x20
ceph_sync_fs+0x5a/0x130
iterate_supers+0x8f/0xf0
ksys_sync+0x4f/0xb0
__ia32_sys_sync+0xa/0x10
do_syscall_64+0x50/0x1c0
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7fc6409ab617--- fs/ceph/caps.c | 5 ++++- fs/ceph/snap.c | 4 +++- fs/ceph/super.h | 2 +- fs/ceph/xattr.c | 11 ++++++++--- 4 files changed, 16 insertions(+), 6 deletions(-)
fs/ceph/caps.c +4 -1
@@ -1305,6 +1305,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, {struct ceph_inode_info *ci = cap->ci;struct inode *inode = &ci->vfs_inode; +struct ceph_buffer *old_blob =NULL ;struct cap_msg_args arg;int held, revoking;int wake =0 ;
@@ -1369,7 +1370,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, ci->i_requested_max_size = arg.max_size;if (flushing &CEPH_CAP_XATTR_EXCL ) { -__ceph_build_xattrs_blob (ci); + old_blob =__ceph_build_xattrs_blob (ci); arg.xattr_version = ci->i_xattrs.version; arg.xattr_buf = ci->i_xattrs.blob; }else {
@@ -1404,6 +1405,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob); + ret =send_cap_msg (&arg);if (ret <0 ) {dout ("error sending cap msg, must requeue %p\n" , inode);
fs/ceph/snap.c +3 -1
@@ -464,6 +464,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)struct inode *inode = &ci->vfs_inode;struct ceph_cap_snap *capsnap;struct ceph_snap_context *old_snapc, *new_snapc; +struct ceph_buffer *old_blob =NULL ;int used, dirty; capsnap =kzalloc (sizeof (*capsnap),GFP_NOFS );
@@ -540,7 +541,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) capsnap->gid = inode->i_gid;if (dirty &CEPH_CAP_XATTR_EXCL ) { -__ceph_build_xattrs_blob (ci); + old_blob =__ceph_build_xattrs_blob (ci); capsnap->xattr_blob =ceph_buffer_get (ci->i_xattrs.blob); capsnap->xattr_version = ci->i_xattrs.version;
@@ -583,6 +584,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) }spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob);kfree (capsnap);ceph_put_snap_context (old_snapc); }
fs/ceph/super.h +1 -1
@@ -924,7 +924,7 @@ extern int ceph_getattr(const struct path *path, struct kstat *stat,int __ceph_setxattr (struct inode *,const char *,const void *,size_t ,int );ssize_t __ceph_getxattr (struct inode *,const char *,void *,size_t );extern ssize_t ceph_listxattr (struct dentry *,char *,size_t ); -extern void __ceph_build_xattrs_blob (struct ceph_inode_info *ci); +extern struct ceph_buffer *__ceph_build_xattrs_blob (struct ceph_inode_info *ci);extern void __ceph_destroy_xattrs (struct ceph_inode_info *ci);extern void __init ceph_xattr_init (void );extern void ceph_xattr_exit (void );
fs/ceph/xattr.c +8 -3
@@ -752,12 +752,15 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,/* * If there are dirty xattrs, reencode xattrs into the prealloc_blob -* and swap into place. +* and swap into place. It returns the old i_xattrs.blob (or NULL) so +* that it can be freed by the caller as the i_ceph_lock is likely to be +* held. */ -void __ceph_build_xattrs_blob (struct ceph_inode_info *ci) +struct ceph_buffer *__ceph_build_xattrs_blob (struct ceph_inode_info *ci) {struct rb_node *p;struct ceph_inode_xattr *xattr =NULL ; +struct ceph_buffer *old_blob =NULL ;void *dest;dout ("__build_xattrs_blob %p\n" , &ci->vfs_inode);
@@ -788,12 +791,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci) dest - ci->i_xattrs.prealloc_blob->vec.iov_base;if (ci->i_xattrs.blob) -ceph_buffer_put (ci->i_xattrs.blob); + old_blob = ci->i_xattrs.blob; ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob =NULL ; ci->i_xattrs.dirty = false; ci->i_xattrs.version++; } + +return old_blob; }static inline int __get_request_mask (struct inode *in) {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 68/76 ceph: fix buffer free while holding i_ceph_lock in fill_inode()
In reply to Sasha LevinFrom: Luis Henriques <[email protected]>
[ Upstream commit af8a85a41734f37b67ba8ce69d56b685bee4ac48 ]
Calling ceph_buffer_put() in fill_inode() may result in freeing the i_xattrs.blob buffer while holding the i_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.
The following backtrace was triggered by fstests generic/070.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
in_atomic(): 1, irqs_disabled(): 0, pid: 3852, name: kworker/0:4
6 locks held by kworker/0:4/3852:
#0: 000000004270f6bb ((wq_completion)ceph-msgr){+.+.}, at: process_one_work+0x1b8/0x5f0
#1: 00000000eb420803 ((work_completion)(&(&con->work)->work)){+.+.}, at: process_one_work+0x1b8/0x5f0
#2: 00000000be1c53a4 (&s->s_mutex){+.+.}, at: dispatch+0x288/0x1476
#3: 00000000559cb958 (&mdsc->snap_rwsem){++++}, at: dispatch+0x2eb/0x1476
#4: 000000000d5ebbae (&req->r_fill_mutex){+.+.}, at: dispatch+0x2fc/0x1476
#5: 00000000a83d0514 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: fill_inode.isra.0+0xf8/0xf70
CPU: 0 PID: 3852 Comm: kworker/0:4 Not tainted 5.2.0+ #441
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
Workqueue: ceph-msgr ceph_con_workfn
Call Trace:
dump_stack+0x67/0x90
___might_sleep.cold+0x9f/0xb1
vfree+0x4b/0x60
ceph_buffer_release+0x1b/0x60
fill_inode.isra.0+0xa9b/0xf70
ceph_fill_trace+0x13b/0xc70
? dispatch+0x2eb/0x1476
dispatch+0x320/0x1476
? __mutex_unlock_slowpath+0x4d/0x2a0
ceph_con_workfn+0xc97/0x2ec0
? process_one_work+0x1b8/0x5f0
process_one_work+0x244/0x5f0
worker_thread+0x4d/0x3e0
kthread+0x105/0x140
? process_one_work+0x5f0/0x5f0
? kthread_park+0x90/0x90
ret_from_fork+0x3a/0x50--- fs/ceph/inode.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
fs/ceph/inode.c +4 -3
@@ -743,6 +743,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,int issued, new_issued, info_caps;struct timespec64 mtime, atime, ctime;struct ceph_buffer *xattr_blob =NULL ; +struct ceph_buffer *old_blob =NULL ;struct ceph_string *pool_ns =NULL ;struct ceph_cap *new_cap =NULL ;int err =0 ;
@@ -883,7 +884,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,if ((ci->i_xattrs.version ==0 || !(issued &CEPH_CAP_XATTR_EXCL )) &&le64_to_cpu (info->xattr_version) > ci->i_xattrs.version) {if (ci->i_xattrs.blob) -ceph_buffer_put (ci->i_xattrs.blob); + old_blob = ci->i_xattrs.blob; ci->i_xattrs.blob = xattr_blob;if (xattr_blob) memcpy(ci->i_xattrs.blob->vec.iov_base,
@@ -1023,8 +1024,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page, out:if (new_cap)ceph_put_cap (mdsc, new_cap); -if (xattr_blob) -ceph_buffer_put (xattr_blob); +ceph_buffer_put (old_blob); +ceph_buffer_put (xattr_blob);ceph_put_string (pool_ns);return err; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 69/76 KVM: arm/arm64: Only skip MMIO insn once
In reply to Sasha LevinFrom: Andrew Jones <[email protected]>
[ Upstream commit 2113c5f62b7423e4a72b890bd479704aa85c81ba ]
If after an MMIO exit to userspace a VCPU is immediately run with an immediate_exit request, such as when a signal is delivered or an MMIO emulation completion is needed, then the VCPU completes the MMIO emulation and immediately returns to userspace. As the exit_reason does not get changed from KVM_EXIT_MMIO in these cases we have to be careful not to complete the MMIO emulation again, when the VCPU is eventually run again, because the emulation does an instruction skip (and doing too many skips would be a waste of guest code :-) We need to use additional VCPU state to track if the emulation is complete. As luck would have it, we already have 'mmio_needed', which even appears to be used in this way by other architectures already.
--- virt/kvm/arm/mmio.c | 7 +++++++ 1 file changed, 7 insertions(+)
virt/kvm/arm/mmio.c +7 -0
@@ -86,6 +86,12 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)unsigned int len;int mask; +/* Detect an already handled MMIO return */ +if (unlikely (!vcpu->mmio_needed)) +return 0 ; + + vcpu->mmio_needed =0 ; +if (!run->mmio.is_write) { len = run->mmio.len;if (len >sizeof (unsigned long ))
@@ -188,6 +194,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, run->mmio.is_write = is_write; run->mmio.phys_addr = fault_ipa; run->mmio.len = len; + vcpu->mmio_needed =1 ;if (!ret) {/* We handled the access successfully in the kernel. */
Signature · 6 lines
2.20.1 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
Sasha Levin
maintainerPATCH 70/76 afs: Fix leak in afs_lookup_cell_rcu()
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit a5fb8e6c02d6a518fb2b1a2b8c2471fa77b69436 ]
Fix a leak on the cell refcount in afs_lookup_cell_rcu() due to non-clearance of the default error in the case a NULL cell name is passed and the workstation default cell is used.
Also put a bit at the end to make sure we don't leak a cell ref if we're going to be returning an error.
This leak results in an assertion like the following when the kafs module is unloaded:
AFS: Assertion failed 2 == 1 is false 0x2 == 0x1 is false ------------[ cut here ]------------ kernel BUG at fs/afs/cell.c:770! ... RIP: 0010:afs_manage_cells+0x220/0x42f [kafs] ... process_one_work+0x4c2/0x82c ? pool_mayday_timeout+0x1e1/0x1e1 ? do_raw_spin_lock+0x134/0x175 worker_thread+0x336/0x4a6 ? rescuer_thread+0x4af/0x4af kthread+0x1de/0x1ee ? kthread_park+0xd4/0xd4 ret_from_fork+0x24/0x30
--- fs/afs/cell.c | 4 ++++ 1 file changed, 4 insertions(+)
fs/afs/cell.c +4 -0
@@ -74,6 +74,7 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net, cell =rcu_dereference_raw (net->ws_cell);if (cell) {afs_get_cell (cell); + ret =0 ;break ; } ret = -EDESTADDRREQ ;
@@ -108,6 +109,9 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,done_seqretry (&net->cells_lock, seq); +if (ret !=0 && cell) +afs_put_cell (net, cell); +return ret ==0 ? cell :ERR_PTR (ret); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 71/76 afs: Fix possible oops in afs_lookup trace event
In reply to Sasha LevinFrom: Marc Dionne <[email protected]>
[ Upstream commit c4c613ff08d92e72bf64a65ec35a2c3aa1cfcd06 ]
The afs_lookup trace event can cause the following:
[ 216.576777] BUG: kernel NULL pointer dereference, address: 000000000000023b [ 216.576803] #PF: supervisor read access in kernel mode [ 216.576813] #PF: error_code(0x0000) - not-present page ... [ 216.576913] RIP: 0010:trace_event_raw_event_afs_lookup+0x9e/0x1c0 [kafs]
If the inode from afs_do_lookup() is an error other than ENOENT, or if it is ENOENT and afs_try_auto_mntpt() returns an error, the trace event will try to dereference the error pointer as a valid pointer.
Use IS_ERR_OR_NULL to only pass a valid pointer for the trace, or NULL.
Ideally the trace would include the error value, but for now just avoid the oops.
--- fs/afs/dir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
fs/afs/dir.c +2 -1
@@ -952,7 +952,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, inode ? AFS_FS_I(inode) : NULL); }else {trace_afs_lookup (dvnode, &dentry->d_name, - inode ?AFS_FS_I (inode) :NULL ); +IS_ERR_OR_NULL (inode) ?NULL + :AFS_FS_I (inode)); }return d; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 72/76 afs: use correct afs_call_type in yfs_fs_store_opaque_acl2
In reply to Sasha LevinFrom: YueHaibing <[email protected]>
[ Upstream commit 7533be858f5b9a036b9f91556a3ed70786abca8e ]
It seems that 'yfs_RXYFSStoreOpaqueACL2' should be use in yfs_fs_store_opaque_acl2().
--- fs/afs/yfsclient.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/afs/yfsclient.c +1 -1
@@ -2155,7 +2155,7 @@ int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); size =round_up (acl->size,4 ); - call = afs_alloc_flat_call(net, &yfs_RXYFSStoreStatus, + call = afs_alloc_flat_call(net, &yfs_RXYFSStoreOpaqueACL2, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFid) + sizeof(__be32) + size,
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 73/76 RDMA/bnxt_re: Fix stack-out-of-bounds in bnxt_qplib_rcfw_send_message
In reply to Sasha LevinFrom: Selvin Xavier <[email protected]>
[ Upstream commit d37b1e534071ab1983e7c85273234b132c77591a ]
Driver copies FW commands to the HW queue as units of 16 bytes. Some of the command structures are not exact multiple of 16. So while copying the data from those structures, the stack out of bounds messages are reported by KASAN. The following error is reported.
[ 1337.530155] ================================================================== [ 1337.530277] BUG: KASAN: stack-out-of-bounds in bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re] [ 1337.530413] Read of size 16 at addr ffff888725477a48 by task rmmod/2785
[ 1337.530540] CPU: 5 PID: 2785 Comm: rmmod Tainted: G OE 5.2.0-rc6+ #75 [ 1337.530541] Hardware name: Dell Inc. PowerEdge R730/0599V5, BIOS 1.0.4 08/28/2014 [ 1337.530542] Call Trace: [ 1337.530548] dump_stack+0x5b/0x90 [ 1337.530556] ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re] [ 1337.530560] print_address_description+0x65/0x22e [ 1337.530568] ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re] [ 1337.530575] ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re] [ 1337.530577] __kasan_report.cold.3+0x37/0x77 [ 1337.530581] ? _raw_write_trylock+0x10/0xe0 [ 1337.530588] ? bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re] [ 1337.530590] kasan_report+0xe/0x20 [ 1337.530592] memcpy+0x1f/0x50 [ 1337.530600] bnxt_qplib_rcfw_send_message+0x40a/0x850 [bnxt_re] [ 1337.530608] ? bnxt_qplib_creq_irq+0xa0/0xa0 [bnxt_re] [ 1337.530611] ? xas_create+0x3aa/0x5f0 [ 1337.530613] ? xas_start+0x77/0x110 [ 1337.530615] ? xas_clear_mark+0x34/0xd0 [ 1337.530623] bnxt_qplib_free_mrw+0x104/0x1a0 [bnxt_re] [ 1337.530631] ? bnxt_qplib_destroy_ah+0x110/0x110 [bnxt_re] [ 1337.530633] ? bit_wait_io_timeout+0xc0/0xc0 [ 1337.530641] bnxt_re_dealloc_mw+0x2c/0x60 [bnxt_re] [ 1337.530648] bnxt_re_destroy_fence_mr+0x77/0x1d0 [bnxt_re] [ 1337.530655] bnxt_re_dealloc_pd+0x25/0x60 [bnxt_re] [ 1337.530677] ib_dealloc_pd_user+0xbe/0xe0 [ib_core] [ 1337.530683] srpt_remove_one+0x5de/0x690 [ib_srpt] [ 1337.530689] ? __srpt_close_all_ch+0xc0/0xc0 [ib_srpt] [ 1337.530692] ? xa_load+0x87/0xe0 ... [ 1337.530840] do_syscall_64+0x6d/0x1f0 [ 1337.530843] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1337.530845] RIP: 0033:0x7ff5b389035b [ 1337.530848] Code: 73 01 c3 48 8b 0d 2d 0b 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d fd 0a 2c 00 f7 d8 64 89 01 48 [ 1337.530849] RSP: 002b:00007fff83425c28 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [ 1337.530852] RAX: ffffffffffffffda RBX: 00005596443e6750 RCX: 00007ff5b389035b [ 1337.530853] RDX: 000000000000000a RSI: 0000000000000800 RDI: 00005596443e67b8 [ 1337.530854] RBP: 0000000000000000 R08: 00007fff83424ba1 R09: 0000000000000000 [ 1337.530856] R10: 00007ff5b3902960 R11: 0000000000000206 R12: 00007fff83425e50 [ 1337.530857] R13: 00007fff8342673c R14: 00005596443e6260 R15: 00005596443e6750
[ 1337.530885] The buggy address belongs to the page: [ 1337.530962] page:ffffea001c951dc0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 1337.530964] flags: 0x57ffffc0000000() [ 1337.530967] raw: 0057ffffc0000000 0000000000000000 ffffffff1c950101 0000000000000000 [ 1337.530970] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 [ 1337.530970] page dumped because: kasan: bad access detected
[ 1337.530996] Memory state around the buggy address: [ 1337.531072] ffff888725477900: 00 00 00 00 f1 f1 f1 f1 00 00 00 00 00 f2 f2 f2 [ 1337.531180] ffff888725477980: 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 [ 1337.531288] >ffff888725477a00: 00 f2 f2 f2 f2 f2 f2 00 00 00 f2 00 00 00 00 00 [ 1337.531393] ^ [ 1337.531478] ffff888725477a80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 1337.531585] ffff888725477b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 1337.531691] ==================================================================
Fix this by passing the exact size of each FW command to bnxt_qplib_rcfw_send_message as req->cmd_size. Before sending the command to HW, modify the req->cmd_size to number of 16 byte units.
--- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 8 +++++++- drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 11 ++++++++--- 2 files changed, 15 insertions(+), 4 deletions(-)
drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +7 -1
@@ -136,6 +136,13 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req,spin_unlock_irqrestore (&cmdq->lock, flags);return -EBUSY ; } + + size = req->cmd_size; +/* change the cmd_size to the number of 16byte cmdq unit. +* req->cmd_size is modified here +*/ +bnxt_qplib_set_cmd_slots (req); +memset (resp,0 ,sizeof (*resp)); crsqe->resp = (struct creq_qp_event *)resp; crsqe->resp->cookie = req->cookie;
@@ -150,7 +157,6 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, cmdq_ptr = (struct bnxt_qplib_cmdqe **)cmdq->pbl_ptr; preq = (u8 *)req; - size = req->cmd_size *BNXT_QPLIB_CMDQE_UNITS ; do { /* Locate the next cmdq slot */ sw_prod = HWQ_CMP(cmdq->prod, cmdq);
drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +8 -3
@@ -55,9 +55,7 @@do { \memset (&(req),0 ,sizeof ((req))); \ (req).opcode = CMDQ_BASE_OPCODE_##CMD; \ - (req).cmd_size = (sizeof ((req)) + \ -BNXT_QPLIB_CMDQE_UNITS -1 ) / \ -BNXT_QPLIB_CMDQE_UNITS ; \ + (req).cmd_size =sizeof ((req)); \ (req).flags =cpu_to_le16 (cmd_flags); \ }while (0 )
@@ -95,6 +93,13 @@ static inline u32 bnxt_qplib_cmdqe_cnt_per_pg(u32 depth) BNXT_QPLIB_CMDQE_UNITS); } +/* Set the cmd_size to a factor of CMDQE unit */ +static inline void bnxt_qplib_set_cmd_slots (struct cmdq_base *req) +{ + req->cmd_size = (req->cmd_size +BNXT_QPLIB_CMDQE_UNITS -1 ) / +BNXT_QPLIB_CMDQE_UNITS ; +} +#define MAX_CMDQ_IDX (depth) ((depth) - 1)static inline u32 bnxt_qplib_max_cmdq_idx_per_pg (u32 depth)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 74/76 io_uring: add need_resched() check in inner poll loop
In reply to Sasha LevinFrom: Jens Axboe <[email protected]>
[ Upstream commit 08f5439f1df25a6cf6cf4c72cf6c13025599ce67 ]
The outer poll loop checks for whether we need to reschedule, and returns to userspace if we do. However, it's possible to get stuck in the inner loop as well, if the CPU we are running on needs to reschedule to finish the IO work.
Add the need_resched() check in the inner loop as well. This fixes a potential hang if the kernel is configured with CONFIG_PREEMPT_VOLUNTARY=y.
--- fs/io_uring.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
fs/io_uring.c +7 -1
@@ -716,7 +716,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,static int io_iopoll_getevents (struct io_ring_ctx *ctx,unsigned int *nr_events,long min) { -while (!list_empty (&ctx->poll_list)) { +while (!list_empty (&ctx->poll_list) && !need_resched ()) {int ret; ret =io_do_iopoll (ctx, nr_events, min);
@@ -743,6 +743,12 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)unsigned int nr_events =0 ;io_iopoll_getevents (ctx, &nr_events,1 ); + +/* +* Ensure we allow local-to-the-cpu processing to take place, +* in this case we need to ensure that we reap all events. +*/ +cond_resched (); }mutex_unlock (&ctx->uring_lock); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 75/76 gpio: Fix irqchip initialization order
In reply to Sasha LevinFrom: Linus Walleij <[email protected]>
[ Upstream commit 48057ed1840fde9239b1e000bea1a0a1f07c5e99 ]
The new API for registering a gpio_irq_chip along with a gpio_chip has a different semantic ordering than the old API which added the irqchip explicitly after registering the gpio_chip.
Move the calls to add the gpio_irq_chip *last* in the function, so that the different hooks setting up OF and ACPI and machine gpio_chips are called *before* we try to register the interrupts, preserving the elder semantic order.
This cropped up in the PL061 driver which used to work fine with no special ACPI quirks, but started to misbehave using the new API.
--- drivers/gpio/gpiolib.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-)
drivers/gpio/gpiolib.c +15 -15
@@ -1371,21 +1371,13 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,if (status) goto err_remove_from_list; - status =gpiochip_irqchip_init_valid_mask (chip); -if (status) - goto err_remove_from_list; - status =gpiochip_alloc_valid_mask (chip);if (status) - goto err_remove_irqchip_mask; - - status =gpiochip_add_irqchip (chip, lock_key, request_key); -if (status) - goto err_free_gpiochip_mask; + goto err_remove_from_list; status =of_gpiochip_add (chip);if (status) - goto err_remove_chip; + goto err_free_gpiochip_mask; status =gpiochip_init_valid_mask (chip);if (status)
@@ -1411,6 +1403,14 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,machine_gpiochip_add (chip); + status =gpiochip_irqchip_init_valid_mask (chip); +if (status) + goto err_remove_acpi_chip; + + status =gpiochip_add_irqchip (chip, lock_key, request_key); +if (status) + goto err_remove_irqchip_mask; +/* * By first adding the chardev, and then adding the device, * we get a device node entry in sysfs under
@@ -1422,21 +1422,21 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,if (gpiolib_initialized) { status =gpiochip_setup_dev (gdev);if (status) - goto err_remove_acpi_chip; + goto err_remove_irqchip; }return 0 ; +err_remove_irqchip: +gpiochip_irqchip_remove (chip); +err_remove_irqchip_mask: +gpiochip_irqchip_free_valid_mask (chip); err_remove_acpi_chip:acpi_gpiochip_remove (chip); err_remove_of_chip:gpiochip_free_hogs (chip);of_gpiochip_remove (chip); -err_remove_chip: -gpiochip_irqchip_remove (chip); err_free_gpiochip_mask:gpiochip_free_valid_mask (chip); -err_remove_irqchip_mask: -gpiochip_irqchip_free_valid_mask (chip); err_remove_from_list:spin_lock_irqsave (&gpio_lock, flags);list_del (&gdev->list);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 76/76 KVM: arm/arm64: VGIC: Properly initialise private IRQ affinity
In reply to Sasha LevinFrom: Andre Przywara <[email protected]>
[ Upstream commit 2e16f3e926ed48373c98edea85c6ad0ef69425d1 ]
At the moment we initialise the target *mask* of a virtual IRQ to the VCPU it belongs to, even though this mask is only defined for GICv2 and quickly runs out of bits for many GICv3 guests.
This behaviour triggers an UBSAN complaint for more than 32 VCPUs:
------
[ 5659.462377] UBSAN: Undefined behaviour in virt/kvm/arm/vgic/vgic-init.c:223:21 [ 5659.471689] shift exponent 32 is too large for 32-bit type 'unsigned int'
------
Also for GICv3 guests the reporting of TARGET in the "vgic-state" debugfs dump is wrong, due to this very same problem.
Because there is no requirement to create the VGIC device before the VCPUs (and QEMU actually does it the other way round), we can't safely initialise mpidr or targets in kvm_vgic_vcpu_init(). But since we touch every private IRQ for each VCPU anyway later (in vgic_init()), we can just move the initialisation of those fields into there, where we definitely know the VGIC type.
On the way make sure we really have either a VGICv2 or a VGICv3 device, since the existing code is just checking for "VGICv3 or not", silently ignoring the uninitialised case.
--- virt/kvm/arm/vgic/vgic-init.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-)
virt/kvm/arm/vgic/vgic-init.c +20 -10
@@ -8,6 +8,7 @@#include <linux/cpu.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include "vgic.h"
@@ -164,12 +165,18 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) irq->vcpu =NULL ; irq->target_vcpu = vcpu0;kref_init (&irq->refcount); -if (dist->vgic_model ==KVM_DEV_TYPE_ARM_VGIC_V2 ) { +switch (dist->vgic_model) { +case KVM_DEV_TYPE_ARM_VGIC_V2 : irq->targets =0 ; irq->group =0 ; - }else { +break ; +case KVM_DEV_TYPE_ARM_VGIC_V3 : irq->mpidr =0 ; irq->group =1 ; +break ; +default : +kfree (dist->spis); +return -EINVAL ; } }return 0 ;
@@ -209,7 +216,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) irq->intid = i; irq->vcpu =NULL ; irq->target_vcpu = vcpu; - irq->targets =1U << vcpu->vcpu_id;kref_init (&irq->refcount);if (vgic_irq_is_sgi (i)) {/* SGIs */
@@ -219,11 +225,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)/* PPIs */ irq->config =VGIC_CONFIG_LEVEL ; } - -if (dist->vgic_model ==KVM_DEV_TYPE_ARM_VGIC_V3 ) - irq->group =1 ; -else - irq->group =0 ; }if (!irqchip_in_kernel (vcpu->kvm))
@@ -286,10 +287,19 @@ int vgic_init(struct kvm *kvm)for (i =0 ; i <VGIC_NR_PRIVATE_IRQS ; i++) {struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; -if (dist->vgic_model ==KVM_DEV_TYPE_ARM_VGIC_V3 ) +switch (dist->vgic_model) { +case KVM_DEV_TYPE_ARM_VGIC_V3 : irq->group =1 ; -else + irq->mpidr =kvm_vcpu_get_mpidr_aff (vcpu); +break ; +case KVM_DEV_TYPE_ARM_VGIC_V2 : irq->group =0 ; + irq->targets =1U << idx; +break ; +default : + ret = -EINVAL ; + goto out; + } } }
Signature · 6 lines
2.20.1 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm